Dynamic congestion control for network slicing

Abstract

A computer-implemented model for dynamic congestion control of a network slice is provided. The method includes: obtaining a recommendation of a congestion control process for a plurality of interfaces of the network slice from a network node based on at least one condition related to the network slice. Application of the congestion control process handles the at least one condition related to the network slice. The method also includes: applying the congestion control process in a protocol stack for the plurality of interfaces of the network slice.

Description

Technical Field

[0001] The present disclosure generally relates to computer-implemented methods for dynamic congestion control of network slicing and related methods and apparatus. Background Art

[0002] Network congestion may occur when a network node or link cannot carry all the traffic generated by a sending node. In the face of network congestion, a congestion control mechanism (also referred to herein as a congestion control process) may be necessary, otherwise the network may collapse, and there may be packet loss and exponentially growing delays. Congestion control is a process in which a sender node and relay nodes between the sender and the receiver control their transmission rates to achieve optimal or improved network-wide resource allocation (e.g., network throughput). In mobile networks such as fourth-generation (4G) and fifth-generation (5G) networks, since the traffic is based on Internet Protocol (IP) flows, the transport network can be severely affected by network congestion. When optimizing or improving congestion control in a network, multiple objectives can be pursued to achieve a desired global optimal or improved operating point. Examples of different objectives and trade-offs include fairness, aggregate throughput, latency, and the like. Summary of the invention

[0003] In various embodiments, operations of a computer-implemented method for dynamic congestion control of a network slice are provided. The method includes obtaining, from a network node, a recommendation of a congestion control procedure for a plurality of interfaces of the network slice based on at least one condition associated with the network slice, wherein application of the congestion control procedure addresses the at least one condition associated with the network slice. The method also includes applying the congestion control procedure in a protocol stack for the plurality of interfaces of the network slice.

[0004] In some embodiments, additional operations include: extracting at least one condition related to the network slice, wherein the extracting includes obtaining the at least one condition from at least one of the network slice request and a network knowledge database.

[0005] In some embodiments, further operations include: obtaining a network topology of a network slice instance for a network slice request, wherein the network topology includes multiple network functions assigned to the network slice instance and multiple links between the multiple network functions.

[0006] In some embodiments, further operations include: determining a plurality of interfaces included in the network slice instance.

[0007] Corresponding embodiments of the inventive concept directed to a network node, a simulation-to-reality system, a computer program product and a computer program are also provided.

[0008] Potential advantages of the disclosed embodiments include improved efficiency of 5G networks. For example, different congestion control processes for different network slices can be dynamically implemented. Congestion control process selection can be aware of network slice requirements, and the use of congestion control processes can adapt to newly commissioned network slices over time. In addition, as new congestion control processes emerge, such new congestion control processes can be used in the network. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The accompanying drawings illustrate certain non-limiting embodiments of the inventive concept, and are included to provide a further understanding of the present disclosure, and are incorporated into and constitute a part of this application. In the drawings:

[0010] Figure 1 are two diagrams showing different network scenarios where different prioritizations are applied;

[0011] Figure 2 is an exemplary table showing a network slice request network slice type (NEST) based on a generic network slice template (GST) standardized by the GSM Association (GSMA);

[0012] Figure 3 is a block diagram of an exemplary network interface between a gNodeB and a User Plane Function (UPF) in the user plane;

[0013] Figure 4 is a block diagram of an exemplary network interface between a gNodeB, an access and mobility management function (AMF), and a session management function (SMF) in the control plane;

[0014] Figure 5 is a diagram showing an overview of dynamic congestion control selection according to some embodiments of the present disclosure;

[0015] Figure 6 is a diagram of entities involved in an exemplary embodiment applied to a 5G core network according to some embodiments of the present disclosure;

[0016] Figure 7 is a flow chart illustrating the operation of a method and entities involved in the method according to some embodiments of the present disclosure;

[0017] Figure 8 is a sequence diagram of operations performed in an exemplary embodiment for dynamic congestion control selection according to some embodiments of the present disclosure;

[0018] Fig. 9 is a block diagram of a network node according to some embodiments of the present disclosure;

[0019] Fig.10 is an operational flow chart according to various embodiments of the present disclosure; and

[0020] Fig.11 is a block diagram of a wireless network according to some embodiments of the present disclosure. DETAILED DESCRIPTION

[0021] Hereinafter, the inventive concept will be described more fully with reference to the accompanying drawings, in which examples of embodiments of the inventive concept are shown. However, the inventive concept can be embodied in a variety of different forms and should not be construed as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that the disclosure will be comprehensive and complete, and the scope of the inventive concept will be fully conveyed to those skilled in the art. It should also be noted that these embodiments are not mutually exclusive. A component from one embodiment may be assumed by default to be present in / used in another embodiment.

[0022] The following description presents various embodiments of the disclosed subject matter. These embodiments are presented as teaching examples and are not to be construed as limiting the scope of the disclosed subject matter. For example, some details of the embodiments may be modified, omitted or expanded without departing from the scope of the subject matter.

[0023] The following description presents various embodiments of the disclosed subject matter. These embodiments are presented as teaching examples and are not to be construed as limiting the scope of the disclosed subject matter. For example, certain details of the embodiments may be modified, omitted, or extended without departing from the scope of the subject matter. The term "user equipment" is used in a non-restrictive manner and, as described below, may refer to any type of communication device. The term "user equipment" herein may be interchangeable and replaceable with the term "communication device". In addition, the term "network node" is used in a non-restrictive manner and, as described below, may refer to, but is not limited to, any type of core network node in a 5G network or any network node in an IP flow-based network.

[0024] Different processes for congestion control can address many objectives, and the best trade-offs between objectives can be considered based on the expected customer experience and the current network state (e.g., number of users, operating costs, etc.). In addition, the prioritization of objectives to pursue can change over time, such as when the number of users in the network changes. This can involve not only the use of different congestion control mechanisms, but also intelligent systems that can dynamically pick and choose different mechanisms based on network operation.

[0025] In the 5G Core (5GC), user equipment (UE) (as further defined herein) traffic is associated with a packet data unit (PDU) session, which is carried over an IP-based flow between a radio access network (RAN) access point (e.g., gNodeB) and a user plane function (UPF) that serves as the PDU session anchor, which is the UPF that provides the N6 interface to the data network (DN). Since this IP-based transport network is under the control of the operator, different traffic prioritization strategies can be adopted. For example, if there are few active UEs in the network, throughput can be prioritized even if this causes some fairness interference as it may not affect the UE's quality of service (QoS). On the other hand, if the network starts to become congested, it can benefit from a congestion control process that emphasizes fairness. Figure 1 are two diagrams 100a, 100b showing different network scenarios where different prioritizations are applied. Diagram 100a shows a number of resources 102 available to each UE 108, where throughput to the UE 108 through the packet switches 104a to 104f and the base station 106 takes precedence over fairness without compromising the quality of experience (QoE) of the UE 108. Diagram 100b shows several UEs 108 / traffic, where fairness takes precedence over throughput to the UE 108 through the packet switches 104a to 104f and the base station 106, as some UEs 108 may consume all available resources while other UEs 108 may be hungry.

[0026] In 5GC, each PDU session is associated with a network slice instance (NSI). NSI is a logical network that provides specific network capabilities and network characteristics for different UEs and their applications. Network slices involve access networks (RAN), transport networks, core networks (CN), and possibly, cloud networks as part of communication service providers. Since many links in a network slice are based on IP flows, congestion control mechanisms can directly affect the quality of the network slice, or the degree to which the service level specifications of the network slice are met.

[0027] Network slices may be formally specified by a set of standardized requirements (also referred to herein as specifications) that are used as input to a 5G management system that creates and manages network slices in a 5G network. A Generic Network Slice Template (GST) or any other proprietary approach (e.g., GST is specified by the GSMA, and other vertical associations may also have their own slice template specifications) may be used to specify the exact requirements needed for a given network slice that must be created. A network slice template has a set of application-level attributes that specify the QoS expected by the UE. The goals of the management system may include implementing optimal or improved congestion control mechanisms in the links of the 5G network to meet the requirements of all network slices being managed in the network.

[0028] The following description of potential problems with some methods is current implementation as part of the present disclosure and should not be construed as previously known to others.

