Communication device, method, and non-transitory computer-readable storage medium for resource scaling

Abstract

This communication device may comprise: a memory storing instructions; and at least one processor comprising processing circuitry. The instructions, when executed individually or collectively by the at least one processor, may instruct the communication device to: by using an artificial intelligence model, obtain information on a traffic burst of a network slice corresponding to one of a plurality of slice types including eMBB and URLLC; on the basis of the information on the traffic burst of the network slice and information on requirements for the network slice, determine a scaling scheme for a resource to be used in a virtualized network function; and perform resource allocation to the virtualized network function by using the determined scaling scheme. The scaling scheme may include at least one among a first scaling scheme for adjusting the number of processing units, or a second scaling scheme using resizing within the same processing unit.

Description

Communication device, method, and non-transient computer-readable storage medium for scaling resources

[0001] The present disclosure relates to a communication device, a method, and a non-transient computer-readable storage medium for scaling resources.

[0002] To support the communication system, base stations can be connected to the core network. The 5G (5th generation) core network is provided based on a service-based architecture (SBA) centered on network function (NF) services.

[0003] The information described above may be provided as related art for the purpose of aiding understanding of the present disclosure. No claim or determination is made as to whether any of the foregoing may be applied as prior art related to the present disclosure.

[0004] A communication device is provided. The communication device may be configured to perform an auto-scaling function to adaptively adjust resources according to changes in network traffic. The communication device may include a memory comprising one or more storage media for storing instructions. The communication device may include at least one processor comprising processing circuitry. When the instructions are executed individually or collectively by the at least one processor, the communication device may be prompted to obtain information about a traffic burst of a network slice corresponding to one of a plurality of slice types, including eMBB (enhanced mobile broadband) and URLLC (ultra-reliable low latency communication), using an artificial intelligence model. When the instructions are executed individually or collectively by the at least one processor, the communication device may be prompted to determine a scaling method for resources to be utilized in a virtualized network function based on the information about the traffic burst of the network slice and the information about the requirements of the network slice. When the above instructions are executed individually or collectively by the at least one processor, they may cause the communication device to perform resource allocation to the virtualized network function using the determined scaling method. The scaling method may include at least one of a first scaling method for controlling the number of processing units or a second scaling method using resizing within the same processing unit.

[0005] A method is provided. The method may be performed in a communication device configured to perform an auto-scaling function for adaptively adjusting resources according to changes in network traffic. The method may include an operation of obtaining information about a traffic burst of a network slice corresponding to one of a plurality of slice types, including eMBB (enhanced mobile broadband) and URLLC (ultra-reliable low latency communication), using an artificial intelligence model. The method may include an operation of determining a scaling method for resources to be utilized in a virtualized network function based on the information about the traffic burst of the network slice and information about the requirements of the network slice. The method may include an operation of performing resource allocation to the virtualized network function using the determined scaling method. The scaling method may include at least one of a first scaling method for adjusting the number of processing units or a second scaling method using resizing within the same processing unit.

[0006] A non-transient computer-readable storage medium is provided. The non-transient computer-readable storage medium may store one or more programs. The one or more programs may include instructions that cause the communication device to obtain information about a traffic burst of a network slice corresponding to one of a plurality of slice types, including eMBB (enhanced mobile broadband) and URLLC (ultra-reliable low latency communication), by using an artificial intelligence model when executed by the communication device configured to perform an auto-scaling function for adaptively adjusting resources according to changes in network traffic. The one or more programs may include instructions that cause the communication device to determine a scaling method for resources to be utilized in a virtualized network function based on the information about the traffic burst of the network slice and the information about the requirements of the network slice when executed by the communication device. The one or more programs may include instructions that cause the communication device to perform resource allocation to the virtualized network function using the determined scaling method when executed by the communication device. The above scaling method may include at least one of a first scaling method for controlling the number of processing units or a second scaling method that uses resizing within the same processing unit.

[0007] Figure 1a illustrates an example of a communication system.

[0008] Figure 1b illustrates an example of a core network.

[0009] Figure 2 illustrates an example of a network environment using a computing server.

[0010] Figure 3 illustrates an example of the components of a computing server.

[0011] FIGS. 4a and 4b illustrate examples of computing servers that scale resources according to an increase in traffic.

[0012] Figure 5 illustrates an example of the performance of scaling performed on resources.

[0013] FIGS. 6a and 6b illustrate examples of computing servers that scale resources according to an increase in traffic.

[0014] Figure 7 illustrates an example of the performance of scaling performed on resources.

[0015] FIG. 8 illustrates examples of operations of a communication device for performing resource allocation.

[0016] FIG. 9 illustrates the functional configuration of a communication device.

[0017] Throughout the drawings, the same reference numerals will be understood to refer to the same parts, components, and structures.

[0018] The terms used in this disclosure are used merely to describe specific embodiments and are not intended to limit the scope of other embodiments. A singular expression may include a plural expression unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as generally understood by those skilled in the art described in this disclosure. Terms used in this disclosure that are defined in a general dictionary may be interpreted as having the same or similar meaning as they have in the context of the relevant technology, and are not to be interpreted in an ideal or overly formal sense unless explicitly defined in this disclosure. In some cases, even terms defined in this disclosure are not to be interpreted to exclude the embodiments of this disclosure.

[0019] In the various embodiments of the present disclosure described below, a hardware-based approach is described as an example. However, since the various embodiments of the present disclosure include techniques using both hardware and software, the various embodiments of the present disclosure do not exclude a software-based approach.

[0020] Terms used in the following description to refer to signals (e.g., signal, information, message, signaling), terms referring to data types (e.g., list, set, subset), terms for operation states (e.g., step, operation, procedure), terms referring to data (e.g., traffic, packet, user stream, information, bit, symbol, codeword), terms referring to resources (e.g., symbol, slot, subframe, radio frame, subcarrier, RE (resource element), RB (resource block), BWP (bandwidth part), occasion), terms referring to channels, terms referring to network entities, terms referring to device components, etc., are examples provided for the convenience of explanation. Accordingly, the present disclosure is not limited to the terms described below, and other terms having equivalent technical meanings may be used. Additionally, terms such as '...part', '...device', '...object', '...body' used below may refer to at least one shape structure or a unit that processes a function.

[0021] Additionally, in this disclosure, expressions of "greater than" or "less than" may be used to determine whether a specific condition is satisfied or fulfilled; however, this is merely for the purpose of expressing an example and does not exclude descriptions of "greater than" or "less than." Conditions described as "greater than" may be replaced with "greater than," conditions described as "less than" may be replaced with "less than," and conditions described as "greater than and less than" may be replaced with "greater than and less than." Furthermore, "A" to "B" below refer to at least one of elements from A (including A) to B (including B). Below, "C" and / or "D" refers to including at least one of "C" or "D," i.e., {"C", "D", "C" and "D"}.

[0022] This disclosure describes various embodiments using terms used in some communication standards (e.g., 3GPP (3rd Generation Partnership Project), ETSI (European Telecommunications Standards Institute), xRAN (extensible radio access network), O-RAN (open-radio access network), but these are merely illustrative examples. Various embodiments of this disclosure can be easily modified and applied to other communication systems.

[0023] FIG. 1a illustrates an example of a communication system (100).

[0024] Referring to FIG. 1a, the communication system (100) may include a terminal (110). The terminal (110) is a device used by a user and communicates with a base station (120) via a wireless channel. The link from the base station (120) to the terminal (110) is referred to as a downlink (DL), and the link from the terminal (110) to the base station (120) is referred to as an uplink (UL). Additionally, although not shown in FIG. 1a, the terminal (110) and another terminal may communicate with each other via a wireless channel. In this case, the link between the terminal (110) and another terminal (device-to-device link, D2D) is referred to as a sidelink, and the sidelink may be used interchangeably with the PC5 interface. In some other embodiments, the terminal (110) may be operated without user intervention. According to one embodiment, the terminal (110) is a device that performs machine type communication (MTC) and may not be carried by a user. Additionally, according to one embodiment, the terminal (110) may be a narrowband (NB)-Internet of Things (IoT) device. The terminal (110) may be referred to as 'user equipment (UE)', 'customer premises equipment (CPE)', 'mobile station', 'subscriber station', 'remote terminal', 'wireless terminal', 'electronic device', or 'user device', or other terms having an equivalent technical meaning. Hereinafter, in describing the mobility of the terminal of the present disclosure, the terminal (110) is referred to as a UE, but it is understood that other terms may be used depending on the communication environment or embodiment.

[0025] A base station (120) is a network infrastructure that provides wireless access to a terminal (110). The base station (120) has coverage defined based on the distance over which it can transmit signals. In the sense of providing an access network (AN) in addition to being a base station, the base station (120) may be referred to as a 'RAN node', 'network node', or 'access point (AP)', or in the sense of supporting radio access technology (RAT), it may be referred to as an 'eNodeB (eNB)', '5G node (5th generation node)', 'next generation nodeB (gNB)', 'wireless point', 'transmission / reception point (TRP)', or other terms having an equivalent technical meaning.

[0026] Although a single network entity is illustrated in FIG. 1a, embodiments of the present disclosure are not limited thereto. For example, a base station (120) may be implemented in a distributed deployment according to a central unit (CU) configured to perform the functions of the upper layers (e.g., PDCP, RRC) of the access network and a distributed unit (DU) configured to perform the functions of the lower layers (e.g., RLC (radio link control), MAC (media access control), PHY (physical)). For example, to reduce installation costs and increase available cell coverage, the base station (120) may be implemented with geographically distributed DUs and RUs.

[0027] The core network (133) may be configured to connect the base station (120) to the data network. The core network (133) may include various network entities for managing mobility, session management, policy management, and / or data network connectivity, and each network entity may represent a node defining a specific network function. For example, the core network (133) may be referred to as an EPC (evolved packet core) (or EPS (evolved packet system)) as a set of network entities for an LTE access network. For example, the core network (133) may be referred to as a 5GC (5th generation core) (or 5GS (5th generation system)) as a set of network entities for an NR access network. As an example of the core network (133), the 5GC is described in detail through FIG. 1b.

