Transport Network Domain Slice Architecture Cross-Reference to Related Applications

Abstract

Embodiments relate to systems, apparatuses, and methods that include a Network Slice Management Function (NSMF) and a Transport Network-Network Slice Subnet Management Function (TN-NSSMF). The NSMF is configured to request at least a Transport Network (TN) domain of a network architecture to create a TN portion of a network slice in a wireless communications system. The TN-NSSMF is configured to manage the TN portion of the network slice. One of the NSMF and the TN-NSSMF has artificial intelligence / machine learning (AI / ML) integrated therein that is configured to enable the one of the NSMF and the TN-NSSMF to monitor and analyze performance of the network slice in the TN domain.

Description

[Technical Field]

[0001] This application claims priority to Indian Patent Application No. 202221064468, entitled "Transport Network Domain Slice Performance Monitoring, Analysis and SLA Guarantee," filed on November 11, 2022, the entire contents of which are incorporated herein by reference.

[0002] In some implementations, the present subject matter relates to telecommunications systems, and in particular to transport network domain slice architectures. [Background technology]

[0003] In today's world, cellular networks provide on-demand communication capabilities to individuals and businesses. Typically, cellular networks are wireless networks that can be distributed over a terrestrial area called a cell. Each such cell is served by at least one fixed-location transceiver called a cell site or base station. Each cell can use a different set of frequencies from its neighboring cells to avoid interference and provide improved service within each cell. When cells are combined together, they provide radio coverage over a wide geographic area, allowing numerous mobile phones and / or other wireless devices or portable transceivers to communicate with each other and with fixed transceivers and phones anywhere in the network. Such communication is performed through base stations and is achieved even when a mobile transceiver is traveling through two or more cells during transmission. Major wireless communication providers have deployed such cell sites worldwide, allowing communicating mobile phones and mobile computing devices to connect to the public switched telephone network and the public Internet.

[0004] A mobile phone is a portable telephone that can receive and / or make telephone and / or data communications through a cell site or transmission tower by using radio waves to transfer signals to and from the mobile phone. Given the large number of mobile phone users, current mobile phone networks offer limited shared resources. In that regard, cell sites and handsets may change frequencies and use low-power transmitters to allow simultaneous use of the network by many callers with less interference. Cell site coverage may depend on the particular geographic location and / or the number of users that can potentially use the network. For example, in urban areas, a cell site may have a range of up to about 1 / 2 mile, while in rural areas, the range may be as long as 5 miles, and in some areas, users may receive signals from cell sites as far as 25 miles away.

[0005] The following are some examples of digital cellular technologies used by communication providers: Global System for Mobile Communications ("GSM"), General Packet Radio Service ("GPRS"), cdmaOne, CDMA2000, Evolved Data Optimized ("EV-DO"), Enhanced Data Rates for GSM Evolution ("EDGE"), Universal Mobile Telecommunications System ("UMTS"), Digital Enhanced Cordless Communications ("DECT"), Digital AMPS ("IS-136 / TDMA"), and Integrated Digital Enhanced Network ("iDEN"). 4G LTE, developed by the Long Term Evolution, or 3rd Generation Partnership Project ("3GPP®") standards organization, is a standard for high-speed data wireless communication for mobile phones and data terminals. 5G standards are currently being developed and deployed. 3GPP cellular technologies such as LTE and 5G NR are an evolution of earlier generations of 3GPP technologies such as GSM / EDGE and UMTS / HSPA digital cellular technologies, and allow for increased capacity and speeds by using different air interfaces along with improvements to the core network.

[0006] A cellular network can be divided into a radio access network and a core network. The radio access network ("RAN") can include network functions capable of handling radio layer communication processing. The core network can include network functions capable of handling higher layer communication, e.g., Internet Protocol ("IP"), transport layer, and application layer. In some cases, the RAN functions can be divided into baseband unit functions and radio unit functions; for example, a radio unit connected to a baseband unit via a fronthaul network can be responsible for lower layer processing of the radio physical layer, and the baseband unit can be responsible for higher layer radio protocols, e.g., MAC, RLC, etc.