[0029] Currently, dynamic changes of congestion control policies applied in 5GC are not implemented, and several efficient congestion control processes may be ignored. Providing a dynamic and cognitive architecture of intelligent agents capable of determining the most suitable or improved combination of different congestion control processes can improve the efficiency of business flows in 5GC and simplify QoS guarantees for applications.

[0030] During the network slicing commissioning process, network resources and services can be enabled to provide the expected network slicing requirements. See, for example, 3GPP TS28.530, Technical Specification Group Services and System Aspects; Management and Orchestration; Concepts, Use Cases and Requirements (Release 16), https: / / www.3gpp.org / DynaReport / 28530.htm. An important part of an end-to-end network slicing solution is all links between network functions in the user plane, which includes a collection of UPFs. Virtual links between all UPFs can be created using the standardized tunneling protocol GTP-U. See, for example, the official document NG.116 of the GSM Association, Generic Network Slicing Template, Version 2.0. The services in these virtual links are UDP-based and may therefore suffer from network congestion. Therefore, selecting a more suitable or improved congestion control process to run in the (controlled) 5G core network can achieve more efficient network slicing.

[0031] Currently, intelligent solutions are not used to address congestion control in 5G core networks. In addition, such solutions would require understanding of the network slice requirements used by users to carry PDU sessions. Even if existing congestion control mechanisms (e.g., Transmission Control Protocol (TCP) Reno version, Cubic version, Bottleneck Bandwidth and Round Trip Time (BBR) version, etc.) are applied to the network, they cannot be changed dynamically because such processes used on the Internet are usually static.

[0032] Various embodiments of the present disclosure may provide solutions to these and other potential problems. In some embodiments of the present disclosure, a method is provided for selecting an optimal or improved congestion control process to be used in a 5GC interface of a given network slice using a cognitive layer in which an artificial intelligence (AI) inspired proxy network is selected based on specified KPIs.

[0033] As mentioned herein, the cognitive layer includes a combination of semantic information and statistics from the use of available congestion control processes for the selection process. The semantic information may include, but is not limited to, a semantic description of components and information associated with the congestion control process in the network. In an exemplary embodiment, the semantic information includes, but is not limited to, required information (e.g., channel, UE operating system, UE location); topology or network information that is optimal for the congestion control process (e.g., data center, multi-path or single path); type of congestion control process (e.g., learning-based (e.g., Monte Carlo-based, supervised learning, unsupervised learning, reinforcement learning, etc.) or rule-based (e.g., loss-based, delay-based, capacity-based, hybrid, etc.); technology or technology information that is optimal for the congestion control process (e.g., wired or wireless); and priorities (e.g., throughput, fairness, loss reduction, delay reduction, flow completion time (FCT)), etc.).

[0034] In an exemplary embodiment, semantic information for a particular congestion control process, Timely (see, e.g., https: / / conferences.sigcomm.org / sigcomm / 2015 / pdf / papers / p537.pdf), includes topology or network information that is optimal for Timely (e.g., data center); the type of congestion control process for Timely (e.g., rule-based (e.g., latency-based)); technology or technology information that is optimal for Timely (e.g., wired); and a priority for Timely (e.g., throughput and latency reduction).

[0035] For statistics, unsupervised learning techniques can be used to classify the suitability of a process based on data collected over time.

[0036] The combination of these two types of information (ie, semantic / declarative and usage data) can allow the cognitive layer to make decisions even when there is little usage data available (eg, when a new congestion control process is introduced into the system).

[0037] Although some of the embodiments discussed herein are described in the non-limiting context of a cognitive layer for selecting a congestion control process, the invention is not limited thereto. Rather, other machine processors may be used, including, but not limited to, machine processors that may be based solely on unsupervised learning methods. In exemplary embodiments using a machine processor that includes an unsupervised learning method, the selection will not take into account higher-level declarative knowledge, but may rely on insights extracted from usage data. In exemplary embodiments using a cognitive layer or an unsupervised learning method, the operational flow from network slice request until instantiation of the selected slice follows Figure 7 and Figure 8The operations included in (discussed further herein) are similar to those included in , except that in an exemplary embodiment using an unsupervised learning approach rather than a cognitive layer, the congestion control selection module 605 can directly receive and reply to the request.

[0038] The dynamic congestion control selection according to various embodiments of the present disclosure can be implemented as a virtual network function, or a part of an existing network function. Therefore, the methods of various embodiments can be run in a cloud environment. The method of the present disclosure can be implemented in a cloud environment in a manner similar to the exemplary implementation described herein, as a part of an existing network function.

[0039] In some embodiments, since the core network and its network functions are under the control of the operator, the cognitive layer can select agents that implement the best or improved strategy for a given network scenario. Some new machine learning (ML)-based congestion control processes (e.g., reinforcement learning (RL)) can be included in the selection list together with traditional TCP congestion control (e.g., Cubic version, BBR version, etc.).

[0040] In various embodiments, the dynamic selection of the congestion control process can be applied to streams using any type of transport protocol, such as User Datagram Protocol (UDP), Transmission Control Protocol (TCP), or Stream Control Transmission Protocol (SCTP). In the case of TCP and SCTP, the congestion control process can use standardized fields in the header directly or use non-standardized header options. In the case of UDP, the congestion control process can add an additional header with any necessary data on top of UDP, or utilize a tunnel header, such as General Packet Radio Service (GPRS) Tunneling Protocol (GTP-U), which is an option for the user plane interface in 5GC.

[0041] The methods of various embodiments of the present disclosure include a cognitive layer selecting different protocol stacks based on the current network slicing requirements. The network slicing specifications may be specified through standardized templates (such as GST from GSMA) or other means provided by operators or vertical industry associations. Once the network requirements are specified, the cognitive layer is required to select an agent (e.g., an ML model) to implement a congestion control process that handles such requirements. The agent may not only consider the GST specifications, but also other relevant information, such as the current network status and coexistence with other business flows, the network topology involved, etc. The selected congestion control process is then applied in the protocol stack of the network function (mainly UPF) of each interface in the 5G core.

[0042] In various embodiments of the present disclosure, since congestion control is aware of the network slice requirements, the selection of the congestion control process to be applied can be used by the Network Slice Management Function / Network Slice Subnet Management Function (NSMF / NSSMF) during the network slice commissioning phase.

[0043] Furthermore, in various embodiments of the present disclosure, the cognitive layer may use a combination of declarative and statistical knowledge for the selection process. The declarative component includes knowledge encapsulated in the cognitive layer that describes the algorithm (e.g., coexistence with other algorithms, what properties it has—fairness, throughput, etc.). The statistical component includes insights extracted from metrics collected while the algorithm is running.

[0044] Potential advantages provided by various embodiments of the present disclosure may include improving the efficiency of the 5G core network. The efficiency improvement may include:

[0045] (1) Different congestion control processes for different network slices. The concept of network slicing can imply the isolation of network resources. Since the intelligent agent can select the congestion control process based on the IP flow and understand the network slice, different congestion control processes can be applied to different network slices according to the optimization or improvement criteria of the network management system.

[0046] (2) Understand the congestion control choices required by the network slices. Optimal or improved intelligent agents can also be deployed for individual network slices to better meet their requirements. The management system can consider not only individual network slice requirements, but also the aggregation of all network slices commissioned to operate in the network to make global optimization or improvement decisions.

[0047] (3) Adaptive use of congestion control procedures. The optimal or improved congestion control procedures for newly commissioned network slices can also change over time.

[0048] (4) Evolution of new congestion control processes. With the emergence of new congestion control processes, especially those based on ML technology, new intelligent agents can be used in the network.

[0049] The dynamic congestion control selection method of various embodiments of the present disclosure can select the most suitable congestion control process to be used in the 5G core interface between network functions to meet the requirements of the network slice associated with the network service used by the UE. The method may include an AI-based cognitive layer. The cognitive layer includes a collection of intelligent agents that can optimize high-level KPIs. In some embodiments, the input of the method includes: high-level requirements for KPIs that are considered as cognitive layers, and knowledge from different sources. The high-level requirements in the 5G system can be associated with the network slice to be provided to the network service, and they can be expressed by a network slice template. In the 5GC, at least some knowledge can be obtained from the UDM network function. The output of the method includes a selection of a suitable congestion control process (e.g., the most suitable congestion control process) to be used by the network functions involved in a given network slice. In terms of the 5G core, if the method is applied to the user plane, the selected congestion control process can be used by the N3 interface between the gNodeB and the first selected UPF and all N9 interfaces between the first selected UPF and the PDU session anchor.