[0028] FIG. 1b illustrates an example of a core network (e.g., a core network (133)).

[0029] Referring to FIG. 1b, the UE exemplifies the terminal (110) of FIG. 1a, and the RAN Node exemplifies the base station (120) of FIG. 1b. Network entities of the core network (133) may include various network functions (NFs). The terminal (110) and the base station (120) may communicate with the NFs of the core network. For example, the core network (133) may include an access and mobility management function (AMF) (130), a session management function (SMF) (140), a user plane function (UPF) (150), a policy and charging function (PCF) (170), and a unified data management function (UDM) (180).

[0030] The AMF (130) provides functions for connection and mobility management at the UE (e.g., terminal (110)) level, and can basically be connected to one AMF per UE.Specifically, the AMF (130) provides signaling between CN (e.g., core network (133)) nodes for mobility between 3GPP access networks, termination of radio access network (RAN) control plane (CP) interfaces (i.e., N2 interfaces), termination of NAS signaling (N1), NAS (non-access stratum) signaling security (NAS ciphering and integrity protection), access stratum (AS) security control, registration management (registration area management), connection management, idle mode UE reachability (including control and execution of paging retransmission), mobility management control (subscription and policy), support for intra-system mobility and inter-system mobility, support for network slicing, SMF selection, lawful intercept (for AMF events and interfaces to LI systems), and sessions between the UE and the SMF (e.g., SMF (140)). It may support functions such as providing session management (SM) message delivery, a transparent proxy for SM message routing, access authentication, access authorization including roaming authorization checks, providing SMS (short message service) message delivery between the UE and the SMSF (short message service function), a security anchor function (SAF) and / or security context management (SCM). Some or all of the functions of the AMF (130) may be supported within a single instance of a single AMF.According to some examples, the AMF (130) may select an NF from among a plurality of NFs. For example, the AMF (130) may perform SMF selection or PCF (policy charging function) selection.

[0031] The SMF (140) can provide session management functions. If a UE (e.g., terminal (110)) has multiple sessions, each session can be managed by a different SMF. Specifically, the SMF (140) can support functions such as session management (e.g., session establishment, modification, and termination, including maintaining a tunnel between the UPF (150) and the AN node (e.g., base station (120)), UE IP address allocation and management (optional authentication), selection and control of UP functions, setting up traffic steering to route traffic from the UPF to an appropriate destination, termination of the interface toward policy control functions, enforcement of the control portion of policies and QoS (quality of service), lawful interception (for SM events and interfaces to LI systems), termination of the SM portion of NAS messages, downlink data notification, initiator of AN-specific SM information (transmitted to the AN node via N2 through the AMF), determination of the session's SSC mode (e.g., SSC mode 2, SSC mode 3), and roaming functions. According to embodiments, UPF selection may be performed by the SMF (140). Some or all of the functions of the SMF (140) may be supported within a single instance of the SMF. According to some embodiments, the SMF (140) may select an NF from among a plurality of NFs. For example, the SMF (140) may perform UPF selection or PCF selection.

[0032] The SMF (140) can support functions related to the management of GTP-U (general packet radio service tunneling protocol - user plane) tunnels. For example, the SMF (140) can manage a GTP-U tunnel between a base station (120) and a UPF (150). The GTP-U tunnel can be used to transmit user plane data between the base station (120) and the UPF (150).

[0033] The SMF (140) can directly transmit and receive signals with the UPF (150), but signal processing with the terminal (110) and base station (120) may require the support of the AMF (130).

[0034] UPF (150) can transmit downlink PDUs received from DN (155) to terminal (110) via base station (120), or transmit uplink PDUs received from terminal (110) to DN (155) via base station (120). Specifically, the UPF (150) can support functions such as an anchor point for intra / inter RAT mobility, an external PDU session point for interconnection to a data network, packet routing and forwarding, packet inspection and policy rule enforcement in the user plane, lawful intercept, traffic usage reporting, an uplink classifier to support routing of traffic flows to a data network, a branching point to support multi-homed PDU sessions, QoS handling for the user plane (e.g., packet filtering, gating, uplink / downlink rate enforcement), uplink traffic verification (SDF mapping between service data flow (SDF) and QoS flow), transport level packet marking within the uplink and downlink, downlink packet buffering, and downlink data notification triggering. Some or all of the functions of UPF (150) can be supported within a single instance of UPF.

[0035] DN (155) represents an internet network for accessing an external communication network. For example, DN (155) refers to operator services, internet access, or third-party services. DN (155) transmits a downlink protocol data unit (PDU) to UPF (150) or receives a PDU transmitted from the terminal (110) from UPF (150).

[0036] The PCF (170) can receive information about packet flow from the application server and provide functions to determine policies such as mobility management and session management. Specifically, the PCF (170) supports functions such as supporting a unified policy framework to control network behavior, providing policy rules so that CP function(s) (e.g., AMF (130), SMF (140), etc.) can enforce policy rules, and frontend implementations to access relevant subscription information for policy decisions within the user data repository (UDR).

[0037] The UDM (180) stores user subscription data, policy data, etc. The UDM (180) may include two parts: an application front end (FE) and a user data store (UDR).

[0038] The core network (133) may include various NFs in addition to the network entities / network functions described above. For example, the core network (133) may include NSSF (network slice selection function) (191), NEF (network exposure function) (192), NRF (network repository function) (193), NSSAAF (network slice-specific authentication and authorization) (194), AUSF (authentication server function) (195), AF (application function) (196), SCP (service communication proxy) (197), and NSACF (network slice admission control function) (198).

[0039] NSSF (191) can support the function of selecting a set of network slice instances to provide service to the terminal (110). NSSF (191) can determine the allowed network slice selection assistance information (NSSAI) and, if needed, determine the mapping for the subscribed single-NSSAI. NSSF (191) can determine the configured NSSAI and, if needed, determine the mapping for the subscribed single-NSSAI. NSSF (191) can determine the set of AMFs used to service the UE, or determine them by querying the NRF for a list of AMFs based on the configuration. NSSF (191) can provide support for network slice limits and network slice instance limits based on NWDAF analysis.

[0040] NEF (192) may provide means for securely exposing, for example, third party, internal exposure / re-exposure, application functions, services and capabilities for edge computing provided by 3GPP NFs. NEF (192) receives information from other NFs or based on capabilities exposed to other NFs. NEF (192) may store the received information as structured data using a standardized interface to a data storage network function. The stored information may be re-exposed by NEF (192) to other NFs and AFs (e.g., AF (196)) and used for other purposes such as analysis.

[0041] NRF (193) can support service discovery functions. NRF (193) can receive NF discovery requests from NF instances and provide information about discovered NF instances to the NF instances. Additionally, NRF (193) maintains available NF instances and the services they support. NF discovery and NF selection can be performed on a specific NF on its own or by referring to NRF (193).

[0042] NSSAAF (194) can support authentication and authorization functions per network slice.

[0043] AUSF (195) stores data for authentication of the UE (e.g., terminal (110)).

[0044] AF (196) can interact with the 3GPP core network to provide services (e.g., support for application impact on traffic routing, access to network capability exposure, and interaction with policy frameworks for policy control).

[0045] SCP (197) can perform functions such as indirect communication, delegated discovery, message delivery and routing to target NF / NF services, message delivery and routing to next-hop SCPs, communication security (e.g., NF service consumer authorization to access NF service producer APIs), load balancing, monitoring, and overload control. SCP (197) can be deployed in a distributed manner. For example, there may be two or more SCPs in a communication path between NF services. Messages can be routed through SCPs. For example, to enable the routing of said messages (i.e., next SCP hop discovery), SCP (197) can register a profile with an NRF (e.g., NRF (193)). As another example, SCP (197) can use a local configuration. Some or all of the functions of SCP (197) can be supported within a single instance of a single AMF.

[0046] NSACF (198) can monitor and control the number of registered UEs per network slice for network slices to which network slice admission control is applied.

[0047] In 3GPP systems, conceptual links connecting NFs within a 5G system are defined as reference points or interfaces. The following is an example of a reference point included in the 5G system architecture depicted in Fig. 1b.

[0048] - N1: Reference point or interface between terminal (110) and AMF (130)

[0049] - N2: Reference point or interface between base station (120) and AMF (130)

[0050] - N3: Reference point or interface between base station (120) and UPF (150)

[0051] - N4: Reference point or interface between SMF (140) and UPF (150)

[0052] - N5: Reference point or interface between PCF (170) and AF (196)

[0053] - N6: Reference point or interface between UPF (150) and DN (155)

[0054] - N7: Reference point or interface between SMF (140) and PCF (170)

[0055] - N8: Reference point or interface between UDM (180) and AMF (130)

[0056] - N9: Reference point or interface between two core UPFs (e.g., UPF(150)).

[0057] - N10: Reference point or interface between UDM (180) and SMF (140)

[0058] - N11: Reference point or interface between AMF (130) and SMF (140)

[0059] - N12: Reference point or interface between AMF (130) and AUSF (195)

[0060] - N13: Reference point or interface between UDM (180) and AUSF (195)

[0061] - N14: Reference point or interface between two AMFs (e.g., AMF (130)).

[0062] - N15: For non-roaming scenarios, a reference point between PCF (170) and AMF (130); for roaming scenarios, a reference point or interface between PCF (170) and AMF (130) within the visited network.

[0063] Instead of implementing the network nodes required in a radio access network (RAN) using physical hardware equipment, a virtualized RAN (vRAN) is being used to virtualize the necessary network functions. Virtualization enables flexible scalability and rapid, continuous development by transitioning distributed units (DU) and centralized units (CU) from dedicated hardware to software components. Through this virtualization, the network can easily meet the evolving demands of new and existing services while minimizing the impact on deployment and operational costs. For example, virtualized network functions can be implemented as containerized network functions (CNFs), which are decoupled from hardware. Containerized network functions can be referred to as cloud-native network functions. A communication device executing containerized network functions (e.g., a server device, the computing server (202) in FIG. 2)) may have multiple processing units (e.g., pods) containing one or more containers to provide a microservices-type architecture. The computing resources, such as CPU (central processing unit) cores or memory, occupied by each processing unit may be independent or different. In the communication device, processing units may be expanded according to capacity requirements, and resources in the communication device (e.g., computing resources, network resources) may be scaled in or scaled out through the addition of new processing units or the removal of existing processing units.