[0007] One network technology that may be used in a cellular network is network slicing, where RANs and core networks ("CNs") are interconnected with each other via a transport network ("TN"). Under network slicing, network resources and network functions may be bundled into network slices according to the individual services, service level agreements (SLAs), and / or network path routing to be provided by each network slice. That is, a network slice over a cellular network may provide customized network services by combining control plane ("CP") and user plane ("UP") network functions for the network services required for a particular service over the CN and RAN. Summary of the Invention [Problem to be solved by the invention]

[0008] The aspects of slice creation and resource reservation in the RAN and CN domains are defined by standards, such as 3GPP and Internet Engineering Task Force ("IETF") standards. However, the aspects of slice creation and resource reservation in the TN domain are not defined by standards, such as 3GPP and IETF standards.

[0009] Therefore, there is a need for further improvements in network slicing technology. [Means for solving the problem]

[0010] In some implementations, the subject matter relates to an apparatus. The apparatus may include a network slice management function (NSMF) and a transport network-network slice subnet management function (TN-NSSMF). The NSMF is configured to request at least a transport network (TN) domain of a network architecture to create a TN portion of a network slice in a wireless communication system. The TN-NSSMF is configured to manage the TN portion of the network slice. One of the NSMF and the TN-NSSMF has artificial intelligence / machine learning (AI / ML) integrated therein, the AI / ML being configured to enable the one of the NSMF and the TN-NSSMF to monitor and analyze performance of the network slice in the TN domain.

[0011] The device may monitor and analyze TN domain slice performance and enable generating necessary actions to optimize and guarantee end-to-end (E2E) network slice service level agreements (SLAs) from TN domain aspects.

[0012] In some implementations, the present subject matter can include one or more of the following optional features.

[0013] In some implementations, the apparatus may further include a Representational State Transfer Application Programming Interface (REST-API) interface between the NSMF and the TN-NSSMF.

[0014] In some implementations, one of the NSMF and the TN-NSSMF in which AI / ML is integrated may be the NSMF. Furthermore, the NSMF may be configured to collect input data for AI / ML workflows, such as model training and / or inference, where the input data may include one or more of the following: data mapping between radio access network (RAN) and core slice aggregations by S-NSSAI and transport slice identifier (Tx-Slice-ID), data mapping between Tx-Slice-ID and logical dedicated forwarding plane (DFP) paths, telemetry data providing forwarding plane health for each DFP, a traffic matrix providing bandwidth consumption of all slice flows for each transport link, and a segment routing over IPv6 (SRv6) performance management (SRv6-PM) report. Furthermore, the apparatus may also include a REST-API interface between the NSMF and the TN-NSSMF, where the NSMF may be configured to collect at least a portion of the AI / ML input data via the REST-API interface.

[0015] In some implementations, one of the NSMF and the TN-NSSMF in which AI / ML is integrated may be the TN-NSSMF. Further, the TN-NSSMF may include a network slice controller (NSC) or a TN domain manager, and the TN-NSSMF may be configured to collect input data for AI / ML workflows such as model training and / or inference, where the input data may include one or more of the following: data mapping between aggregations of radio access network (RAN) and core slices by S-NSSAI and transport slice identifier (Tx-Slice-ID), data mapping between Tx-Slice-ID and logical dedicated forwarding plane (DFP) paths, telemetry data providing the health of the forwarding plane for each DFP, a traffic matrix providing the bandwidth consumption of all slice flows for each transport link, and Segment Routing over IPv6 (SRv6) Performance Management (SRv6-PM) reports. And / or the device may include a REST-API interface between the NSMF and the TN-NSSMF, and the TN-NSSMF may be configured to collect slice mapping and application service level agreement (SLA) information from the NSMF via the REST-API interface.

[0016] In some implementations, the NSMF can be configured to be communicatively coupled to a TN domain, a RAN domain, and a core network (CN) domain. Further, the RAN domain can include at least one base station therein, and the base station can include at least one of an eNodeB and a gNodeB.

[0017] In some implementations, the wireless communication system may include at least one of a 5G New Radio (NR) communication system and a Long Term Evolution (LTE) communication system.

[0018] In some implementations, the AI / ML may include a linear regression model, a feed-forward network (FFN) / convolutional neural network (CNN) model, or a long-short-term memory (LSTM) model, or the AI / ML may include a model repository including one or more of a linear regression model, an FFN / CNN model, and an LSTM model, and the AI / ML is configured to select a model from the model repository randomly or based on initial configuration requirements entered by a user. In related implementations, the AI / ML is configured to use the selected model to perform an evaluation of configuration parameters of the structured data packet and / or wireless communication system to generate a performance score for the network slice, the configuration parameters including one or more of TN topology information, TN configuration information, high-level policy information, and subnet information. In some implementations, the AI / ML is configured to take corrective action based on the performance score of the network slice, and the corrective action may include creating a new forwarding plane or assigning an additional network to the network slice.