[0050] Figure 5 is a diagram showing an overview of dynamic congestion control selection according to some embodiments of the present disclosure. Although the embodiments discussed above are described in the non-limiting context of a 5G network, the present invention is not limited thereto. Instead, other networks may be used, including but not limited to any IP flow-based network. Figure 5 The exemplary embodiments of the present disclosure show an overview of the methods of various embodiments with respect to, for example, 5G network functions, interfaces, etc., or any type of existing and future IP flow-based networks. Various embodiments of the present disclosure are discussed herein in the context of 5GC, including the rich data and knowledge commonly found in mobile network core functions, and nodes in the network that can be designed to cope with dynamic changes in the congestion control processes used. Therefore, the methods of various embodiments can be applied to both controlled and newly built deployments, such as 5GC.

[0051] Still reference Figure 5 , the cognitive layer 504 receives input 502. The input 502 includes, but is not limited to, network slice transport-related attributes, 5GC topology (e.g., network functions and links), user plane, and / or control plane interfaces, link speed operating ranges, degree of multiplexing (e.g., number of senders), etc. Based on the input 502, the cognitive layer 504 obtains a dynamic recommendation of a congestion control process 514 for an interface of a selected transport protocol 516 for the network slice based on at least one condition related to the network slice from the input 502. The cognitive layer 504 outputs 518 the selected congestion control process (including the selected transport protocol and the selected congestion control process).

[0052] Figure 6is a diagram of entities involved in an exemplary embodiment applied to a 5G core network according to some embodiments of the present disclosure. Figure 6 , the UE or any communication service consumer (CSC) device 108 provides a network slice request as input to the cognitive layer 504, which includes a list of requirements to be met by the communication service provider (CSP) managing the 5G network. Although the cognitive layer 504 is depicted as a layer in the 5G core node 102, the present invention is not limited to this. Instead, other locations of the cognitive layer 504 can be used, including but not limited to in an external network, an external network connected to the Internet, etc. Figure 2 (described further below) is an exemplary table 200 showing a network slice request network slice type (NEST) based on the Generic Network Slice Template (GST) standardized by the GSM Association (GSMA). See, for example, the GSM Association official document NG.116, Generic Network Slice Template, Version 3.0. Again, refer to Figure 6 , the cognitive layer 504 is communicatively connected to the UDM 60, the NSMF / NSSMF 603, and the congestion control selection module 605 to perform the operations of various embodiments of the present disclosure (e.g., as described with respect to Figure 5 described operations).

[0053] Reference again Figure 2 , table 200 includes attributes 202. In an exemplary embodiment, attributes 202 include delay tolerance, deterministic communication, and slice quality of service parameters, which are some non-limiting examples of attributes used for congestion control process selection purposes. For each attribute 202, table 200 may also include attribute value 204, parameter 206, and parameter value 208.

[0054] Figure 7 is a flow chart illustrating the operation of a method and entities involved in the method according to some embodiments of the present disclosure. Figure 7 The operation 701 is summarized as follows:

[0055] From the network slice template 703, operation 705 includes extracting the transmission related requirements (e.g., delay tolerance, downlink / uplink throughput, etc.) for a given network slice. These requirements can be obtained directly from the network slice request sent by the UE / CSC 108, or it can be obtained from a network database (e.g., a UDM storing information related to all network slice instances). Figure 2 The properties discussed in the table are examples of transfer-related requirements that may be considered.

[0056] Operation 707 includes obtaining a network topology of a network slice instance that has been (or is to be) debugged for a network slice request. The network topology includes network functions for the network slice instance to which the network slice request is assigned and the (virtual) links between them. The network function may be part of a user plane or a control plane. Communication between network functions in the 5G core network may follow a service-based architecture (SBA), in which operations based on representational state transfer (REST) ​​based on the hypertext transfer protocol (HTTP) protocol are used; or may follow an interface-based architecture, in which network functions communicate directly using different types of transport protocols and tunnels. In some embodiments, interface-based connections between network functions are used for the application of congestion control methods, because these interfaces may have more services that suffer from network congestion and have deterministic network function pairs involved in the communication.

[0057] In some embodiments, operation 709 includes determining a network interface in a user plane that is part of a network slice instance (e.g., between a RAN and a data network). The interfaces in this exemplary embodiment are N3 (between a gNodeB and a first selected UPF) and N9 (between UPFs); and these interfaces use a GTP-U tunneling protocol to carry data payloads.

[0058] Optionally or alternatively, in some embodiments, optional operation 711 includes determining a network interface for which a congestion control process in the control plane may be useful. As discussed further below, this operation is optional and may be considered depending on the evolution and growth of the network control plane of the 5G core network.

[0059] In some embodiments, operation 713 includes querying the cognitive layer for selecting the best or improved congestion control process for each selected interface in the 5G core network. For operation 713, the network slice requirements extracted in operation 705 may be normalized and converted into KPIs that can be processed by the cognitive layer. The selection method is performed by the cognitive layer (e.g., an AI-inspired process) that leverages existing declarative and procedural knowledge and machine reasoning techniques.

[0060] In some embodiments, operation 715 comprises applying the selected congestion control process in the target network function (found in operation 707). The implementation of the congestion control selection may be made by different locations / entities 717 and occur at different stages of the life cycle of the network slice. For example, in some embodiments, the selection may involve the configuration of the network function during the network slice commissioning and / or instantiation phase. See, for example, 3GPP TR 28.801, Technical Specification Group Services and System Aspects; Telecommunications Management; Study on Management and Orchestration of Network Slices for Next Generation Networks (Release 15), www.3gpp.org / DynaReport / 28801.htm. Different congestion control processes may have been previously implemented in virtual or physical network interface cards.

[0061] Still reference Figure 7 , the entities 717 involved in various embodiments of the present disclosure include, but are not limited to, the UE / CSC 108 communicating with the congestion control selection module 605 regarding a network slice request (e.g., GST or other). The congestion control selection module 605 may communicate with the UDM 601 (e.g., in conjunction with any of operations 705 to 711). Optional operation 711 may involve the cognitive layer 504 or the congestion control selection module 605. Option 715 may involve the congestion control selection module 605 communicating with the NSMF / NSSMF 603.

[0062] The applicability of exemplary embodiments of the methods of the present disclosure will now be discussed in the 5GC user plane and control plane. The methods of various embodiments of the present invention may be used for congestion control selection in any part of the 5GC (including the control plane and the user plane). In some embodiments for the user plane, the selected congestion control process may be used in the GTP-U tunnel established through interfaces N3 and N9 (see, for example, Figure 3 , which shows a block diagram 300 of an exemplary network interface between a gNodeB and a user plane function (UPF) in the user plane). This may be a common scenario in which congestion control options may be applied, since congestion control is important for QoS of 5G slices and the user plane may be where most data flows are transmitted.

[0063] In some embodiments for the control plane, the transport level protocol for the control flow may be more heterogeneous and vary according to the interface. Figure 4 is a block diagram 400 of an exemplary network interface between a gNodeB, an access and mobility management function (AMF), and a session management function (SMF) in the control plane. Figure 4, an interface using SCTP in the control plane is shown. Note that while all interfaces can benefit from better congestion control choices, interoperability may be disrupted if different congestion control procedures are applied to the network functions at both ends of the interface. It should also be noted that traffic in the control plane may cause less congestion and is less restrictive in terms of QoS requirements.

[0064] Figure 8 is a sequence diagram of operations performed in an exemplary embodiment for dynamic congestion control selection according to some embodiments of the present disclosure.

[0065] refer to Figure 8 , the UE / CSC 108 sends 801 a network slice request with requirements (e.g., NEST) to the congestion control selection module 605. In response to receiving the network slice request, the congestion control selection module 605 extracts 803 the transmission related requirements from the network slice request.

[0066] At operation 805, the congestion control selection module 605 requests the network slice topology (including network functions and links) from the UDM 601. In response to the request at operation 805, the UDM 601 sends 807 the network slice topology to the congestion control selection module 605.

[0067] At operation 809, the congestion control selection module 605 requests the user plane interface used in the network slice from the UDM 601. In response to the request of operation 809, the UDM 601 sends 811 user plane interface information (e.g., endpoints and links) to the congestion control selection module 605.