[0064] As mentioned above, unlike existing hardware-based RANs, vRAN can provide a more flexible and efficient network structure through software and virtualization. Scaling in vRAN may involve processes for effectively managing network resources and optimizing the performance of wireless access networks. Based on the flexibility of virtualization, vRAN can support various scaling methods. Such scaling is carried out in various aspects, such as network resizing, responding to traffic fluctuations, and the efficient allocation of resources. To explain scaling, necessary terms may be defined. Vertical scaling refers to a method of increasing or decreasing resources within a single communication unit or a single containerized network function (cNF). For example, vertical scaling can be referred to as a method of allocating resources to enhance the performance of existing instances (e.g., processing units, containers, pods) for a network function. For example, vertical scaling can be referred to as a method of resource allocation performed by utilizing resource resizing within the same processing unit. In the case of vertical scaling, if network traffic or the number of users increases, the amount of resources allocated to cNF may increase, and conversely, if they decrease, the amount of resources allocated to cNF may decrease. For example, the amount of traffic loss when vertical scaling is performed may be less than the amount of traffic loss when horizontal scaling, which will be described later, is performed. In this disclosure, traffic may be referred to as network traffic and / or a term having an equivalent technical meaning.

[0065] Horizontal scaling refers to a method of adjusting the performance of an entire system by adding or removing communication devices or cNFs. For example, horizontal scaling can be referred to as a method of allocating resources to add or remove instances (e.g., processing units, containers, pods) for network functions. For example, horizontal scaling can be referred to as a method in which resource allocation is performed by adjusting the number of processing units. In the case of horizontal scaling, resources can be optimized by creating new cNFs when network traffic or the number of users increases, and removing unnecessary cNFs when they decrease. A communication device (or system) can use horizontal scaling to distribute the load (e.g., traffic load) to processing units. The communication device can relieve load by distributing the load. For example, horizontal scaling can be related to high availability.

[0066] Although vertical scaling and horizontal scaling are described in this disclosure as examples of scaling methods, the scaling methods are not limited to two types. For example, there may be hybrid scaling in which both vertical scaling and horizontal scaling are performed. Furthermore, vertical scaling can also be understood as a different scaling method depending on the amount of resources being resized. In addition, horizontal scaling can also be understood as a different scaling method depending on the number of processing units being added or removed.

[0067] Determining the optimal amount of resources to be allocated to the cNF is a critical issue when performing scaling in vRAN. If scaling is not performed appropriately for resource requirements that vary with traffic volume, under-provisioning or over-provisioning may occur. For example, if computing resources lower than the required amount are deployed to the cNF (under-provisioning), costs may be incurred due to traffic loss resulting from the inability to handle traffic. Conversely, if computing resources higher than the required amount are deployed to the cNF (over-provisioning), costs may be incurred due to energy loss from operating unnecessary computing resources. Therefore, scaling techniques are required that can minimize network costs, such as traffic loss and energy loss resulting from under-provisioning and / or over-provisioning.

[0068] As the number of containers supporting network functions in a wireless access network environment increases, the complexity of the containerized network functions may increase. For example, an increase in the complexity of containerized network functions may include an increase in the difficulty of managing the containerized network functions. As the complexity of the containerized network functions increases, communication devices executing the containerized network functions (e.g., server devices, computing servers (202) of FIG. 2) may require automation of scaling to minimize the network costs.

[0069] In addition, the communication device (e.g., server device, computing server (202) of FIG. 2) may require automation of scaling to meet the requirements of the communication service (e.g., service level agreement (SLA)) despite the dynamic and unpredictable nature of the traffic pattern. Furthermore, even if the communication device is implemented in various carrier infrastructures (e.g., public cloud, edge computing, resource-constrained micro data centers), automation of scaling may be required to meet the requirements of the communication service.

[0070] In the present disclosure, techniques for auto-scaling to adaptively adjust (or configure) resources according to costs (e.g., scaling costs), changes in traffic (or traffic load), types of applications according to network slices, and / or requirements (or constraints) of the infrastructure may be described. A communication device according to embodiments of the present disclosure may determine a scaling method according to costs, changes in traffic, types of applications according to network slices, and / or requirements of the infrastructure. The scaling method may include vertical scaling, horizontal scaling, and / or hybrid scaling that combines vertical and horizontal scaling. According to embodiments of the present disclosure, the stability of communication services may be increased and efficient utilization of resources may be possible.

[0071] Although a 5G communication environment is described as an example in FIG. 1b, this description does not limit the scope of the communication environments of the embodiments of the present disclosure. The technical principles according to the embodiments of the present disclosure may also be applied to 4G (4th generation), 6G (6th generation), and communication technologies (or network environments) after 6G.

[0072] FIG. 2 illustrates an example of a network environment (200) using a computing server.

[0073] Referring to FIG. 2, the network environment (200) may include a wireless communication device (201) and / or a computing server (202). The wireless communication device (201) may include network equipment for providing a wireless communication environment. For example, the wireless communication device (201) may include a radio unit (RU) and / or a massive MIMO unit (MMU). The wireless communication device (201) may provide a cell to a terminal (e.g., terminal (110)). For example, the wireless communication device (201) may be located at a cell site to provide cell coverage. Although described based on one wireless communication device (201), embodiments of the present disclosure are not limited thereto. The computing server (202) described below may provide an access network over multiple cell sites through multiple wireless communication devices.

[0074] The computing server (202) may be configured to provide network functions. For network functions, the descriptions of network functions (NFs) in FIG. 1b may be referenced. For example, network functions may include network functions for access networks. For example, the computing server (202) may include a distributed unit (DU). In terms of providing virtualized network functions, the DU of the computing server (202) may be referred to as a virtualized DU (vDU). As an example, but not limited to, the computing server (202) may include a centralized unit (CU) (or control unit). In terms of providing virtualized network functions, the CU of the computing server (202) may be referred to as a virtualized CU (vCU). The computing server (202) may be connected to a wireless communication device (201) located at a cell site. For example, the computing server (202) may be implemented in the cloud for low latency. A computing server (202) can control a wireless communication device (201). As a non-limiting example, the computing server (202) can control the wireless communication device (201) on a cell site. The computing server (202) may be referred to as an edge cloud in terms of controlling the wireless communication device (201) on a cell site.

[0075] The computing server (202) may be configured to provide virtualized network functions. For example, the computing server (202) may provide network functions using a virtual machine. The computing server (202) may execute virtualized network functions in a virtual machine. For example, the computing server (202) may provide network function(s) based on virtualized network functions. For example, a virtualized network function may be implemented as a containerized network function (cNF). A container may be referred to as a virtualized execution environment. A container may be referred to as a unit that packages and executes software components of a network function. The computing server (202) may have multiple processing units containing one or more containers. A processing unit (e.g., a pod) may be referred to as the smallest unit that executes a container in the computing server (202).

[0076] The computing server (202) can perform resource scaling for the network functions it provides. According to one embodiment, the computing server (202) may have information about resource status. The information about resource status may include information about which network functions are enabled and which network functions are disabled, and / or information about the amount of resources allocated to the enabled network functions. According to one embodiment, the computing server (202) may have information about channels. The information about channels may include information about channel quality (e.g., quality indicators), information about load (e.g., number of connected terminals, traffic volume, cell capacity), and / or information about modulation and coding methods. The computing server (202) can scale resources using the information about resource status and / or the information about channels.

[0077] Although not illustrated in FIG. 2, the computing server (202) may be connected to an external communication device (e.g., a server corresponding to the computing server (202)). For example, the external communication device may be configured to provide network functions different from those provided by the computing server (202). For example, the external communication device may provide a virtualized UPF (e.g., UPF (150)) and / or a virtualized AMF (e.g., AMF (130)). Based on the computing server (202) and at least one external communication device connected to the computing server (202), a core network (e.g., core network (133)) may be implemented.

[0078] FIG. 3 illustrates an example of a component of a computing server. Terms such as '...part', '...unit' used below refer to a unit that processes at least one function or operation, and this may be implemented as hardware or software, or a combination of hardware and software.

[0079] Referring to FIG. 3, the computing server (202) may include a control unit (301), a scaling unit (303), and / or a vDU (virtualized DU) (305). The components of the computing server (202) shown in FIG. 3 are merely exemplary components, and the embodiments of the present disclosure are not limited to the descriptions of the components of the computing server (202) shown in FIG. 3. For example, even if some of the components of the computing server (202) are omitted or other components are added, any device configured to perform resource scaling functions (e.g., computing device, server device, communication device) may be understood as an embodiment of the present disclosure. As an example, but not limited to, the computing server (202) may include a vDU (305) and other virtualized network functions.

[0080] The control unit (301) may be used to manage the components of the computing server (202). For example, the control unit (301) may be used to manage virtualized network functions (e.g., vDU (305)). For example, the control unit (301) may be used to deploy and monitor virtualized network functions. The control unit (301) may be used to recover from failures of virtualized network functions. For example, the control unit (301) may include an orchestrator platform (e.g., Kubernetes). An orchestrator platform may be referred to as a software system for deploying or managing multiple containers or virtualized network functions.

[0081] The scaling unit (303) may be used to allocate resources (e.g., computing resources, network resources) to virtualized network functions. For example, the scaling unit (303) may be used to allocate resources to vDUs (305). For example, the scaling unit (303) may be used to determine how to allocate resources to vDUs (305). The scaling unit (303) may perform resource allocation dynamically according to changes in traffic (or traffic load).

[0082] The computing server (202) can determine a scaling method based on cost (e.g., scaling cost) by using the scaling unit (303). For example, the computing server (202) can determine a scaling method that considers licensing costs by using the scaling unit (303). For example, the computing server (202) can determine a scaling method that balances the performance and cost of network functions by using the scaling unit (303).

[0083] The computing server (202) can predict irregular traffic bursts using the scaling unit (303). For example, the computing server (202) can determine or provide a scaling method based on the traffic burst. For example, the computing server (202) can adaptively determine or provide a scaling method based on the traffic burst.