[0019] Also disclosed are non-transitory computer program products (i.e., physically embodied computer program products) that store instructions that, when executed by one or more data processors of one or more computing systems, cause at least one data processor to perform the operations described herein. Similarly, disclosed are computer systems that may include one or more data processors and memory coupled to the one or more data processors. The memory may store, on a temporary or permanent basis, instructions that cause at least one processor to perform one or more of the operations described herein. Additionally, methods may be performed by one or more data processors within a single computing system or distributed across two or more computing systems. Such computing systems may be connected and may exchange data and / or commands or other instructions, etc., via one or more connections, including, but not limited to, connections over a network (e.g., the Internet, a wireless wide area network, a local area network, a wide area network, a wired network, etc.), such as via a direct connection between one or more of the computing systems.

[0020] The details of one or more variations of the subject matter described herein are set forth in the accompanying drawings and the description below. Other features and advantages of the subject matter described herein will be apparent from the description and drawings, and from the claims. [Brief explanation of the drawings]

[0021] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate certain aspects of the subject matter disclosed herein and, together with the description, serve to explain some of the principles associated with the disclosed implementations.

[0022] [Figure 1a] FIG. 1a illustrates an exemplary conventional Long Term Evolution ("LTE") communication system.

[0023] [Figure 1b] FIG. 1b illustrates further details of the exemplary LTE system shown in FIG. 1a.

[0024] [Figure 1c] FIG. 1c illustrates additional details of the evolved packet core of the exemplary LTE system shown in FIG. 1a.

[0025] [Figure 1d] FIG. 1d illustrates an exemplary evolved Node B of the exemplary LTE system shown in FIG. 1a.

[0026] [Figure 2] FIG. 2 shows further details of the evolved Node B shown in FIGS. 1a-1d.

[0027] [Figure 3] FIG. 3 illustrates an exemplary virtual radio access network in accordance with some implementations of the present subject matter.

[0028] [Figure 4] FIG. 4 illustrates an exemplary 3GPP split architecture for providing use of higher frequency bands to its users.

[0029] [Figure 5a] FIG. 5a illustrates an exemplary 5G wireless communication system.

[0030] [Figure 5b] FIG. 5b illustrates an example layer architecture of a split gNB and / or a split ng-eNB (e.g., a next-generation eNB that may be connected to 5GC).

[0031] [Figure 5c] FIG. 5c illustrates an exemplary functional division in the gNB architecture shown in FIGS. 5a-5b.

[0032] [Figure 6] FIG. 6 illustrates an exemplary wireless communication system in accordance with some implementations of the present subject matter.

[0033] [Figure 7] FIG. 7 illustrates an example high-level network slice architecture in accordance with some implementations of the present subject matter.

[0034] [Figure 8a] FIG. 8a is a schematic diagram illustrating an exemplary incorporation of AI / ML into NSMF, according to some implementations of the present subject matter.

[0035] [Figure 8b] FIG. 8b is a schematic diagram illustrating an exemplary integration of AI / ML into an NSC / TN domain manager, according to some implementations of the present subject matter.

[0036] [Figure 9] FIG. 9 is a diagram illustrating an example traffic matrix label in accordance with some implementations of the present subject matter.

[0037] [Figure 10] FIG. 10 illustrates an exemplary UE for AI / ML-based transport network domain slice performance monitoring, analysis, and SLA guarantees, in accordance with some implementations of the present subject matter.

[0038] [Figure 11] FIG. 11 illustrates an exemplary system in accordance with some implementations of the present subject matter.

[0039] [Figure 12] FIG. 12 illustrates an exemplary system in accordance with some implementations of the present subject matter. DETAILED DESCRIPTION OF THE INVENTION

[0040] The present subject matter may provide systems and methods that may be implemented in wireless communication systems, including various wireless communication systems, including 5G New Radio communication systems, Long Term Evolution communication systems, and the like.

[0041] Generally, the present subject matter relates to transport network domain slice architectures.

[0042] Some implementations of the present subject matter provide transport network domain slice performance monitoring, analysis, and service level agreement (SLA) assurance based on artificial intelligence / machine learning (AI / ML). The network slice architecture includes integration of a network slice management function (NSMF) or a network slice controller / transport network (NSC / TN) domain manager with AI / ML. The NSMF or NSC / TN domain manager is associated with other northbound interfaces and a Representational State Transfer Application Programming Interface (REST-API) interface between the NSC and the NSMF. The AI / ML integration is used to monitor and analyze TN domain slice performance and generate the necessary actions to optimize and ensure end-to-end (E2E) network slice SLAs from TN domain aspects.