[0068] Alternatively, in some embodiments, operations 813 and 815 may be performed. In operation 813, the congestion control selection module 605 requests a control plane interface used in the network slice. In response to the request of operation 813, the UDM 601 sends control plane interface information (e.g., endpoints and links) to the congestion control selection module 605.

[0069] For each selected interface, the operations of 817 and 819 are dynamically repeated (or in other words, looped). In operation 817, the congestion control selection module 605 requests a congestion control process from the cognitive layer 504. In response to the request of operation 817, the cognitive layer 504 sends the selected congestion control process (or the identification of the selected congestion control process) to the congestion control selection module 605.

[0070] Still reference Figure 8 , for each selected interface, operation 821 is repeated (or in other words, looped). In operation 821 , the congestion control selection module 605 applies the selected congestion control process in the NSMF / NSSMF 603 .

[0071] Various embodiments of the present disclosure include a method for selecting an optimal or improved congestion control process for a transport network of a network slice based on a set of requirements. The selection may be assisted by an AI-based approach (e.g., a cognitive layer and / or a machine processor) that may select the optimal or improved process based on declarative knowledge and / or historical data. The selection may also take into account standardized requirements for network slices, which may be expressed through templates (e.g., GST from GSMA) or any other expression created by other vertical industries.

[0072] In various embodiments, the method may include six operations, such as reference Figure 7 and Figure 8 As described, wherein initially transport related requirements may be extracted from the network topology as part of a network slice for finding relevant interfaces. For interfaces in the user plane, and optionally for interfaces in the control plane, congestion control procedures may be applied following the provided recommendations.

[0073] In some embodiments, the selection method can be implemented as part of the Network Slice Management Function / Network Slice Subnet Management Function (NSMF / NSSMF) during the network slice commissioning phase.

[0074] Now that the operation of the various components has been described, reference will now be made to various embodiments of the present disclosure. Fig.10 The flowchart of the network node 900 of the network specific network is discussed in detail. Fig. 9 The invention relates to a computer-implemented method for performing dynamic congestion control for network slices (implemented as a block diagram of the structure of the block diagram). As shown in the figure, the network node 900 may include a network interface circuit 914 (also referred to as a network interface), which is configured to provide communication with a network and / or other nodes of the radio access network RAN. The network node 900 may also include a processing circuit 912 (also referred to as a processor) coupled to the network interface circuit, and a memory circuit 916 (also referred to as a memory) coupled to the processing circuit 912. The memory circuit 916 may include a computer-readable program code that, when executed by the processing circuit 912, causes the processing circuit 912 to perform operations. In addition, modules may be stored in the memory 916, and these modules may provide instructions so that when the instructions of the modules are executed by the corresponding computer processing circuits of the machine learning model or cognitive layer 920, the processing circuits of the machine learning model or cognitive layer 920 perform according to the embodiments disclosed herein. Fig.10 The corresponding operations of the flowchart.

[0075] As discussed herein, operations of the network node 900 may be performed by the machine learning model or cognitive layer 920 and / or the network interface circuitry 914. For example, the machine learning model or cognitive layer 920 and / or the processor 912 may control the network interface circuitry 914 to send communications to one or more other network nodes via the network interface circuitry 914 and / or receive communications from one or more other network nodes via the network interface circuitry. Fig.10 Each operation described in the drawings may be combined and / or omitted in any combination with each other, and all such combinations are expected to fall within the spirit and scope of the present disclosure.

[0076] refer to Fig.10 , a computer-implemented method for dynamic congestion control of a network slice is provided. The method comprises: obtaining 1007 a recommendation of a congestion control process for a plurality of interfaces of the network slice from a network node based on at least one condition related to the network slice. Application of the congestion control process processes the at least one condition related to the network slice. The method further comprises: applying 1009 the congestion control process in a protocol stack for the plurality of interfaces of the network slice.

[0077] In some embodiments, the network node includes at least one of a cognitive layer and a machine learning model. The machine learning model includes an unsupervised machine learning model.

[0078] In some embodiments, the cognitive layer includes declarative knowledge and statistical knowledge. The declarative knowledge includes knowledge encapsulated in the cognitive layer describing the plurality of congestion control processes, and the statistical knowledge includes information extracted from a plurality of metrics of operating the congestion control process in the plurality of congestion control processes.

[0079] In some embodiments, at least one condition related to the network slice includes at least one of a specification of the network slice, a state of the network, traffic flows in other network slices, and a topology of the network.

[0080] In some embodiments, obtaining (1007) includes: processing an input of the cognitive layer to obtain an output from the cognitive layer. The output includes a recommendation for a congestion control process. The input includes at least one piece of knowledge information from the network and at least one key performance indicator (KPI) associated with at least one condition related to the network slice.

[0081] In some embodiments, applying (1009) a congestion control process in a protocol stack for multiple interfaces of a network slice includes: applying the congestion control process to traffic flows passing through the multiple interfaces using a transport protocol.

[0082] In some embodiments, the method further comprises: extracting (1001) at least one condition related to the network slice. The extracting comprises: obtaining at least one condition from at least one of the network slice request and the network knowledge database.

[0083] In some embodiments, the method further comprises: obtaining (1003) a network topology of a network slice instance for a network slice request. The network topology comprises a plurality of network functions assigned to the network slice instance and a plurality of links between the plurality of network functions.

[0084] In some embodiments, the method further includes: determining (1005) a plurality of interfaces included in the network slice instance.

[0085] In some embodiments, the plurality of interfaces comprises: an interface in a user plane or an interface in a control plane of the network.

[0086] In some embodiments, extracting (1001) includes normalizing at least one condition and converting it into at least one KPI.

[0087] In some embodiments, applying (1009) a congestion control process to multiple interfaces of a network slice includes: applying the congestion control process in multiple network functions.

[0088] In some embodiments, obtaining (1007) includes: obtaining after configuration of multiple network functions during at least one of a network slice commissioning phase and an instantiation phase.

[0089] For some embodiments of computer-implemented methods and related methods for dynamic congestion control for network slicing, Fig.10 Various operations in the flowchart may be optional. For example, Fig.10 The operations of blocks 1001, 1003, and 1005 may be optional.

[0090] Fig.11 is a block diagram of a wireless network according to some embodiments.

[0091] Although the subject matter described herein can be implemented in any suitable type of system using any suitable components, the embodiments disclosed herein are directed to wireless networks (e.g., Fig.11 For simplicity, Fig.11The wireless network of FIG. 41 depicts only network 4106, network nodes 4160 and 4160b, and WD 4110, 4110b, and 4110c (also referred to as mobile terminals). In practice, the wireless network may also include any additional elements suitable for supporting communication between wireless devices or between a wireless device and another communication device (e.g., a landline phone, a service provider, or any other network node or terminal device). In the illustrated components, network node 4160 and wireless device (WD) 4110 are depicted with additional details. The wireless network may provide communication and other types of services to one or more wireless devices to facilitate wireless devices to access and / or use services provided by or via the wireless network.

[0092] A wireless network may include and / or interface with any type of communication, telecommunication, data, cellular and / or radio network or other similar type of system. In some embodiments, a wireless network may be configured to operate according to a specific standard or other type of predefined rules or procedures. Thus, specific embodiments of a wireless network may implement communication standards such as Global System for Mobile Communications (GSM), Universal Mobile Telecommunications System (UMTS), Long Term Evolution (LTE), and / or other suitable 2G, 3G, 4G, or 5G standards; wireless local area network (WLAN) standards (e.g., IEEE 802.11 standards); and / or any other suitable wireless communication standards, such as Worldwide Interoperability for Microwave Access (WiMax), Bluetooth, Z-Wave, and / or ZigBee standards.

[0093] Network 4106 may include one or more backhaul networks, core networks, IP networks, public switched telephone networks (PSTN), packet data networks, optical networks, wide area networks (WANs), local area networks (LANs), wireless local area networks (WLANs), wired networks, wireless networks, metropolitan area networks, and other networks to enable communication between devices.

[0094] The network node 4160 and the WD 4110 include various components described in more detail below. These components work together to provide network node and / or wireless device functions, such as providing wireless connections in a wireless network. In different embodiments, the wireless network may include any number of wired or wireless networks, network nodes, base stations, controllers, wireless devices, relay stations, and / or any other components or systems that can facilitate or participate in the communication of data and / or signals (whether via a wired connection or via a wireless connection).