[0084] The computing server (202) may use the scaling unit (303) to determine or provide a scaling method according to orchestrator requirements (or constraints). Orchestrator requirements may be referred to as conditions that the orchestrator platform must consider when deploying or managing containerized network functions (cNF). For example, orchestrator requirements may include the availability of processing units (e.g., nodes) for executing network functions, storage space for network functions, bandwidth for network functions, and / or geographical distribution for network functions, but the embodiments are not limited thereto. The computing server (202) may use the scaling unit (303) to determine or provide a scaling method according to the type of application associated with the network slice. For example, the application may be referred to as a service or software that operates using a specific network slice. For example, the application may be associated with a network slice instance. For example, the application may be referred to as an end-user service that utilizes the network slice.

[0085] The scaling unit (303) may include a traffic prediction module (310), a cost analysis module (320), an application analysis module (330), an orchestrator analysis module (340), and / or a scaling decision module (350).

[0086] The traffic prediction module (310) can be used to predict or determine the type of traffic burst. A traffic burst can be referred to as a phenomenon where traffic surges. If a traffic burst is not properly responded to, problems such as network congestion, traffic loss (or packet loss), and / or service delay may occur. The traffic prediction module (310) can obtain information about the traffic burst. For example, the type of traffic burst can be determined based on the information about the traffic burst. For example, the information about the traffic burst may include the probability of a traffic burst and / or the duration of the traffic burst. For example, the traffic prediction module (310) can trigger vertical scaling based on the duration of a traffic burst being shorter than a reference time. For example, the traffic prediction module (310) can trigger horizontal scaling based on the duration of a traffic burst being longer than a reference time.

[0087] Vertical scaling can be referred to as a scaling method that changes the amount of resources allocated to existing instances (e.g., processing units, containers, pods). Latency when vertical scaling is performed can be shorter than latency when horizontal scaling is performed. For relatively short traffic bursts, vertical scaling may be more advantageous than horizontal scaling in terms of latency. Horizontal scaling can be referred to as a scaling method that deploys or removes instances (e.g., processing units, containers, pods) for virtualized network functions (e.g., vDU(305)). Because horizontal scaling is more advantageous than vertical scaling in terms of scalability and stability, horizontal scaling may be more suitable than vertical scaling for relatively long traffic bursts.

[0088] The traffic prediction module (310) may include an artificial intelligence model. For example, the artificial intelligence model may be generated through machine learning. For example, the artificial intelligence model may be trained to determine the type of traffic burst based on acquiring traffic data. For example, the artificial intelligence model may be trained to determine the type of traffic burst by analyzing the workload (e.g., traffic throughput) of the computing server (202) (or vDU (305)). For example, the artificial intelligence model may be trained using previous workload data of the computing server (202) (or vDU (305)). For example, the artificial intelligence model may determine or predict the type of traffic burst after the reference time because it was trained using workload data prior to the reference time. The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. For example, an artificial intelligence model may include an artificial neural network model comprising multiple layers and / or operations (or computations).As a non-limiting example, an artificial intelligence model may include one of FNN (feedforward neural network), DNN (deep neural network), CNN (convolutional neural network), R-CNN (region with convolution neural network), RPN (region proposal network), RNN (recurrent neural network), S-DNN (stacking-based deep neural network), S-SDNN (state-space dynamic neural network), deconvolution network, RBM (restricted Boltzmann machine), DBN (deep belief network), BRDNN (bidirectional recurrent deep neural network), deep Q-networks, fully convolutional network, LSTM (long short-term memory) network, and classification network, or a combination of two or more of these. However, it is not limited thereto.

[0089] The cost analysis module (320) may be used to evaluate, calculate, obtain, or identify costs associated with a scaling method (e.g., scaling costs). For example, the cost analysis module (320) may be used to evaluate a scaling method based on the cost of using a processor (e.g., CPU (central processing unit), GPU (graphic processing unit)), the cost of using memory (e.g., non-volatile memory, volatile memory), the cost of using an SR-IOV (single root input / output virtualization) device, and / or the cost of using a license (e.g., a license to use additional features in software). The cost analysis module (320) may be used to balance the performance and economic efficiency of a scaling method. As an example, but not limited to, the cost analysis module (320) may be used to determine or select the optimal scaling method among candidate scaling methods based on cost. For example, the optimal scaling method may be referred to as the scaling method that requires the least cost without violating requirements (or constraints) (e.g., SLA, QOS).

[0090] The application analysis module (330) can be used to analyze applications related to network slices. The application analysis module (330) can analyze applications related to network slices to identify the scaling methods that the applications can support. For example, the application analysis module (330) can identify the requirements of applications related to network slices. For example, by analyzing applications related to network slices, the application analysis module (330) can identify the acceptable downtime of the applications. For example, the application analysis module (330) can determine a scaling method for minimal downtime using the acceptable downtime. For example, a first application according to a network slice may support horizontal scaling among vertical scaling and horizontal scaling. For example, a second application according to a different network slice may support vertical scaling and horizontal scaling.

[0091] The orchestrator analysis module (340) can be used to determine a scaling method based on orchestrator requirements. For example, the orchestrator analysis module (340) can obtain information about requirements from the orchestrator platform within the control unit (301).

[0092] The scaling decision module (350) may be used to determine a scaling method using the output data of the traffic prediction module (310), the output data of the cost analysis module (320), the output data of the application analysis module (330), and / or the output data of the orchestrator analysis module (340). The computing server (202) may scale resources for virtualized network functions (e.g., vDU (305)) according to the output data of the scaling decision module (350).

[0093] vDU (305) may be referred to as a software component to support the functions of the DU. vDU (305) may be implemented as a containerized network function. vDU (305) may be configured to control the RU (e.g., wireless communication device (201)).

[0094] In FIG. 3, the computing server (202) is shown to include a control unit (301), a scaling unit (303), and / or a vDU (305), but the embodiments are not limited. According to one embodiment, the control unit (301), the scaling unit (303), and / or the vDU (305) may be included in separate communication devices, and each of the communication devices may be implemented in a state where they are connected to each other.

[0095] FIGS. 4a and 4b illustrate an example of a computing server that scales resources according to an increase in traffic. For example, an increase in traffic may be referred to as a traffic burst. The scaling is performed by reducing or increasing the number of components of the network functions being executed, and the amount of computing resources allocated to newly added network functions may be adaptively set. In this disclosure, a network function may represent a containerized network function and may represent a node in the form of software implemented independently of hardware. A network function may be referred to as a processing unit, pod, network function container, network container, virtualized network node, virtualized container, virtualized network function, containerized network function, CNF, VNF, flavor, and / or equivalent technical terms.

[0096] Referring to FIG. 4a, the network environment (401) may include a wireless communication device (201), switches (e.g., a core switch (421), spine switches (423), leaf switches (425)), a computing server (202), and / or a communication device (460).

[0097] Network slice technology may be applied to a wireless communication device (201) and a computing server (202). Network slices may have types optimized according to various services. For example, network slices may include mMTC (massive machine type communications) slices, eMBB (enhanced mobile broadband) slices, and / or URLLC (ultra-reliable low latency communication) slices. For example, mMTC slices may be used for connecting massive IoT (internet of things) devices. For example, eMBB slices may be used for high bandwidth and high-speed data transmission. For example, eMBB slices may be characterized by high throughput and / or dynamic traffic. For example, URLLC slices may be used for ultra-low latency and high reliability. For example, URLLC slices may be characterized by minimizing traffic loss and / or strict reliability. For example, application requirements related to eMBB slices may allow for a certain degree of flexibility regarding traffic loss, whereas application requirements related to URLLC slices may indicate that there will be no traffic loss at all. For example, depending on the application requirements related to eMBB slices, horizontal scaling may be determined over vertical scaling in response to traffic bursts associated with the eMBB slice. For example, horizontal scaling can be achieved by adding a replica of a processing unit that supports virtualized network functions.For example, depending on the application requirements related to URLLC slicing, vertical scaling may be determined over horizontal scaling in response to traffic bursts caused by the URLLC slicing. For example, vertical scaling can be achieved by increasing the amount of resources for processing units that support virtualized network functions.

[0098] Fronthall traffic (411) can be transmitted from a wireless communication device (201) to a vDU (305) within a computing server (202). For example, fronthall traffic (411) can be transmitted from the wireless communication device (201) to the vDU (305) through switches (e.g., a core switch (421), spine switches (423), leaf switches (425)). For example, the core switch (421) may be referred to as a switch connected to the spine switches (423) and used to centrally manage traffic within the network. For example, the core switch (421) may be used to manage traffic flowing between the wireless communication device (201), the computing server (202), and / or the communication device (460). For example, the communication device (460) may be configured to provide a virtualized CU (vCU). For example, spine switches (423) may be referred to as intermediate layer switches connected to core switches (421) and leaf switches (425). For example, leaf switches (425) may be referred to as switches located at the outermost edge of the data center connected to server devices (e.g., computing servers (202)). The maximum allowable bandwidth of the interface between the switches (e.g., core switches (421), spine switches (423), leaf switches (425)) may have a specified value (e.g., 10 Gbps (gigabits per second)). The value of fronthall traffic (411) in the network environment (401) may be smaller than the specified value.

[0099] The computing server (202) may include a control unit (301) and / or a vDU (305). The vDU (305) may have a first node (431), a second node (433), a third node (435), and / or a fourth node (437), but the embodiments are not limited. Each of the nodes (431, 433, 435, 437) may be referred to as a server for executing each of the processing units (441, 443, 445, 447). For example, each of the nodes (431, 433, 435, 437) may include a physical server and / or a virtualized server. For example, the first node (431) may be used to execute the first processing unit (441). For example, the first processing unit (441) may include a virtualized module used to collect or manage data obtained from a wireless communication device (201) (e.g., a radio unit (RU)). For example, the first processing unit (441) may include data ingestion processing (DIP) and / or data management processing (DMP). For example, the second node (433) may be used to execute the second processing unit (443). For example, the second processing unit (442) may include data plane processing (DPP) (444). For example, the DPP (444) may be used for real-time processing of user data. For example, the DPP (444) may be used to execute baseband functions of the radio link control (RLC) / media access control (MAC) / physical (PHY) layer. For example, the third node (435) may be used to execute the third processing unit (445). For example, the fourth node (437) may be used to execute the fourth processing unit (447).