[0043] 3GPP standards that define one or more aspects that may be related to the present subject matter include 3GPP TS 28.531, "3rd Generation Partnership Project, Technical Specification Group, Service and System Aspects, Management and Orchestration, Provisioning" and 3GPP TS 28.533, "3rd Generation Partnership Project, Technical Specification Group, Service and System Aspects, Management and Orchestration, Architectural Framework." IETF and / or O-RAN Alliance standards may also be related to one or more aspects of the present subject matter.

[0044] One or more aspects of the present subject matter may be incorporated into transmitter and / or receiver components of base stations (e.g., gNodeBs, eNodeBs, etc.) within such communication systems. The following is a general discussion of Long Term Evolution and 5G New Radio communication systems. I. Long Term Evolution Communication System

[0045] 1a-1c and 2 illustrate an exemplary conventional Long Term Evolution ("LTE") communication system 100 along with its various components. The LTE system, or 4G LTE, as it is commercially known, is governed by a standard for high-speed data wireless communication for mobile phones and data terminals. The standard is an evolution of GSM / EDGE ("Global System for Mobile Communications" / "Enhanced Data Rates for GSM Evolution") and UMTS / HSPA ("Universal Mobile Telecommunications System" / "High-Speed ​​Packet Access") network technologies. The standard was developed by 3GPP ("3rd Generation Partnership Project").

[0046] As shown in FIG. 1a, system 100 may include an Evolved Universal Terrestrial Radio Access Network (“EUTRAN”) 102, an Evolved Packet Core (“EPC”) 108, and a Packet Data Network (“PDN”) 101, where EUTRAN 102 and EPC 108 provide communications between user equipment 104 and PDN 101. EUTRAN 102 may include multiple evolved Node Bs (“eNodeBs” or “ENODEBs” or “enodeb” or “eNBs”) or base stations 106(a, b, c) (as shown in FIG. 1b) that provide communications capabilities to multiple user equipment 104(a, b, c). User equipment 104 may be a mobile phone, a smartphone, a tablet, a personal computer, a personal digital assistant (“PDA”), a server, a data terminal, and / or any other type of user equipment, and / or any combination thereof. User equipment 104 can connect to the EPC 108 and ultimately to the PDN 101 via any eNodeB 106. Typically, user equipment 104 can connect to the nearest eNodeB 106 in terms of distance. In the LTE system 100, the EUTRAN 102 and the EPC 108 cooperate to provide connectivity, mobility, and services for user equipment 104.

[0047] Figure 1b shows further details of the network 100 shown in Figure 1a. As mentioned above, the EUTRAN 102 includes multiple eNodeBs 106, also known as cell sites. The eNodeBs 106 provide radio functionality and perform important control functions, including air link resource scheduling or radio resource management, active mode mobility or handover, and admission control for services. The eNodeBs 106 are responsible for selecting which mobility management entity (MME, as shown in Figure 1c) will serve the user equipment 104, as well as protocol features such as header compression and encryption. The eNodeBs 106 that make up the EUTRAN 102 cooperate with each other for radio resource management and handover.

[0048] Communication between the user equipment 104 and the eNodeB 106 occurs over an air interface 122 (also known as the "LTE-Uu" interface). As shown in FIG. 1b, the air interface 122 provides communication between the user equipment 104b and the eNodeB 106a. The air interface 122 uses orthogonal frequency division multiple access ("OFDMA") and single-carrier frequency division multiple access ("SC-FDMA"), an OFDMA variant, on the downlink and uplink, respectively. OFDMA allows the use of multiple known antenna technologies, such as multiple-input multiple-output ("MIMO").

[0049] The air interface 122 uses various protocols, including radio resource control ("RRC") for signaling between the user equipment 104 and the eNodeB 106 and non-access stratum ("NAS") for signaling between the user equipment 104 and the MME (as shown in FIG. 1c). In addition to signaling, user traffic is transferred between the user equipment 104 and the eNodeB 106. Both signaling and traffic in the system 100 are carried by physical layer ("PHY") channels.