[0095] As used herein, a network node refers to a device that is capable of, configured, arranged and / or operable to communicate directly or indirectly with a wireless device and / or with other network nodes or devices in a wireless network to implement and / or provide wireless access to a wireless device and / or perform other functions (e.g., management) in a wireless network. Examples of network nodes include, but are not limited to, core nodes, access points (APs) (e.g., radio access points), base stations (BSs) (e.g., radio base stations, NodeBs, evolved NodeBs (eNBs), and NR NodeBs (gNBs)). Base stations can be classified based on the amount of coverage they provide (or in other words, based on their transmit power levels), so they can also be referred to as femto base stations, pico base stations, micro base stations, or macro base stations. A base station can be a relay node or a relay donor node that controls a relay. A network node may also include one or more (or all) parts of a distributed radio base station, such as a centralized digital unit and / or a remote radio unit (RRU), sometimes referred to as a remote radio head (RRH). These remote radio units may be integrated with antennas as radios with integrated antennas, or may not be integrated with antennas as radios with integrated antennas. Portions of distributed radio base stations may also be referred to as nodes in a distributed antenna system (DAS). Still other examples of network nodes include multi-standard radio (MSR) equipment (such as an MSR BS), a network controller (such as a radio network controller (RNC) or a base station controller (BSC)), a base transceiver station (BTS), a transmission point, a transmission node, a multi-cell / multicast coordination entity (MCE), a core network node (e.g., MSC, MME), an O&M node, an OSS node, a SON node, a positioning node (e.g., E-SMLC), and / or an MDT. As another example, a network node may be a virtual network node, as described in more detail below. However, more generally, a network node may represent any suitable device (or device group) that is capable, configured, arranged, and / or operable to enable and / or provide access to a wireless network to a wireless device, or to provide a certain service to a wireless device that has accessed a wireless network.

[0096] exist Fig.11 In the embodiment, the network node 4160 includes a processing circuit 4170, a device readable medium 4180, an interface 4190, an auxiliary device 4184, a power supply 4186, a power supply circuit 4187, and an antenna 4162. Fig.11The network node 4160 shown in the example wireless network of may represent a device including a combination of the hardware components shown, but other embodiments may include network nodes having different combinations of components. It should be understood that the network node includes any suitable combination of hardware and / or software required to perform the tasks, features, functions, and methods disclosed herein. In addition, although the components of the network node 4160 are depicted as a single box located within a larger box or nested within multiple boxes, in reality, the network node may include multiple different physical components that constitute a single illustrated component (for example, the device readable medium 4180 may include multiple separate hard drives and multiple RAM modules).

[0097] Similarly, the network node 4160 may be composed of multiple physically separate components (e.g., a Node B component and an RNC component, a BTS component and a BSC component, etc.), which may have respective corresponding components. In certain scenarios where the network node 4160 includes multiple separate components (e.g., BTS and BSC components), one or more of the separated components may be shared between multiple network nodes. For example, a single RNC may control multiple NodeBs. In such a scenario, each unique NodeB and RNC pair may be considered a single separate network node in some cases. In some embodiments, the network node 4160 may be configured to support multiple radio access technologies (RATs). In such an embodiment, some components may be replicated (e.g., separate device-readable media 4180 for different RATs), and some components may be reused (e.g., the same antenna 4162 may be shared by the RATs). The network node 4160 may also include multiple groups of various components shown for different wireless technologies (e.g., GSM, WCDMA, LTE, NR, WiFi, or Bluetooth wireless technologies) integrated into the network node 4160. These wireless technologies may be integrated into the same or different chips or chipsets and other components within network node 4160 .

[0098] The processing circuit 4170 is configured to perform any determination, calculation, or similar operation (e.g., certain obtaining operations) described herein as being provided by the network node. These operations performed by the processing circuit 4170 may include information obtained by the processing circuit 4170 through the following processing: for example, converting the obtained information into other information, comparing the obtained information or the converted information with information stored in the network node, and / or performing one or more operations based on the obtained information or the converted information, and making a determination based on the results of the processing.

[0099] The processing circuit 4170 may include a combination of one or more of the following: a microprocessor, a controller, a microcontroller, a central processing unit, a digital signal processor, an application specific integrated circuit, a field programmable gate array, or any other suitable computing device, resource, or combination of hardware, software and / or encoded logic, which is operable to provide network node 4160 functions alone or in conjunction with other network node 4160 components (e.g., device readable medium 4180). For example, the processing circuit 4170 may execute instructions stored in the device readable medium 4180 or stored in a memory within the processing circuit 4170. Such functions may include providing any of the various wireless features, functions, or benefits discussed herein. In some embodiments, the processing circuit 4170 may include a system on a chip (SOC).

[0100] In some embodiments, the processing circuit 4170 may include one or more of a radio frequency (RF) transceiver circuit 4172 and a baseband processing circuit 4174. In some embodiments, the radio frequency (RF) transceiver circuit 4172 and the baseband processing circuit 4174 may be located on separate chips (or chipsets), boards, or units (e.g., a radio unit and a digital unit). In alternative embodiments, part or all of the RF transceiver circuit 4172 and the baseband processing circuit 4174 may be on the same chip or chipset, board, or unit.

[0101] In certain embodiments, some or all of the functions described herein as being provided by a network node, base station, eNB, or other such network device may be performed by a processing circuit 4170 that executes instructions stored on a device-readable medium 4180 or a memory within the processing circuit 4170. In alternative embodiments, some or all of the functions may be provided by the processing circuit 4170, for example, in a hardwired manner, without executing instructions stored on a separate or discrete device-readable medium. In any of these embodiments, the processing circuit 4170 may be configured to perform the described functions, whether or not executing instructions stored on a device-readable storage medium. The benefits provided by such functions are not limited to the processing circuit 4170 or to other components of the network node 4160, but are enjoyed by the network node 4160 as a whole and / or by end users and the wireless network as a whole.

[0102] Device readable medium 4180 may include any form of volatile or non-volatile computer readable memory, including but not limited to permanent storage devices, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), read-only memory (ROM), mass storage media (e.g., hard disk), removable storage media (e.g., flash drive, compact disk (CD) or digital video disk (DVD)), and / or any other volatile or non-volatile, non-transitory device readable and / or computer executable memory device that stores information, data and / or instructions that can be used by processing circuit 4170. Device readable medium 4180 may store any suitable instructions, data or information, including computer programs, software, applications including one or more of logic, rules, codes, tables, etc., and / or other instructions that can be executed by processing circuit 4170 and used by network node 4160. Device readable medium 4180 may be used to store any calculations made by processing circuit 4170 and / or any data received via interface 4190. In some embodiments, the processing circuit 4170 and the device readable medium 4180 may be considered to be integrated.

[0103] Interface 4190 is used for wired or wireless communication of signaling and / or data between network node 4160, network 4106 and / or WD 4110. As shown, interface 4190 includes port / terminal 4194 for sending data to network 4106 and receiving data from network 4106, for example, via a wired connection. Interface 4190 also includes radio front-end circuit 4192, which can be coupled to antenna 4162, or in some embodiments is part of antenna 4162. Radio front-end circuit 4192 includes filter 4198 and amplifier 4196. Radio front-end circuit 4192 can be connected to antenna 4162 and processing circuit 4170. Radio front-end circuit can be configured to adjust the signal communicated between antenna 4162 and processing circuit 4170. Radio front-end circuit 4192 can receive digital data, which will be sent out to other network nodes or WDs via a wireless connection. The radio front end circuit 4192 may convert the digital data into a radio signal having appropriate channel and bandwidth parameters using a combination of filters 4198 and / or amplifiers 4196. The radio signal may then be transmitted via antenna 4162. Similarly, when receiving data, the radio signal may be collected by antenna 4162 and then converted into digital data by the radio front end circuit 4192. The digital data may be passed to the processing circuit 4170. In other embodiments, the interface may include different components and / or different combinations of components.

[0104] In certain alternative embodiments, the network node 4160 may not include a separate radio front end circuit 4192, and instead, the processing circuit 4170 may include the radio front end circuit and may be connected to the antenna 4162 without a separate radio front end circuit 4192. Similarly, in some embodiments, all or some of the RF transceiver circuit 4172 may be considered part of the interface 4190. In other embodiments, the interface 4190 may include one or more ports or terminals 4194, the radio front end circuit 4192, and the RF transceiver circuit 4172 as part of a radio unit (not shown), and the interface 4190 may communicate with the baseband processing circuit 4174 as part of a digital unit (not shown).