[0100] The computing server (202) can receive or acquire fronthall traffic (411) using the second node (433) among the nodes (431, 433, 435, 437) of the vDU (305). For example, the computing server (202) can process the fronthall traffic (411) using the DPP (444). For example, the fronthall traffic (411) can be processed by the DPP (444) alone because the value of the fronthall traffic (411) is smaller than the value of the maximum allowable bandwidth of the interface (e.g., 10 Gbps (gigabits per second)). For example, the value of the fronthall traffic (411) can be composed of the sum of the traffic value of the mMTC slice (e.g., 2 Gbps), the traffic value of the eMBB slice (e.g., 3 Gbps), and the traffic value of the URLLC slice (e.g., 4 Gbps).

[0101] According to one embodiment, a computing server (202) can transmit mid-haul traffic (412) to a communication device (460) using a DPP (444) within a vDU (305). For example, the communication device (460) may be configured to provide a virtualized CU (vCU). For example, the mid-haul traffic (412) may flow through a wireless access network (WAN) between the DPP (444) and the communication device (460).

[0102] Referring to FIG. 4b, the fronthole traffic (451) in the network environment (402) may differ from the fronthole traffic (411) of FIG. 4a. For example, the value of the traffic in the eMBB slice of the fronthole traffic (451) (e.g., 12 Gbps) may be greater than the value of the maximum allowable bandwidth of the interface (e.g., 10 Gbps). Because the value of the traffic in the eMBB slice of the fronthole traffic (451) (e.g., 12 Gbps) is greater than the value of the maximum allowable bandwidth of the interface (e.g., 10 Gbps), the fronthole traffic (451) may not be able to be processed by the DPP (444) of the vDU (305) alone.

[0103] The computing server (202) can scale resources using the scaling unit (303). For example, the computing server (202) can determine the scaling method based on costs (e.g., scaling costs), changes in traffic (or traffic load), the type of application according to the network slice, and / or the requirements of the infrastructure. For example, the scaling unit (303) of the computing server (202) can determine horizontal scaling based on the value of the maximum allowable bandwidth of the interface. For example, the scaling unit (303) of the computing server (202) can determine horizontal scaling based on the determination that the value of traffic in the eMBB slice is greater than the value of the maximum allowable bandwidth of the interface. For example, the computing server (202) can create or add a DPP (446), which is a replica of the DPP (444), to the third processing unit (445). For example, the computing server (202) can process fronthole traffic (451) using DPP (444) and DPP (446).

[0104] According to one embodiment, scaling performed in response to an increase in fronthaul traffic (451) (e.g., a traffic burst) may be more cost-effective than resource allocation that provides the maximum number of DPPs (e.g., DPP (444), DPP (446)) from the time the vDU (305) is deployed. For example, if computing resources higher than the computing resource requirements are allocated to the vDU (305) (over-provisioning), energy loss costs may occur due to the operation of unnecessary computing resources.

[0105] According to one embodiment, in the case of scaling performed in response to an increase in fronthaul traffic (451) (e.g., a traffic burst), traffic loss may occur in vDU (305). For example, if the time of increase in fronthaul traffic (451) is earlier than the time of scaling, traffic loss may occur in vDU (305). The scaling unit (303) of the computing server (202) may perform scaling before the time of increase in fronthaul traffic (451) to prevent or minimize the traffic loss. For example, the traffic prediction module (e.g., traffic prediction module (310)) of the scaling unit (303) may predict changes in fronthaul traffic (e.g., fronthaul traffic (411), fronthaul traffic (451)) using an artificial intelligence model. For example, the computing server (202) can scale resources based on a determination that fronthaul traffic (e.g., fronthaul traffic (411), fronthaul traffic (451)) increases using the scaling unit (303). For example, the computing server (202) can determine the type of traffic burst using the scaling unit (303) and scale resources before the traffic burst occurs. For example, the computing server (202) can minimize traffic loss by performing scaling based on a prediction of changes in fronthaul traffic (451) before the point of increase in fronthaul traffic (451). For example, by minimizing traffic loss, the quality of scaling can be enhanced.

[0106] According to one embodiment, a computing server (202) can transmit mid-haul traffic (452) to a communication device (460) using a DPP (444) and / or a DPP (446) within a vDU (305). For example, the communication device (460) may be configured to provide a virtualized CU (vCU). For example, mid-haul traffic (452) may flow through a wireless access network (WAN) between the DPP (444) and the communication device (460). For example, mid-haul traffic (452) may flow through a WAN between the DPP (446) and the communication device (460).

[0107] Figure 5 illustrates an example of the performance of scaling performed on resources.

[0108] Referring to FIG. 5, the graph (501) may represent the traffic request volume of an eMBB slice over time and / or the resource allocation volume according to the traffic request volume of an eMBB slice. The horizontal axis of the graph (501) may represent time. Among the vertical axes of the graph (501), the left vertical axis may represent the traffic request volume of an eMBB slice, and among the vertical axes, the right vertical axis may represent the resource allocation volume (e.g., the number of replicas of virtualized network functions).

[0109] Data (510) represents the distribution of traffic request volume of an eMBB slice over time. For example, the traffic request volume may correspond to a traffic load. Data (510) may represent various values ​​over time. For example, data (510) may have a maximum value at 6:00 AM and a minimum value at 3:00 PM.

[0110] Line (520) may indicate a case where the computing server (e.g., computing server (202)) does not dynamically allocate resources based on the traffic request volume of the eMBB slice. The computing server (202) may allocate a specified resource (e.g., a resource corresponding to 10 replicas of DPP (444)) to a virtualized network function (e.g., vDU (305)) over the entire time interval of the graph (501).

[0111] Line (530) may represent a case where, according to an embodiment of the present disclosure, the computing server (202) dynamically allocates resources based on the traffic request volume of the eMBB slice. The computing server (202) may allocate more resources as the traffic request volume of the eMBB slice increases. There may be assumptions for line (530) of the graph (501) of FIG. 5. The computing server (202) may perform resource scaling based on costs (e.g., scaling costs). For example, the computing server (202) may perform a scaling method in which the optimal cost is calculated while ensuring an acceptable quality of service (QOS). For example, the cost may be calculated as the sum of the cost of using processors (e.g., CPU, GPU), the cost of using storage (e.g., memory), the cost of licenses, and / or the cost of service level agreement (SLA) penalties for traffic loss. For example, the SLA may include a minimum value of traffic loss to ensure an acceptable QOS. For example, the computing server (202) can perform scaling such that the traffic loss is greater than the minimum value of the traffic loss. For example, the computing server (202) can determine or predict traffic changes using a traffic prediction module (e.g., traffic prediction module (310)). For example, the computing server (202) can determine a scaling method using the determined traffic change. For example, the computing server (202) can perform a scaling method that minimizes cost loss and traffic loss using the determined traffic change. For example, the computing server (202) can determine the timing for triggering scaling.As an example not limited to, the computing server (202) may determine a scaling method and perform the scaling method based further on the number of nodes within the computing server (202), the cost of using the nodes, the bandwidth of the interface (e.g., wired interface), the maximum number of processors (or cores of processors), and / or the capacity of memory.

[0112] According to one embodiment, the computing server (202) for the graph (501) may have a structure of multi-core (e.g., 16) processors. For example, the computing server (202) may include memory (e.g., volatile memory) having a value of about 32 GB (gigabytes). For example, the computing server (202) may have a network bandwidth of up to 10 Gbps. For example, the hourly usage cost of the computing server (202) may be $0.65.

[0113] The cost according to line (520) may be about $156, and the cost according to line (530) may be about $93. The cost of line (530) may be about 60% of the cost of line (520). The scaling method of line (530) according to the embodiment of the present disclosure may be more efficient and advantageous in terms of cost than the scaling method of line (520).

[0114] FIGS. 6a and 6b illustrate an example of a computing server that scales resources according to an increase in traffic. For example, an increase in traffic may be referred to as a traffic burst. The scaling is performed by reducing or increasing the number of components of the network functions being executed, and the amount of computing resources allocated to newly added network functions may be adaptively set. In this disclosure, a network function may represent a containerized network function and may represent a node in the form of software implemented independently of hardware. A network function may be referred to as a processing unit, pod, network function container, network container, virtualized network node, virtualized container, virtualized network function, containerized network function, CNF, VNF, flavor, and / or equivalent technical terms.

[0115] Referring to FIG. 6a, fronthall traffic (611) in a network environment (601) can be transmitted from a wireless communication device (201) to a vDU (305) in a computing server (202). Since the value of the fronthall traffic (611) (e.g., 11 Gbps) is greater than the value of the maximum allowable bandwidth of the interface (e.g., 10 Gbps), the vDU (305) can process the fronthall traffic (611) using DPP (644) and DPP (646). For DPP (644) and DPP (646), the descriptions of DPP (444) in FIG. 4a may be referenced. For example, a second processing unit (443) in the vDU (305) may include DPP (644). For example, a third processing unit (445) in the vDU (305) may include DPP (646).

[0116] According to one embodiment, the requirements of an application (e.g., a mission critical message) associated with a URLLC slice among the fronthaul traffic (611) may include a latency of less than about 10 ms and / or a reliability of greater than about 99.9999%. The computing server (202) may allocate resources from the time the vDU (305) is deployed according to the requirements of the application associated with the URLLC slice. For example, if computing resources higher than the computing resource requirements are placed in the vDU (305) (over-provisioning), energy loss costs may occur due to the operation of unnecessary computing resources. According to one embodiment, the closer the time when the traffic of the URLLC slice increases and the time when resources are scaled, the requirements of the application associated with the URLLC slice can be met with minimal loss. This method will be described and illustrated with reference to FIG. 6b.