[0050] Multiple eNodeBs 106 may be interconnected with each other using X2 interfaces 130(a, b, c). As shown in FIG. 1b, X2 interface 130a provides interconnection between eNodeB 106a and eNodeB 106b, X2 interface 130b provides interconnection between eNodeB 106a and eNodeB 106c, and X2 interface 130c provides interconnection between eNodeB 106b and eNodeB 106c. The X2 interfaces may be established between two eNodeBs to provide for the exchange of signals, which may include information related to loading or interference, as well as information related to handover. The eNodeBs 106 communicate with the evolved packet core 108 via S1 interfaces 124(a, b, c). The S1 interface 124 can be divided into two interfaces, one for the control plane (shown in FIG. 1c as control plane interface (S1-MME interface) 128) and the other for the user plane (shown in FIG. 1c as user plane interface (S1-U interface) 125).

[0051] The EPC 108 establishes and enforces quality of service ("QoS") for user services and allows the user equipment 104 to maintain a consistent Internet Protocol ("IP") address while moving. Note that each node of the network 100 has its own IP address. The EPC 108 is designed to interwork with legacy wireless networks. The EPC 108 is also designed to separate the control plane (i.e., signaling) and the user plane (i.e., traffic) in the core network architecture, which allows for more flexibility in implementation and independent scalability of control and user data functions.

[0052] The EPC 108 architecture is dedicated to packet data and is shown in more detail in Figure 1c. The EPC 108 includes a Serving Gateway (S-GW) 110, a PDN Gateway (P-GW) 112, a Mobility Management Entity ("MME") 114, a Home Subscriber Server ("HSS") 116 (a subscriber database for the EPC 108), and a Policy Control and Charging Rules Function ("PCRF") 118. Some of these (such as the S-GW, P-GW, MME, and HSS) are often combined into nodes according to manufacturer implementations.

[0053] The S-GW 110 functions as an IP packet data router and is the user equipment's bearer path anchor in the EPC 108. Thus, when a user equipment moves from one eNodeB 106 to another during mobility operation, the S-GW 110 remains the same, and the bearer path towards the EUTRAN 102 is switched to communicate with the new eNodeB 106 serving the user equipment 104. If the user equipment 104 moves to the domain of a different S-GW 110, the MME 114 will forward all of the user equipment's bearer path to the new S-GW. The S-GW 110 establishes a bearer path for the user equipment to one or more P-GWs 112. When downstream data is received for an idle user equipment, the S-GW 110 buffers the downstream packets and requests the MME 114 to identify and re-establish the bearer path to and through the EUTRAN 102.

[0054] The P-GW 112 is the gateway between the EPC 108 (and user equipment 104 and EUTRAN 102) and the PDN 101 (shown in FIG. 1a). The P-GW 112 acts as a router for user traffic and performs functions on behalf of the user equipment. These include IP address allocation for the user equipment, packet filtering of downstream user traffic to ensure that it is placed on the appropriate bearer path, and enforcement of downstream QoS, including data rate. Depending on the services a subscriber is using, there may be multiple user data bearer paths between the user equipment 104 and the P-GW 112. A subscriber may use services on PDNs served by different P-GWs, in which case the user equipment has at least one bearer path established to each P-GW 112. During handover of a user equipment from one eNodeB to another, if the S-GW 110 is also changed, the bearer path from the P-GW 112 is switched to the new S-GW.

[0055] The MME 114 performs management of user equipment 104 within the EPC 108, including managing subscriber authentication, maintaining context for authenticated user equipment 104, establishing a network data bearer path for user traffic, and tracking the location of idle mobiles that have not detached from the network. In the case of an idle user equipment 104 that needs to reconnect to the access network to receive downstream data, the MME 114 initiates paging to locate the user equipment and reestablishes a bearer path to and through the EUTRAN 102. The MME 114 for a particular user equipment 104 is selected by the eNodeB 106 from which the user equipment 104 initiates system access. The MME is typically part of a collection of MMEs in the EPC 108 for load sharing and redundancy purposes. In establishing a user's data bearer path, the MME 114 is responsible for selecting the P-GW 112 and S-GW 110, which constitute the termination of the data path through the EPC 108.

[0056] The PCRF 118 is responsible for controlling the policy control decision-making and flow-based charging functionality of the Policy Control Enforcement Function ("PCEF") residing in the P-GW 110. The PCRF 118 provides QoS authorization (QoS Class Identifier ("QCI") and bit rate), which determines how a certain data flow is treated at the PCEF and ensures that this is in accordance with the user's subscription profile.

[0057] As mentioned above, IP services 119 are provided by PDN 101 (as shown in FIG. 1a).