[0105] Antenna 4162 may include one or more antennas or antenna arrays configured to send and / or receive wireless signals. Antenna 4162 may be coupled to radio front-end circuit 4192 and may be any type of antenna capable of wirelessly sending and receiving data and / or signals. In some embodiments, antenna 4162 may include one or more omnidirectional, sectored or planar antennas operable to send / receive radio signals between, for example, 2 GHz and 66 GHz. Omnidirectional antennas may be used to send / receive radio signals in any direction, sectored antennas may be used to send / receive radio signals to / from devices in a specific area, and planar antennas may be line-of-sight antennas for sending / receiving radio signals in a relatively straight line. In some cases, using more than one antenna may be referred to as MIMO. In some embodiments, antenna 4162 may be separate from network node 4160 and may be connected to network node 4160 via an interface or port.

[0106] Antenna 4162, interface 4190 and / or processing circuit 4170 can be configured to perform any receiving operation and / or certain obtaining operation described herein as being performed by a network node. Any information, data and / or signal can be received from a wireless device, another network node and / or any other network device. Similarly, antenna 4162, interface 4190 and / or processing circuit 4170 can be configured to perform any sending operation performed by a network node described herein. Any information, data and / or signal can be sent to a wireless device, another network node and / or any other network device.

[0107] The power circuit 4187 may include or be coupled to a power management circuit and is configured to provide power to the components of the network node 4160 to perform the functions described herein. The power circuit 4187 may receive power from a power source 4186. The power source 4186 and / or the power circuit 4187 may be configured to provide power to the components of the network node 4160 in a form suitable for the various components (e.g., at the voltage and current levels required by each corresponding component). The power source 4186 may be included in or outside the power circuit 4187 and / or the network node 4160. For example, the network node 4160 may be connected to an external power source (e.g., a power outlet) via an input circuit or an interface such as a cable, whereby the external power source supplies power to the power circuit 4187. As another example, the power source 4186 may include a power source in the form of a battery or a battery pack, which is connected to or integrated in the power circuit 4187. If the external power source fails, the battery can provide backup power. Other types of power sources, such as photovoltaic devices, may also be used.

[0108] Alternative embodiments of network node 4160 may include beyond Fig.11 Additional components to those shown may be responsible for providing certain aspects of the functionality of the network node, including any of the functions described herein and / or any functionality required to support the subject matter described herein. For example, the network node 4160 may include a user interface device to allow information to be input into the network node 4160 and to allow information to be output from the network node 4160. This may allow a user to perform diagnostic, maintenance, repair, and other management functions for the network node 4160.

[0109] As used herein, user equipment (UE) or communication service consumer (CSC) equipment refers to equipment that can, is configured, is arranged and / or is operable to communicate wirelessly with network nodes and / or other wireless devices. Unless otherwise specified, the term UE can be used interchangeably with user equipment, user device, communication equipment, wireless device (WD) and / or CSC equipment in this article. Wireless transmission can include using electromagnetic waves, radio waves, infrared waves and / or other types of signals suitable for transmitting information through the air to send and / or receive wireless signals. In some embodiments, UE can be configured to send and / or receive information without direct human interaction. For example, UE can be designed to send information to the network with a predetermined schedule when triggered by an internal or external event, or in response to a request from the network. Examples of UE include, but are not limited to, smart phones, mobile phones, cellular phones, voice over IP (VoIP) phones, wireless local loop phones, desktop computers, personal digital assistants (PDAs), wireless cameras, game consoles or devices, music storage devices, playback devices, wearable terminal devices, wireless endpoints, mobile stations, tablet computers, portable computers, portable embedded devices (LEEs), portable installation equipment (LMEs), smart devices, wireless customer premises equipment (CPEs), vehicle-mounted wireless terminal devices, etc. UEs may support device-to-device (D2D) communication, vehicle-to-vehicle (V2V) communication, vehicle-to-infrastructure (V2I) communication, vehicle-to-anything (V2X) communication, for example, by implementing 3GPP standards for sidelink communication, and in this case may be referred to as D2D communication devices. As another specific example, in an Internet of Things (IoT) scenario, a UE may represent a machine or other device that performs monitoring and / or measurement and sends the results of such monitoring and / or measurement to another UE and / or a network node. In this case, the UE may be a machine-to-machine (M2M) device, which may be referred to as an MTC device in the 3GPP context. As a specific example, the UE may be a UE that implements the 3GPP Narrowband Internet of Things (NB-IoT) standard. Specific examples of such machines or devices are sensors, metering devices (e.g., power meters), industrial machines, or household or personal appliances (e.g., refrigerators, televisions, etc.), personal wearable devices (e.g., watches, fitness trackers, etc.). In other scenarios, the UE may represent a vehicle or other device that is capable of monitoring and / or reporting its operating status or other functions associated with its operation. The UE as described above may represent an endpoint of a wireless connection, in which case the device may be referred to as a wireless terminal. In addition, the UE as described above may be mobile, in which case it may also be referred to as a mobile device or a mobile terminal.

[0110] As shown, wireless device 4110 includes antenna 4111, interface 4114, processing circuit 4120, device readable medium 4130, user interface device 4132, auxiliary device 4134, power supply 4136, and power supply circuit 4137. WD 4110 may include multiple sets of one or more of the components shown for different wireless technologies supported by WD 4110 (e.g., GSM, WCDMA, LTE, NR, WiFi, WiMAX, or Bluetooth wireless technologies, to mention just a few). These wireless technologies may be integrated into a chip or chipset that is the same or different from other components within WD 4110.

[0111] Antenna 4111 may include one or more antennas or antenna arrays, configured to send and / or receive wireless signals, and connected to interface 4114. In some alternative embodiments, antenna 4111 can be separated from WD 4110 and can be connected to WD 4110 through an interface or port. Antenna 4111, interface 4114 and / or processing circuit 4120 can be configured to perform any receiving or sending operation described herein as being performed by WD. Any information, data and / or signal can be received from a network node and / or another WD. In some embodiments, radio front-end circuit and / or antenna 4111 can be considered as an interface.

[0112] As shown, the interface 4114 includes a radio front-end circuit 4112 and an antenna 4111. The radio front-end circuit 4112 includes one or more filters 4118 and an amplifier 4116. The radio front-end circuit 4112 is connected to the antenna 4111 and the processing circuit 4120, and is configured to condition the signals communicated between the antenna 4111 and the processing circuit 4120. The radio front-end circuit 4112 may be coupled to the antenna 4111 or may be part of the antenna 1011. In some embodiments, the WD 4110 may not include a separate radio front-end circuit 4112; instead, the processing circuit 4120 may include the radio front-end circuit and may be connected to the antenna 4111. Similarly, in some embodiments, some or all of the RF transceiver circuit 4122 may be considered to be part of the interface 4114. The radio front-end circuit 4112 may receive digital data, which will be sent out to other network nodes or WDs via a wireless connection. The radio front end circuit 4112 may convert the digital data into a radio signal having appropriate channel and bandwidth parameters using a combination of filters 4118 and / or amplifiers 4116. The radio signal may then be transmitted via antenna 4111. Similarly, when receiving data, the radio signal may be collected by antenna 4111 and then converted into digital data by the radio front end circuit 4112. The digital data may be passed to processing circuit 4120. In other embodiments, the interface may include different components and / or different combinations of components.

[0113] The processing circuit 4120 may include a combination of one or more of the following: a microprocessor, a controller, a microcontroller, a central processing unit, a digital signal processor, an application-specific integrated circuit, a field programmable gate array, or any other suitable computing device, resource, or combination of hardware, software and / or coded logic, which is operable to provide WD 4110 functions alone or in combination with other WD4110 components (e.g., device-readable medium 4130). Such functions may include providing any of the various wireless features or benefits discussed herein. For example, the processing circuit 4120 may execute instructions stored in the device-readable medium 4130 or in a memory within the processing circuit 4120 to provide the functions disclosed herein.