[0117] According to one embodiment, a computing server (202) can transmit mid-haul traffic (612) to a communication device (460) using a DPP (644) and / or a DPP (646) within a vDU (305). For example, the communication device (460) may be configured to provide a virtualized CU (vCU). For example, mid-haul traffic (612) may flow through a wireless access network (WAN) between the DPP (644) and the communication device (460). For example, mid-haul traffic (612) may flow through a WAN between the DPP (646) and the communication device (460).

[0118] Referring to FIG. 6b, the fronthole traffic (651) in the network environment (602) may differ from the fronthole traffic (611) of FIG. 6a. The value of the traffic in the URLLC slice of the fronthole traffic (651) (e.g., 10 Gbps) may be greater than the value of the traffic in the URLLC slice of the fronthole traffic (611) (e.g., 6 Gbps). The value of the fronthole traffic (651) (e.g., 15 Gbps) may be less than the sum (e.g., 20 Gbps) of the value of the maximum allowable bandwidth of the interface associated with the second node (433) (e.g., 10 Gbps) and the value of the maximum allowable bandwidth of the interface associated with the third node (435) (e.g., 10 Gbps).

[0119] The computing server (202) can scale resources using the scaling unit (303). For example, the computing server (202) can determine the scaling method based on the requirements of the application related to the URLLC slice and / or the increase in fronthall traffic (e.g., the difference between fronthall traffic (611) and fronthall traffic (651)). For example, the computing server (202) can determine vertical scaling. The computing server (202) can obtain DPP (654) by allocating additional resources to the DPP (644) (or the second processing unit (443)) of FIG. 6a. For example, DPP (654) can be included in the second processing unit (443). The computing server (202) can obtain DPP (656) by allocating additional resources to the DPP (646) (or the third processing unit (445)) of FIG. 6a. For example, the DPP (656) may be included in the third processing unit (445). For example, the computing server (202) may process fronthaul traffic (651) using the DPP (654) and the DPP (656).

[0120] The computing server (202) can determine a scaling method based on costs (e.g., scaling costs), changes in traffic (or traffic load), the type of application according to network slices, and / or infrastructure requirements. For example, the computing server (202) can predict or identify an increase in fronthaul traffic (651) in advance using a traffic prediction module (e.g., traffic prediction module (310)). For example, the computing server (202) can scale resources based on identifying an increase in fronthaul traffic (651) in advance. For example, the computing server (202) can determine or identify a trigger point for scaling based on identifying an increase in fronthaul traffic (651) in advance. For example, the computing server (202) can determine a point in time that minimizes traffic loss while minimizing cost loss. For example, the computing server (202) can trigger scaling at said point. For example, the computing server (202) can perform vertical scaling and / or horizontal scaling at the above point.

[0121] Figure 7 illustrates an example of the performance of scaling performed on resources.

[0122] Referring to FIG. 7, the graph (701) may represent the traffic request amount of a URLLC slice over time and / or the resource allocation amount according to the traffic request amount of a URLLC slice. The horizontal axis of the graph (501) may represent time. Among the vertical axes of the graph (501), the left vertical axis may represent the traffic request amount of a URLLC slice, and among the vertical axes, the right vertical axis may represent the resource allocation amount (e.g., the number of cores of a virtual processor).

[0123] Data (710) represents the distribution of traffic request volume of a URLLC slice over time. For example, the traffic request volume may correspond to a traffic load. Data (710) may represent various values ​​over time. For example, Data (710) may have a maximum value at 12:00 AM (or 6:00 PM) and a minimum value at 9:00 AM.

[0124] Line (720) may indicate a case where the computing server (e.g., computing server (202)) does not dynamically allocate resources based on the traffic request volume of the URLLC slice. The computing server (202) may allocate specified resources (e.g., cores of about 100 virtual processors) to virtualized network functions (e.g., vDU (305)) over the entire time interval of the graph (701).

[0125] Line (730) may represent a case where, according to an embodiment of the present disclosure, the computing server (202) dynamically allocates resources based on the traffic request volume of the URLLC slice. The computing server (202) may allocate more resources as the traffic request volume of the URLLC slice increases. There may be assumptions for line (730) of the graph (701) of FIG. 7. The computing server may perform resource scaling based on costs (e.g., scaling costs) and the requirements of the application associated with the URLLC slice. For example, the computing server (202) may scale resources to prevent traffic loss while minimizing cost loss. For example, costs may be calculated as the sum of the usage costs of processors (e.g., CPU, GPU), storage (e.g., memory), and / or license usage costs. For example, the computing server (202) may determine or predict traffic changes using a traffic prediction module (e.g., traffic prediction module (310)). For example, the computing server (202) may determine a scaling method using a determined traffic change. For example, the computing server (202) may perform a scaling method using the determined traffic change to minimize cost loss and prevent traffic loss. For example, the computing server (202) may determine the timing for triggering scaling. As an example, but not limited to, the computing server (202) may determine a scaling method and perform the scaling method based further on the maximum number of processors (or processor cores) and / or the capacity of memory.

[0126] According to one embodiment, the computing server (202) for the graph (701) may have a structure of multi-core (e.g., 16) processors. For example, the computing server (202) may include memory (e.g., volatile memory) having a value of about 32 GB (gigabytes). For example, the computing server (202) may have a network bandwidth of up to 10 Gbps. For example, the hourly usage cost of the computing server (202) may be $0.65.

[0127] The cost according to line (720) may be approximately $97.5, and the cost according to line (730) may be approximately $60.5. The cost of line (730) may be approximately 62% of the cost of line (720). The scaling method of line (730) according to the embodiment of the present disclosure may be more efficient and advantageous in terms of cost than the scaling method of line (720).

[0128] FIG. 8 illustrates examples of operations of a communication device for performing resource allocation. For example, the communication device may be configured to perform an auto-scaling function to adaptively adjust or allocate resources according to changes in traffic. For example, the communication device in which the operations of FIG. 8 are performed may include the computing server (202) of FIG. 2. For example, the operations exemplified in FIG. 8 may be performed or executed by a processor of the communication device (e.g., the processor (900) of FIG. 9).

[0129] Referring to FIG. 8, in operation 801, the communication device may obtain information about a traffic burst of a network slice using an artificial intelligence model. For example, the artificial intelligence model may be included in a scaling unit (e.g., scaling unit (303)). For example, the network slice may correspond to one of a plurality of slice types including eMBB, mMTC, and / or URLLC. For example, the network slice may be one of a plurality of slice types including eMBB, mMTC, and / or URLLC. For example, the information about the traffic burst may include the probability of the traffic burst and / or the duration of the traffic burst. For example, the communication device may determine or identify the type (or scale, degree, characteristics) of the traffic burst using the information about the traffic burst. For example, the communication device may determine the type of increase in traffic of the network slice using an artificial intelligence model. For example, the type of increase in traffic may be related to the traffic burst. For example, the type of traffic increase may be different depending on the duration of the traffic burst and / or the amount of increase in traffic requests following the traffic burst.

[0130] In operation 803, the communication device may determine how to scale resources based on information about traffic bursts, information about costs, and / or information about the requirements of a network slice. For example, resources may be used or utilized by virtualized network functions (e.g., vDU (305)). For example, costs may include scaling costs incurred for scaling. For example, costs may include costs for using processors (e.g., CPU (central processing unit), GPU (graphic processing unit)), costs for using memory (e.g., non-volatile memory, volatile memory), costs for using SR-IOV (single root input / output virtualization) devices, and / or costs for using licenses (e.g., licenses for using additional functions in software). For example, the requirements of a network slice may include the requirements of applications associated with the network slice. For example, the requirements for a network slice may include a latency value, a reliability value, an acceptable traffic loss value, the QoS of the network slice, and / or an SLA associated with the network slice.

[0131] As a non-limited example, the communication device may determine a method of scaling resources based further on orchestrator requirements. For example, orchestrator requirements may include the availability of processing units for executing virtualized network functions, storage space for virtualized network functions, bandwidth for virtualized network functions, and / or the geographical distribution of the communication device.

[0132] In operation 805, the communication device may perform resource allocation to virtualized network functions (e.g., vDU (305)) using a scaling method. For example, the communication device may perform resource allocation using a first scaling method to control the number of processing units. For example, the first scaling method may be included in horizontal scaling. For example, the communication device may perform resource allocation using a second scaling method based on resource resizing within the same processing unit. For example, the second scaling method may be included in vertical scaling. For example, the communication device may perform resource allocation according to a third scaling method that utilizes both the first scaling method and the second scaling method. The first scaling method, the second scaling method, and the third scaling method are merely examples for explaining the scaling methods, and the scaling methods are not limited to three. For example, the first scaling method may be understood as a different scaling method depending on the number of processing units added or removed. For example, the second scaling method can be understood as a different scaling method depending on the amount of resource resizing. For example, the third scaling method can be understood as a different scaling method depending on the amount of change in the number of processing units and / or the amount of resource resizing.

[0133] According to one embodiment, when a network slice corresponding to a traffic burst corresponds to an eMBB, the communication device may perform resource allocation to a virtualized network function using a first scaling method. For example, by performing resource allocation using the first scaling method, the number of processing units may be increased. For example, the communication device may acquire or create replicas of said processing units.

[0134] According to one embodiment, when a network slice corresponding to a traffic burst corresponds to a URLLC, the communication device can perform resource allocation to a virtualized network function using a second scaling method. For example, by the communication device performing resource allocation using the second scaling method, the size of a processing unit may be increased. For example, an increase in the size of a processing unit may indicate an increase in the amount of resources for said processing unit.

[0135] As a non-limiting example, if the network slice corresponding to the traffic burst corresponds to eMBB, the communication device may perform resource allocation to virtualized network functions using a third scaling method. If the network slice corresponding to the traffic burst corresponds to URLLC, the communication device may perform resource allocation to virtualized network functions using a third scaling method.

[0136] According to one embodiment, the number of processing units allocated to a virtualized network function according to a scaling method (e.g., a first scaling method, a third scaling method) used when the traffic burst is associated with eMBB may be greater than the number of processing units allocated to a virtualized network function according to a scaling method (e.g., a second scaling method, a third scaling method) used when the traffic burst is associated with URLLC. The size of the processing unit allocated to a virtualized network function according to a scaling method (e.g., a first scaling method, a third scaling method) used when the traffic burst is associated with eMBB may be smaller than the size of the processing unit allocated to a virtualized network function according to a scaling method (e.g., a second scaling method, a third scaling method) used when the traffic burst is associated with URLLC. However, the embodiments are not limited.