[0058] 1d shows an example structure of an eNodeB 106. The eNodeB 106 may include at least one remote radio head (“RRH”) 132 (typically, there may be three RRHs 132) and a baseband unit (“BBU”) 134. The RRHs 132 may be connected to an antenna 136. The RRHs 132 and BBU 134 may be connected using an optical interface that conforms to the Common Public Radio Interface (“CPRI”) / enhanced CPRI (“eCPRI”) 142 standard specification, either using RRH-specific custom control and user plane framing methods or using O-RAN Alliance compliant control and user plane framing methods. The operation of the eNodeB 106 can be characterized using the following standard parameters (and specifications): radio frequency band (Band 4, Band 9, Band 17, etc.), bandwidth (5, 10, 15, 20 MHz), access method (downlink: OFDMA, uplink: SC-OFDMA), antenna technology (single-user and multi-user MIMO, uplink: single-user and multi-user MIMO), number of sectors (up to 6), maximum transmission speed (downlink: 150 Mb / s, uplink: 50 Mb / s), S1 / X2 interface (1000Base-SX, 1000Base-T), and mobile environment (up to 350 km / h). The BBU 134 can be responsible for digital baseband signal processing, S1 line termination, X2 line termination, call processing, and monitoring and control processing. IP packets received from the EPC 108 (not shown in FIG. 1d) can be modulated into digital baseband signals and transmitted to the RRH 132. Conversely, digital baseband signals received from the RRH 132 may be demodulated into IP packets for transmission to the EPC 108.

[0059] The RRH 132 can transmit and receive wireless signals using the antenna 136. The RRH 132 can convert digital baseband signals from the BBU 134 (using a converter (“CONV”) 140) to radio frequency (“RF”) signals and power amplify them (using an amplifier (“AMP”) 138) for transmission to the user equipment 104 (not shown in FIG. 1d). Conversely, RF signals received from the user equipment 104 are amplified (using AMP 138) and converted (using CONV 140) to digital baseband signals for transmission to the BBU 134.

[0060] Figure 2 shows additional details of an exemplary eNodeB 106. The eNodeB 106 includes multiple layers: LTE Layer 1 202, LTE Layer 2 204, and LTE Layer 3 206. LTE Layer 1 includes the physical layer ("PHY"). LTE Layer 2 includes medium access control ("MAC"), radio link control ("RLC"), and packet data convergence protocol ("PDCP"). LTE Layer 3 includes various functions and protocols, including radio resource control ("RRC"), dynamic resource allocation, eNodeB measurement configuration and provisioning, radio admission control, connection mobility control, and radio resource management ("RRM"). The RLC protocol is an automatic repeat request ("ARQ") fragmentation protocol used over the cellular air interface. The RRC protocol handles LTE Layer 3 control plane signaling between user equipment and the EUTRAN. The RRC includes functions for connection establishment and release, system information broadcast, radio bearer establishment / reconfiguration and release, RRC connection mobility procedures, paging notification and release, and outer loop power control. The PDCP performs IP header compression and decompression, user data transfer, and radio bearer sequence number maintenance. The BBU 134 shown in FIG. 1d may include LTE layers L1-L3.

[0061] One of the primary functions of the eNodeB 106 is radio resource management, including scheduling of both uplink and downlink air interface resources for the user equipment 104, control of bearer resources, and admission control. As an agent for the EPC 108, the eNodeB 106 is responsible for forwarding paging messages used to locate a mobile when it is idle. The eNodeB 106 also communicates common control channel information over the air, performs header compression, encryption and decryption of user data sent over the air, and establishes handover reporting and trigger criteria. As mentioned above, the eNodeB 106 can cooperate with other eNodeBs 106 via the X2 interface for handover and interference management purposes. The eNodeB 106 communicates with the MME of the EPC via the S1-MME interface and with the S-GW using the S1-U interface. Additionally, the eNodeB 106 exchanges user data with the S-GW via the S1-U interface. The eNodeBs 106 and the EPC 108 have a many-to-many relationship to support load sharing and redundancy between MMEs and S-GWs. The eNodeB 106 selects an MME from a group of MMEs so that the load can be shared by multiple MMEs to avoid congestion. II. 5G NR Wireless Communication Network

[0062] In some implementations, the present subject matter relates to 5G New Radio ("NR") communication systems. 5G NR is the next communication standard beyond the 4G / IMT-Advanced standard. 5G networks offer higher capacity than current 4G, allowing for a larger number of mobile broadband users per unit area, and allowing for consumption of more and / or unlimited data amounts in gigabytes per month and per user. This may allow users to stream high-definition media for many hours per day using their mobile devices, even when Wi-Fi networks do not allow for this. 5G networks have improved support for device-to-device communications, lower costs, lower latency and lower battery consumption than 4G equipment, etc. Such a network would have data rates of tens of megabits per second for many users, data rates of 100 Mb / s for metropolitan areas, simultaneous 1 Gb / s to users within a limited area (e.g., an office floor), many simultaneous connections for wireless sensor networks, increased spectral efficiency, improved coverage, increased signaling efficiency, 1-10 ms latency, and reduced latency compared to existing systems.