[0114] As shown, the processing circuit 4120 includes one or more of the RF transceiver circuit 4122, the baseband processing circuit 4124, and the application processing circuit 4126. In other embodiments, the processing circuit may include different components and / or different combinations of components. In some embodiments, the processing circuit 4120 of the WD 4110 may include a SOC. In some embodiments, the RF transceiver circuit 4122, the baseband processing circuit 4124, and the application processing circuit 4126 may be on a separate chip or chipset. In an alternative embodiment, part or all of the baseband processing circuit 4124 and the application processing circuit 4126 may be combined into one chip or chipset, and the RF transceiver circuit 4122 may be on a separate chip or chipset. In another alternative embodiment, part or all of the RF transceiver circuit 4122 and the baseband processing circuit 4124 may be on the same chip or chipset, and the application processing circuit 4126 may be on a separate chip or chipset. In other alternative embodiments, part or all of the RF transceiver circuit 4122, baseband processing circuit 4124, and application processing circuit 4126 may be combined in the same chip or chipset. In some embodiments, the RF transceiver circuit 4122 may be part of the interface 4114. The RF transceiver circuit 4122 may condition the RF signal for the processing circuit 4120.

[0115] In some embodiments, some or all of the functions described herein as being performed by the WD may be provided by a processing circuit 4120 executing instructions stored on a device-readable medium 4130, which in some embodiments may be a computer-readable storage medium. In alternative embodiments, some or all of the functions may be provided by the processing circuit 4120, for example in a hardwired manner, without executing instructions stored on a separate or discrete device-readable storage medium. In any of those specific embodiments, the processing circuit 4120 may be configured to perform the described functions, regardless of whether instructions stored on a device-readable storage medium are executed. The benefits provided by such functionality are not limited to the processing circuit 4120 or to other components of the WD 4110, but are enjoyed by the WD 4110 as a whole and / or generally by end users and wireless networks.

[0116] Processing circuit 4120 may be configured to perform any determination, calculation, or similar operation (e.g., certain acquisition operations) described herein as being performed by WD. Such operations performed by processing circuit 4120 may include information obtained by processing circuit 4120 by, for example, converting the obtained information into other information, comparing the obtained information or the converted information with information stored by WD 4110, and / or performing one or more operations based on the obtained information or the converted information and making a determination based on the results of the processing.

[0117] The device-readable medium 4130 is operable to store computer programs, software, applications including one or more of logic, rules, codes, tables, etc., and / or other instructions executable by the processing circuit 4120. The device-readable medium 4130 may include a computer memory (e.g., random access memory (RAM) or read-only memory (ROM)), a mass storage medium (e.g., a hard disk), a removable storage medium (e.g., a compact disk (CD) or a digital video disk (DVD)), and / or any other volatile or non-volatile, non-transitory device-readable and / or computer-executable memory device that stores information, data, and / or instructions that may be used by the processing circuit 4120. In some embodiments, the processing circuit 4120 and the device-readable medium 4130 may be considered to be integrated.

[0118] The user interface device 4132 may provide components that allow a human user to interact with the WD 4110. This interaction may be in a variety of forms, such as visual, auditory, tactile, etc. The user interface device 4132 is operable to generate output to the user and allow the user to provide input to the WD 4110. The type of interaction may vary depending on the type of user interface device 4132 installed in the WD 4110. For example, if the WD 4110 is a smart phone, the interaction may be performed through a touch screen; if the WD 4110 is a smart meter, the interaction may be performed through a screen that provides a purpose (e.g., the number of gallons used) or a speaker that provides an audible alarm (e.g., if smoke is detected). The user interface device 4132 may include input interfaces, devices and circuits, and output interfaces, devices and circuits. The user interface device 4132 is configured to allow information to be input into the WD 4110, and is connected to the processing circuit 4120 to allow the processing circuit 4120 to process the input information. The user interface device 4132 may include, for example, a microphone, a proximity or other sensor, a key / button, a touch display, one or more cameras, a USB port, or other input circuits. The user interface device 4132 is also configured to allow information to be output from the WD 4110 and to allow the processing circuit 4120 to output information from the WD 4110. The user interface device 4132 may include, for example, a speaker, a display, a vibration circuit, a USB port, a headphone jack, or other output circuits. By using one or more input and output interfaces, devices, and circuits of the user interface device 4132, the WD 4110 can communicate with an end user and / or a wireless network and allow them to benefit from the functionality described herein.

[0119] Auxiliary device 4134 is operable to provide more specific functions that may not normally be performed by a WD. This may include specialized sensors for taking measurements for various purposes, interfaces for additional types of communications such as wired communications, etc. The inclusions and types of components of auxiliary device 4134 may vary depending on the embodiment and / or scenario.

[0120] In some embodiments, the power source 4136 may be in the form of a battery or battery pack. Other types of power sources may also be used, such as an external power source (e.g., a power outlet), a photovoltaic device, or a battery cell. WD 4110 may also include a power circuit 4137 for delivering power from the power source 4136 to various parts of WD 4110, and the various parts of WD 4110 require power from the power source 4136 to perform any functions described or indicated herein. In some embodiments, the power circuit 4137 may include a power management circuit. The power circuit 4137 may additionally or alternatively be operable to receive power from an external power source; in this case, the WD 4110 may be connected to an external power source (e.g., a power outlet) through an input circuit or an interface such as a power cable. In some embodiments, the power circuit 4137 may also be operable to deliver power from an external power source to the power source 4136. For example, this may be used for charging the power source 4136. The power circuit 4137 may perform any formatting, conversion, or other modification to the power from the power source 4136 so that the power is suitable for the various components of the WD 4110 to which it is powered.

[0121] In the above description of various embodiments of the present disclosure, it is to be understood that the terms used herein are only used for the purpose of describing specific embodiments and are not intended to limit the inventive concept. Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meanings as commonly understood by ordinary technicians in the field to which the inventive concept belongs. It should also be understood that terms such as those defined in general dictionaries should be interpreted as having meanings consistent with their meanings in the context of this specification and the relevant technology, and should not be interpreted as ideal or too superficially described meanings, unless so clearly defined herein.

[0122] When an element is referred to as being "connected," "coupled," "responsive," or variations thereof relative to another element, it may be directly connected, coupled to, or responsive to the other element, or there may be an intermediate element. In contrast, when an element is referred to as being "directly connected," "directly coupled," "directly responsive," or variations thereof relative to another element, there is no intermediate element. Throughout the text, similar reference numerals represent similar elements. In addition, "coupling," "connection," "responsiveness," or variations thereof used herein may include wireless coupling, connection, or response. As used herein, the singular forms "one," "an," and "said" are intended to also include plural forms, unless the context clearly indicates otherwise. For the sake of brevity and / or clarity, well-known functions or structures may not be described in detail. The term "and / or" includes any and all combinations of one or more items listed in association.

[0123] It will be understood that although the terms first, second, third, etc. can be used herein to describe each element / operation, these elements / operations should not be limited by these terms. These terms are only used to distinguish one element / operation from another element / operation. Therefore, the first element / operation in some embodiments can be referred to as the second element / operation in other embodiments without departing from the teaching of the inventive concept. Throughout the specification, the same reference numerals or the same reference symbols represent the same or similar elements.

[0124] As used herein, the terms "comprise, comprising, comprises, include, including, includes," "have, has, having," or variations thereof, are open ended and include one or more stated features, integers, elements, steps, components, or functions, but do not preclude the presence or addition of one or more other features, integers, elements, steps, components, functions, or combinations thereof. In addition, as used herein, the commonly used abbreviation "eg," derived from the Latin phrase "exempli gratia," may be used to introduce or specify one or more general examples of a previously mentioned item without being intended as a limitation of that item. The commonly used abbreviation "ie," derived from the Latin phrase "idest," may be used to specify a specific item of a more general reference.

[0125] Example embodiments are described herein with reference to block diagrams and / or flowchart illustrations of computer-implemented methods, devices (systems and / or equipment), and / or computer program products. It should be understood that the blocks of the block diagrams and / or flowchart illustrations and the combination of blocks in the block diagrams and / or flowchart illustrations can be implemented by computer program instructions executed by one or more computer circuits. These computer program instructions can be provided to processor circuits of general-purpose computer circuits, special-purpose computer circuits, and / or other programmable data processing circuits to produce a machine, so that instructions executed by processors of computers and / or other programmable data processing devices convert and control transistors, values ​​stored in memory locations, and other hardware components within such circuits to implement the functions / actions specified in the block diagrams and / or flowcharts, and thereby create devices (functional bodies) and / or structures for implementing the functions / actions specified in the block diagrams and / or flowcharts.