[0137] FIG. 9 illustrates the functional configuration of a communication device (901). The configuration exemplified in FIG. 9 may be understood as the configuration of a computing server (e.g., a computing server (202)). As an example, but not limited to, the configuration exemplified in FIG. 9 may be understood as the configuration of a communication device (460) of FIG. 4a, 4b, 6a, and / or FIG. 6b. Terms such as '...part', '...unit' used below refer to a unit that processes at least one function or operation, which may be implemented in hardware or software, or a combination of hardware and software.

[0138] Referring to FIG. 9, the communication device (901) may include a processor (900), a memory (910), and / or a transceiver (930).

[0139] The processor (900) controls the overall operations of the communication device (901). The processor (900) may be referred to as a control unit. For example, the processor (900) transmits and receives signals through the transceiver (930) (or through the backhaul communication unit). Additionally, the processor (900) writes and reads data to and from memory (910). Furthermore, the processor (900) can perform the functions of a protocol stack required by the communication standard. The processor (900) may include a hardware component for processing data based on one or more instructions. For example, the hardware component for processing data may include a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), a microcontroller (MCU), and / or a neural processing unit (NPU). Although only the processor (900) is shown in FIG. 9, according to other implementation examples, the communication device (901) may include two or more processors. For example, the processor (900) may have the structure of a multi-core processor, such as a dual-core, quad-core, or hexa-core. For example, the processor (900) may include various processing circuits and / or multiple processors. For example, the term "processor" as used herein, including in the claims, may include various processing circuits including at least one processor, and one or more of said at least one processor may be configured to perform the various functions described below in a distributed manner, individually and / or collectively.As used below, where “processor,” “at least one processor,” and “one or more processors” are described as being configured to perform various functions, these terms encompass, for example, but not limited to, situations where one processor performs some of the cited functions and other processor(s) perform other parts of the cited functions, and also situations where one processor can perform all of the cited functions. Additionally, the at least one processor may include a combination of processors that perform the enumerated / disclosed various functions, for example, in a distributed manner. The at least one processor may execute program instructions to achieve or perform the various functions.

[0140] The memory (910) stores data such as basic programs, application programs, and configuration information for the operation of the communication device (901). For example, the memory (910) may store information for the communication device (901) to provide network functions (e.g., vDU (305)). The memory (910) may include a hardware component for storing data and / or instructions that are input by the processor (900) and / or output from the processor (900). The memory (910) may be referred to as a storage unit. The memory (910) may be composed of volatile memory, non-volatile memory, or a combination of volatile and non-volatile memory. Additionally, the memory (910) may provide stored data upon the request of the processor (900).

[0141] The transceiver (930) can perform functions for transmitting and receiving signals in a wired communication environment. The transceiver (930) may include a wired interface for controlling a direct connection between devices through a transmission medium (e.g., copper wire, optical fiber). For example, the transceiver (930) may transmit an electrical signal to another device through a copper wire or perform conversion between an electrical signal and an optical signal. As an example not limited to, the transceiver (930) may perform functions for transmitting and receiving signals in a wireless communication environment. For example, the transceiver (930) may perform conversion functions between a baseband signal and a bit sequence according to the physical layer specifications of the system. For example, when transmitting data, the transceiver (930) generates complex symbols by encoding and modulating the transmitted bit sequence. Also, when receiving data, the transceiver (930) restores the received bit sequence by demodulating and decoding the baseband signal. Additionally, the transceiver (930) may include multiple transmission and reception paths.

[0142] The transceiver (930) can transmit and receive signals. The transceiver (930) transmits and receives signals as described above. Accordingly, all or part of the transceiver (930) may be referred to as a 'communication unit', 'transmitter unit', 'receiver unit', or 'transmitter and receiver unit'. Furthermore, in the following description, transmission and reception performed via a wireless channel are used to mean that processing as described above is performed by the transceiver (930). Although only the transceiver (930) is shown in FIG. 9, according to other embodiments, the communication device (901) may include two or more transceivers.

[0143] Although not illustrated in FIG. 9, the transceiver (930) may further include a backhaul transceiver for connecting to a core network or another base station. The backhaul transceiver may provide an interface for communicating with other nodes within the network. That is, the backhaul transceiver converts a sequence of bits transmitted from a base station to another node, e.g., another access node, another base station, an upper node, a core network, etc., into a physical signal, and converts a physical signal received from another node into a sequence of bits.

[0144] The configuration of the communication device (901) shown in FIG. 9 is merely an example, and the examples of communication devices (or electronic devices) that perform embodiments of the present disclosure are not limited to the configuration shown in FIG. 9. In some embodiments, some configurations may be added, deleted, or changed.

[0145] In an embodiment according to the present disclosure, a communication device (e.g., a computing server (202)) can predict traffic bursts. For example, the communication device can determine or identify network slices associated with traffic bursts. The communication device can determine a scaling method for resources to be utilized by virtual network functions based on information regarding traffic bursts, requirements for network slices, scaling costs, and / or orchestrator requirements. Since the communication device also considers requirements associated with network slices, it can provide communication services that satisfy QOS and / or SLAs. Additionally, the communication device can perform resource scaling (or resource allocation) in preparation for traffic bursts. The communication device can trigger resource scaling at a point where it can minimize scaling costs while satisfying QOS and / or SLAs. The communication device can be advantageous in terms of cost while satisfying the quality of communication services.

[0146] The effects obtainable from the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art to which the present disclosure belongs from the description below.

[0147] The technical problems to be solved in this disclosure are not limited to those mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art to which this disclosure pertains.

[0148] As described above, a communication device (e.g., a computing server (202)) may be configured to perform an auto-scaling function to adaptively adjust resources according to changes in network traffic. The communication device may include a memory comprising one or more storage media for storing instructions. The communication device may include at least one processor comprising processing circuitry. When the instructions are executed individually or collectively by the at least one processor, the communication device may be caused to obtain information about a traffic burst of a network slice corresponding to one of a plurality of slice types, including eMBB (enhanced mobile broadband) and URLLC (ultra-reliable low latency communication), using an artificial intelligence model. When the above instructions are executed individually or collectively by the at least one processor, the communication device may be prompted to determine a scaling method for resources to be utilized in the virtualized network function based on the information regarding the traffic burst of the network slice and the information regarding the requirements of the network slice. When the above instructions are executed individually or collectively by the at least one processor, the communication device may be prompted to perform resource allocation to the virtualized network function using the determined scaling method. The scaling method may include at least one of a first scaling method for controlling the number of processing units or a second scaling method that utilizes resizing within the same processing unit.

[0149] According to one embodiment, the instructions may cause the communication device to determine the scaling method based further on information regarding scaling costs when executed individually or collectively by the at least one processor. The scaling cost may include at least one of processor usage cost, memory usage cost, or software licensing cost.

[0150] According to one embodiment, if the network slice corresponds to the eMBB, the scaling method may be a first method. If the network slice corresponds to the URLLC, the scaling method may be a second method. The number of processing units allocated to the virtualized network function according to the first method may be greater than the number of processing units allocated to the virtualized network function according to the second method.

[0151] According to one embodiment, the information regarding the traffic burst of the network slice may include at least one of the possibility of the traffic burst of the network slice or the duration of the traffic burst.

[0152] According to one embodiment, the information regarding the requirements of the network slice may include at least one of a value of latency, a value of reliability, or a value of acceptable traffic loss.

[0153] According to one embodiment, when the instructions are executed individually or collectively by the at least one processor, the communication device may be caused to determine the scaling method based further on information regarding orchestrator requirements. The orchestrator requirements may include at least one of the availability of a processing unit for executing the virtualized network function, storage space for the virtualized network function, and the geographical distribution of the communication device.

[0154] According to one embodiment, the virtualized network function may include a virtualized distributed unit (vDU). The resources allocated to the vDU through the resource allocation may include at least one of the core of the at least one processor or the capacity of the memory.

[0155] A method performed in a communication device configured to perform an auto-scaling function for adaptively adjusting resources according to changes in network traffic as described above may include an operation of obtaining information regarding a traffic burst of a network slice corresponding to one of a plurality of slice types, including eMBB (enhanced mobile broadband) and URLLC (ultra-reliable low latency communication), using an artificial intelligence model. The method may include an operation of determining a scaling method for resources to be utilized in a virtualized network function based on the information regarding the traffic burst of the network slice and information regarding the requirements of the network slice. The method may include an operation of performing resource allocation to the virtualized network function using the determined scaling method. The scaling method may include at least one of a first scaling method for adjusting the number of processing units or a second scaling method that uses resizing within the same processing unit.

[0156] According to one embodiment, the method may include an operation to determine the scaling method based further on information regarding the scaling cost. The scaling cost may include at least one of a processor usage cost, a memory usage cost, or a software licensing cost.

[0157] According to one embodiment, if the network slice corresponds to the eMBB, the scaling method may be a first method. If the network slice corresponds to the URLLC, the scaling method may be a second method. The number of processing units allocated to the virtualized network function according to the first method may be greater than the number of processing units allocated to the virtualized network function according to the second method.

[0158] According to one embodiment, the information regarding the traffic burst of the network slice may include at least one of the possibility of the traffic burst of the network slice or the duration of the traffic burst.

[0159] According to one embodiment, the information regarding the requirements of the network slice may include at least one of a value of latency, a value of reliability, or a value of acceptable traffic loss.

[0160] According to one embodiment, the method may include an operation to determine the scaling method based further on information regarding orchestrator requirements. The orchestrator requirements may include at least one of the availability of a processing unit for executing the virtualized network function, storage space for the virtualized network function, and the geographical distribution of the communication device.

[0161] According to one embodiment, the virtualized network function may include a virtualized distributed unit (vDU). The resources allocated to the vDU through the resource allocation may include at least one of the core of the at least one processor or the capacity of the memory.