[0063] 3 illustrates an exemplary virtual radio access network 300. The network 300 can provide communication between various components, including a base station (e.g., eNodeB, gNodeB) 301, radio equipment 303, a centralized unit 302, a digital unit 304, and a wireless device 306. The components in the system 300 can be communicatively coupled to a core using a backhaul link 305. The centralized unit ("CU") 302 can be communicatively coupled to a distributed unit ("DU") 304 using a midhaul connection 308. The radio unit ("RU") component 306 can be communicatively coupled to the DU 304 using a fronthaul connection 310.

[0064] In some implementations, the CU 302 can provide intelligent communication capabilities to one or more DU units 304. The units 302, 304 can include one or more base stations, macro base stations, micro base stations, remote radio heads, etc., and / or any combination thereof.

[0065] In a lower layer split architecture environment, the CPRI bandwidth requirement for the NR can be several hundred Gb / s. CPRI compression can be implemented in the DU and RU (as shown in Figure 3). In 5G communication systems, compressed CPRI over Ethernet frames is referred to as eCPRI and is the recommended fronthaul network. This architecture can enable standardization of fronthaul / midhaul, which can include upper layer splitting (e.g., Option 2 or Option 3-1 (upper / lower RLC split architecture)) and fronthaul using an L1 split architecture (Option 7).

[0066] In some implementations, a lower layer split architecture (e.g., Option 7) may include receiver in the uplink and joint processing across multiple transmission points (TPs) for both DL / UL and transport bandwidth and latency requirements to facilitate deployment. Additionally, the subject lower layer split architecture may include splitting between cell-level processing and user-level processing, which may include cell-level processing in a remote unit ("RU") and user-level processing in a DU. Additionally, using the subject lower layer split architecture, frequency-domain samples may be transported over the Ethernet fronthaul, and the frequency-domain samples may be compressed for reduced fronthaul bandwidth.

[0067] 4 illustrates an example communication system 400 that can implement 5G technology and provide its users with access to higher frequency bands (e.g., greater than 10 GHz). The system 400 can include a macro cell 402 and small cells 404, 406.

[0068] The mobile device 408 may be configured to communicate with one or more of the small cells 404, 406. The system 400 may enable splitting of the control plane (C-plane) and user plane (U-plane) between the macrocell 402 and the small cells 404, 406, with the C-plane and U-plane utilizing different frequency bands. Specifically, the small cells 404, 406 may be configured to utilize higher frequency bands when communicating with the mobile device 408. The macrocell 402 may utilize existing cellular bands for C-plane communications. The mobile device 408 may be communicatively coupled via the U-plane 412, where the small cell (e.g., the small cell 406) may provide higher data rates and more flexible / cost / energy-efficient operation. The macrocell 402 may maintain good connectivity and mobility via the C-plane 410. Furthermore, in some cases, LTE and NR may be transmitted on the same frequency.

[0069] 5a illustrates an exemplary 5G wireless communication system 500 according to some implementations of the present subject matter. The system 500 may be configured to have a lower-layer split architecture according to Option 7-2. The system 500 may include a core network 502 (e.g., 5G Core) and one or more gNodeBs (or gNBs), where the gNBs may have a centralized unit gNB-CU. The gNB-CU may be logically divided into a control plane portion gNB-CU-CP 504 and one or more user plane portions gNB-CU-UP 506. The control plane portion 504 and the user plane portion 506 may be configured to be communicatively coupled using an E1 communication interface 514 (as defined in the 3GPP standard). The control plane portion 504 may be configured to be responsible for executing the RRC and PDCP protocols of the radio stack.