[0126] These computer program instructions may also be stored in a tangible computer-readable medium that can direct a computer or other programmable data processing device to act in a specific manner so that the instructions stored in the computer-readable medium produce an article of manufacture, which includes instructions for implementing the functions / actions specified in the blocks of the block diagrams and / or flow charts. Therefore, embodiments of the present inventive concept may be implemented in hardware and / or software (including firmware, stored software, microcode, etc.) running on a processor such as a digital signal processor, which may be collectively referred to as a "circuit", "module" or variations thereof.

[0127] It should also be noted that in some alternative implementations, the function / action marked in the frame may not occur in the order marked in the flow chart. For example, depending on the function / action involved, the two frames shown in succession can actually be performed substantially simultaneously, or the frame can sometimes be performed in the opposite order. In addition, the function of a given frame of a flow chart and / or block diagram can be divided into multiple frames and / or the function of two or more frames of a flow chart and / or block diagram can be integrated at least in part. Finally, without departing from the scope of the inventive concept, other frames can be added / inserted between the frames shown, and / or frames / operations can be omitted. In addition, although some frames include arrows about the communication path for indicating the main direction of communication, it should be understood that communication can occur in the direction opposite to the arrow represented.

[0128] Under the premise of not departing from the principle of the inventive concept basically, many changes and modifications can be made to the embodiment. All these changes and modifications are intended to be included in the scope of the inventive concept herein. Therefore, the above-mentioned subject matter should be understood as exemplary and not restrictive, and the examples of the embodiments are intended to cover all these modifications, improvements and other embodiments that fall within the spirit and scope of the inventive concept. Therefore, to the maximum extent permitted by law, the scope of the inventive concept should be determined by the widest permissible interpretation of the present disclosure including the examples of the embodiments and their equivalents, and should not be limited to or restricted to the previous specific embodiments.

[0129] Provided below are explanations of the various abbreviations / acronyms used in this disclosure.

[0130] Abbreviations

[0131] 5GC 5G Core

[0132] UE User Equipment

[0133] DN Data Network

[0134] UPF User Plane Function

[0135] UDP User Datagram Protocol

[0136] TCP Transmission Control Protocol

[0137] SCTP Stream Control Transmission Protocol

[0138] GTP-U GPRS Tunneling Protocol - User Plane

[0139] PDU Packet Data Unit

[0140] RAN Radio Access Network

[0141] CN Core Network

[0142] References are as follows:

[0143] 1.3GPP TS28.530-Technical Specification Group Services and SystemAspects; Management and orchestration; Concepts, use cases and requirements (Release 16)-https: / / www.3gpp.org / DynaReport / 28530.htm

[0144] 2.GSM Association Official Document NG.116-Generic Network SliceTemplate,Version 2.0

[0145] 3.3GPP TR 28.801-Technical Specification Group Services and SystemAspects;Telecommunication management;Study on management and orchestration ofnetwork slicing for next generation network(Release15)- www.3gpp.org / DynaReport / 28801.html 。

Claims

1. A computer-implemented method for dynamic congestion control of a network slice, the method comprising: obtaining (1007) from a network node a recommendation for a congestion control procedure for a plurality of interfaces of the network slice based on at least one condition associated with the network slice, wherein application of the congestion control procedure addresses the at least one condition associated with the network slice; and Applying (1009) the congestion control process in a protocol stack for the plurality of interfaces of the network slice; The network node comprises a cognitive layer, the cognitive layer comprising declarative knowledge and statistical knowledge, wherein the declarative knowledge comprises knowledge describing a plurality of congestion control processes encapsulated in the cognitive layer, and wherein the statistical knowledge comprises information extracted from a plurality of metrics of operating a congestion control process of the plurality of congestion control processes.

2. The method according to claim 1, wherein: The at least one condition related to the network slice includes at least one of the specifications of the network slice, the status of the network, the traffic flows in other network slices, and the topology of the network.

3. The method according to claim 2, wherein: The obtaining (1007) comprises: processing the input of the cognitive layer to obtain an output from the cognitive layer comprising a recommendation for the congestion control process, wherein the input comprises at least one piece of knowledge information from the network and at least one key performance indicator KPI associated with at least one condition related to the network slice.

4. The method according to claim 1, wherein: Applying (1009) the congestion control process in the protocol stack of the multiple interfaces for the network slice includes: applying the congestion control process to business flows passing through the multiple interfaces using a transport protocol.

5. The method according to claim 1, further comprising: Extracting (1001) at least one condition related to the network slice, wherein the extracting includes obtaining the at least one condition from at least one of a network slice request and a network knowledge database.

6. The method according to claim 5, further comprising: Obtain (1003) a network topology of a network slice instance for the network slice request, wherein the network topology includes multiple network functions assigned to the network slice instance and multiple links between the multiple network functions.

7. The method according to claim 6, further comprising: Determine (1005) the multiple interfaces included in the network slice instance.

8. The method according to claim 7, wherein: The plurality of interfaces include interfaces in a user plane or a control plane of the network.

9. The method according to claim 8, wherein: The extracting (1001) includes normalizing the at least one condition and converting it into the at least one KPI.

10. The method according to claim 9, wherein: Applying (1009) a congestion control process for multiple interfaces of a network slice includes: applying the congestion control process in the multiple network functions.

11. The method according to claim 10, wherein: The obtaining (1007) includes: obtaining after configuration of the multiple network functions during at least one of a network slice debugging phase and an instantiation phase.

12. A network node (102, 900) for dynamic congestion control of a network slice, the network node comprising: at least one processor (920); At least one memory (916) coupled to the at least one processor (920) and storing program code, the program code being executed by the at least one processor to perform operations, the operations comprising: obtaining, from the network node, a recommendation for a congestion control procedure for a plurality of interfaces of the network slice based on at least one condition associated with the network slice, wherein application of the congestion control procedure addresses the at least one condition associated with the network slice; and Applying the congestion control process in a protocol stack for the plurality of interfaces of the network slice; The network node comprises a cognitive layer, the cognitive layer comprising declarative knowledge and statistical knowledge, wherein the declarative knowledge comprises knowledge describing a plurality of congestion control processes encapsulated in the cognitive layer, and wherein the statistical knowledge comprises information extracted from a plurality of metrics of operating a congestion control process of the plurality of congestion control processes.

13. The network node according to claim 12, wherein: The at least one memory (916) is connected to the at least one processor (920) and stores program codes, the program codes being executed by the at least one processor to perform the operations according to any one of claims 2 to 11.

14. A network node (102, 900) for dynamic congestion control of network slicing, The network node is adapted to perform operations comprising: obtaining, from the network node, a recommendation for a congestion control procedure for a plurality of interfaces of the network slice based on at least one condition associated with the network slice, wherein application of the congestion control procedure addresses the at least one condition associated with the network slice; and Applying the congestion control process in a protocol stack for the plurality of interfaces of the network slice; The network node comprises a cognitive layer, the cognitive layer comprising declarative knowledge and statistical knowledge, wherein the declarative knowledge comprises knowledge describing a plurality of congestion control processes encapsulated in the cognitive layer, and wherein the statistical knowledge comprises information extracted from a plurality of metrics of operating a congestion control process of the plurality of congestion control processes.

15. The network node according to claim 14, adapted to perform the operations according to any one of claims 2 to 11.

16. A computer program product comprising a non-transitory storage medium, the non-transitory storage medium comprising program code to be executed by a processing circuit (920) of a network node (102, 900), whereby execution of the program code causes the network node to perform operations comprising: obtaining, from the network node, a recommendation for a congestion control procedure for a plurality of interfaces of the network slice based on at least one condition associated with the network slice, wherein application of the congestion control procedure addresses the at least one condition associated with the network slice; and Applying the congestion control process in a protocol stack for the plurality of interfaces of the network slice; The network node comprises a cognitive layer, the cognitive layer comprising declarative knowledge and statistical knowledge, wherein the declarative knowledge comprises knowledge describing a plurality of congestion control processes encapsulated in the cognitive layer, and wherein the statistical knowledge comprises information extracted from a plurality of metrics of operating a congestion control process of the plurality of congestion control processes.

17. The computer program product according to claim 16, whereby execution of the program code causes the network node (102, 900) to perform operations according to any one of claims 2 to 11.

Images