[0162] In a computer-readable storage medium in which one or more programs as described above are stored, the one or more programs may include instructions that cause the communication device to obtain information about a traffic burst of a network slice corresponding to one of a plurality of slice types, including eMBB (enhanced mobile broadband) and URLLC (ultra-reliable low latency communication), by using an artificial intelligence model when executed by the communication device configured to perform an auto-scaling function for adaptively adjusting resources according to changes in network traffic. The one or more programs may include instructions that cause the communication device to determine a scaling method for resources to be utilized in a virtualized network function based on the information about the traffic burst of the network slice and the information about the requirements of the network slice when executed by the communication device. The one or more programs may include instructions that cause the communication device to perform resource allocation to the virtualized network function using the determined scaling method when executed by the communication device. The above scaling method may include at least one of a first scaling method for controlling the number of processing units or a second scaling method that uses resizing within the same processing unit.

[0163] According to one embodiment, the one or more programs may include instructions that cause the communication device to determine the scaling method based further on information regarding the scaling cost when executed by the communication device. The scaling cost may include at least one of a processor usage cost, a memory usage cost, or a software licensing cost.

[0164] According to one embodiment, if the network slice corresponds to the eMBB, the scaling method may be a first method. If the network slice corresponds to the URLLC, the scaling method may be a second method. The number of processing units allocated to the virtualized network function according to the first method may be greater than the number of processing units allocated to the virtualized network function according to the second method.

[0165] According to one embodiment, the information regarding the traffic burst of the network slice may include at least one of the possibility of the traffic burst of the network slice or the duration of the traffic burst.

[0166] According to one embodiment, the information regarding the requirements of the network slice may include at least one of a value of latency, a value of reliability, or a value of acceptable traffic loss.

[0167] According to one embodiment, the one or more programs may include instructions that cause the communication device to determine the scaling method based further on information regarding orchestrator requirements when executed by the communication device. The orchestrator requirements may include at least one of the availability of a processing unit for executing the virtualized network function, storage space for the virtualized network function, and the geographical distribution of the communication device.

[0168] According to one embodiment, the virtualized network function may include a virtualized distributed unit (vDU). The resources allocated to the vDU through the resource allocation may include at least one of the core of the at least one processor or the capacity of the memory.

[0169] For one or more embodiments, at least one of the components described in one or more of the prior art drawings may be configured to perform one or more operations, techniques, processes and / or methods as described in the present disclosure. For example, a processor (e.g., a baseband processor) described in the present disclosure in relation to one or more of the prior art drawings may be configured to operate according to one or more examples described in the present disclosure. As another example, circuits associated with user equipment (UE), a base station, a network element, etc., as described above in relation to one or more of the prior art drawings may be configured to operate according to one or more examples described herein.

[0170] Any of the embodiments described above may be combined with any other embodiment (or combination of embodiments) unless otherwise explicitly stated. The foregoing description of one or more embodiments is for illustrative and explanatory purposes only, and is not intended to limit or exhaust the scope of the embodiments in the exact form disclosed. Modifications and variations are possible in light of the foregoing teachings or may be obtained from the practice of various embodiments.

[0171] Methods according to the claims or embodiments described in the specification of the present disclosure may be implemented in the form of hardware, software, or a combination of hardware and software.

[0172] When implemented in software, a computer-readable storage medium may be provided for storing one or more programs (software modules). One or more programs stored in the computer-readable storage medium are configured for execution by one or more processors within an electronic device. One or more programs include instructions that cause the electronic device to execute methods according to the claims or embodiments described in the specification of this disclosure. The one or more programs may be provided as a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or distributed online (e.g., download or upload) through an application store (e.g., Play Store™) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created on a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0173] Such programs (software modules, software) may be stored in random access memory, non-volatile memory including flash memory, read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic disc storage devices, compact disc-ROM (CD-ROM), digital versatile discs (DVDs), or other forms of optical storage devices, magnetic cassettes. Alternatively, they may be stored in memory composed of some or all of these. Additionally, each constituent memory may include multiple units.

[0174] Additionally, the program may be stored on an attachable storage device that can be accessed via a communication network such as the Internet, Intranet, LAN (local area network), WAN (wide area network), or SAN (storage area network), or a combination thereof. Such a storage device may be connected to a device performing an embodiment of the present disclosure through an external port. Additionally, a separate storage device on a communication network may be connected to a device performing an embodiment of the present disclosure.

[0175] In the specific embodiments of the present disclosure described above, the components included in the disclosure are expressed in a singular or plural form according to the specific embodiments presented. However, the singular or plural expression is selected to suit the situation presented for convenience of explanation, and the present disclosure is not limited to singular or plural components; even if a component is expressed in the plural form, it may be composed of a singular form, and even if a component is expressed in the singular form, it may be composed of a plural form.

[0176] According to the embodiments, one or more of the aforementioned components or operations may be omitted, or one or more other components or operations may be added. Generally or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the plurality of components in the same or similar manner as those performed by the corresponding component among the plurality of components prior to the integration. According to the embodiments, operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0177] Meanwhile, although specific embodiments have been described in the detailed description of the present disclosure, it is understood that various modifications are possible within the scope of the present disclosure.

Claims

1. A communication device configured to perform an auto-scaling function for adaptively adjusting resources according to changes in network traffic, Memory comprising one or more storage media for storing instructions; and It includes at least one processor comprising a processing circuit, and When the above instructions are executed individually or collectively by the at least one processor, the communication device: Using an artificial intelligence model, information on traffic bursts of a network slice corresponding to one of a plurality of slice types, including eMBB (enhanced mobile broadband) and URLLC (ultra-reliable low latency communication), is obtained, and Based on the information regarding the traffic burst of the network slice and the information regarding the requirements of the network slice, a scaling method for resources to be utilized in the virtualized network function is determined, and Using the scaling method determined above, cause the virtualized network function to perform resource allocation, and The above scaling method includes at least one of a first scaling method for adjusting the number of processing units or a second scaling method that uses resizing within the same processing unit. Communication device.

2. In Claim 1, When the above instructions are executed individually or collectively by the at least one processor, the communication device: Causing to determine the above scaling method based more on information regarding scaling costs, and The above scaling cost includes at least one of processor usage cost, memory usage cost, or software licensing cost, Communication device.

3. In Claim 1, When the above network slice corresponds to the above eMBB, the scaling method is the first method, and If the above network slice corresponds to the above URLLC, the scaling method is the second method, and The number of processing units allocated to the virtualized network function according to the first method is greater than the number of processing units allocated to the virtualized network function according to the second method. Communication device.

4. In Claim 1, The information regarding the traffic burst of the network slice includes at least one of the possibility of the traffic burst of the network slice or the duration of the traffic burst. Communication device.

5. In Claim 1, The information regarding the requirements of the above network slice includes at least one of a value of latency, a value of reliability, or a value of acceptable traffic loss. Communication device.

6. In Claim 1, When the above instructions are executed individually or collectively by the at least one processor, the communication device: Causing the determination of the above scaling method based more on information regarding orchestrator requirements, and The above orchestrator requirements include at least one of the availability of a processing unit for executing the virtualized network function, storage space for the virtualized network function, and the geographical distribution of the communication device. Communication device.

7. In Claim 1, The above virtualized network function includes a vDU (virtualized distributed unit), and The resources allocated to the above vDU through the resource allocation include at least one of the core of the at least one processor or the capacity of the memory. Communication device.

8. A method performed in a communication device configured to perform an auto-scaling function for adaptively adjusting resources according to changes in network traffic, An operation to obtain information about a traffic burst of a network slice corresponding to one of a plurality of slice types, including eMBB (enhanced mobile broadband) and URLLC (ultra-reliable low latency communication), using an artificial intelligence model, An operation to determine a scaling method for resources to be utilized in a virtualized network function based on the information regarding the traffic burst of the network slice and the information regarding the requirements of the network slice, and It includes an operation of performing resource allocation to the virtualized network function using the scaling method determined above, and The above scaling method includes at least one of a first scaling method for adjusting the number of processing units or a second scaling method that uses resizing within the same processing unit. method.

9. In Claim 8, Further including an operation to determine the scaling method based more on information regarding scaling costs, and The above scaling cost includes at least one of processor usage cost, memory usage cost, or software licensing cost, method.

10. In Claim 8, When the above network slice corresponds to the above eMBB, the scaling method is the first method, and If the above network slice corresponds to the above URLLC, the scaling method is the second method, and The number of processing units allocated to the virtualized network function according to the first method is greater than the number of processing units allocated to the virtualized network function according to the second method. method.

11. In Claim 8, The information regarding the traffic burst of the network slice includes at least one of the possibility of the traffic burst of the network slice or the duration of the traffic burst. method.

12. In claim 8, The information regarding the requirements of the above network slice includes at least one of a value of latency, a value of reliability, or a value of acceptable traffic loss. method.

13. In claim 8, Further including an operation to determine the scaling method based more on information regarding orchestrator requirements, and The above orchestrator requirements include at least one of the availability of a processing unit for executing the virtualized network function, storage space for the virtualized network function, and the geographical distribution of the communication device. method.

14. In Claim 8, The above virtualized network function includes a vDU (virtualized distributed unit), and The resources allocated to the above vDU through the resource allocation include at least one of the core of the processor of the communication device or the capacity of the memory of the communication device. method.

15. In a non-transient computer-readable storage medium storing one or more programs, When the above one or more programs are executed by a communication device configured to perform an auto-scaling function for adaptively adjusting resources according to changes in network traffic, Using an artificial intelligence model, information on traffic bursts of a network slice corresponding to one of a plurality of slice types, including eMBB (enhanced mobile broadband) and URLLC (ultra-reliable low latency communication), is obtained, and Based on the information regarding the traffic burst of the network slice and the information regarding the requirements of the network slice, a scaling method for resources to be utilized in the virtualized network function is determined, and Using the scaling method determined above, cause the virtualized network function to perform resource allocation, and The above scaling method includes instructions that cause the communication device, such that the scaling method includes at least one of a first scaling method for controlling the number of processing units or a second scaling method using resizing within the same processing unit. Non-transient computer-readable storage media.

Images