[0070] The control plane portion 504 and user plane portion 506 of the centralized unit of the gNB may be configured to be communicatively coupled to one or more distributed units (DUs) 508, 510 according to an upper layer split architecture. The distributed units 508, 510 may be configured to execute upper portions of the RLC, MAC, and PHY layer protocols of the radio stack. The control plane portion 504 may be configured to be communicatively coupled to the distributed units 508, 510 using an F1-C communication interface 516, and the user plane portion 506 may be configured to be communicatively coupled to the distributed units 508, 510 using an F1-U communication interface 518. The distributed units 508, 510 may be coupled to one or more remote radio units (RUs) 512 via a fronthaul network 520 (which may include one or more switches, links, etc.), which in turn communicate with one or more user equipment (not shown in FIG. 5a). The remote radio unit 512 may be configured to execute lower portions of the PHY layer protocol and provide antenna capabilities to the remote unit for communication with user equipment (similar to the description above in connection with Figures 1a-2).

[0071] Figure 5b shows an example layer architecture 530 for a split gNB. The architecture 530 can be implemented within the communication system 500 shown in Figure 5a, which can be configured as a virtualized disaggregated radio access network (RAN) architecture, whereby layers L1, L2, L3 and radio processing can be virtualized and disaggregated at centralized units, distributed units, and radio units. As shown in Figure 5b, the gNB-DU 508 can be communicatively coupled to the gNB-CU-CP control plane portion 504 (also shown in Figure 5a) and the gNB-CU-UP user plane portion 506. Each of the components 504, 506, 508 can be configured to include one or more layers.

[0072] The gNB-DU 508 may include RLC, MAC, and PHY layers, as well as various communication sublayers. These may include an F1-Application Protocol (F1-AP) sublayer, a GPRS Tunneling Protocol (GTPU) sublayer, a Stream Control Transmission Protocol (SCTP) sublayer, a User Datagram Protocol (UDP) sublayer, and an Internet Protocol (IP) sublayer. As described above, the distributed unit 508 may be communicatively coupled to the control plane portion 504 of the centralized unit, which may also include the F1-AP, SCTP, and IP sublayers, as well as the Radio Resource Control and PDCP Control (PDCP-C) sublayer. Furthermore, the distributed unit 508 may also be communicatively coupled to the user plane portion 506 of the centralized unit of the gNB. The user plane portion 506 may include a Service Data Adaptation Protocol (SDAP), a PDCP User (PDCP-U), a GTPU, a UDP, and an IP sublayer.

[0073] Figure 5c shows an example functional division in the gNB architecture shown in Figures 5a-5b. As shown in Figure 5c, the gNB-DU 508 may be communicatively coupled to the gNB-CU-CP 504 and the gNB-CU-UP 506 using an F1-C communication interface. The gNB-CU-CP 504 and the gNB-CU-UP 506 may be communicatively coupled using an E1 communication interface. An upper portion of the PHY layer (or Layer 1) may be performed by the gNB-DU 508, and a lower portion of the PHY layer may be performed by the RU (not shown in Figure 5c). As shown in Figure 5c, the RRC and PDCP-C portions may be performed by the control plane portion 504, and the SDAP and PDCP-U portions may be performed by the user plane portion 506.

[0074] Some of the functions of the PHY layer in a 5G communication network may include error detection on transport channels and indication to higher layers, FEC encoding / decoding of transport channels, hybrid ARQ soft combining, rate matching of coded transport channels to physical channels, mapping of coded transport channels to physical channels, power weighting of physical channels, modulation and demodulation of physical channels, frequency and time synchronization, radio characteristic measurements and indication to higher layers, MIMO antenna processing, digital and analog beamforming, RF processing, and other functions.

[0075] The MAC sublayer of Layer 2 may perform beam management, random access procedures, mapping between logical channels and transport channels, concatenation of multiple MAC service data units (SDUs) belonging to one logical channel into transport blocks (TBs), multiplexing / demultiplexing of SDUs belonging to logical channels to / from TBs passed to / from the physical layer on transport channels, scheduling information reporting, error correction using HARQ, priority handling between logical channels for one UE, priority handling between UEs using dynamic scheduling, transport format selection, and other functions. The RLC sublayer's functions may include forwarding upper-layer packet data units (PDUs), error correction using ARQ, reordering of data PDUs, duplication and protocol error detection, reestablishment, etc. The PDCP sublayer may be responsible for forwarding user data, various functions during reestablishment procedures, retransmission of SDUs, discarding SDUs in the uplink, forwarding of control plane data, etc.

[0076] The RRC sublayer of Layer 3 may perform the broadcasting of system information to the NAS and AS, establishment, maintenance, and release of RRC connections, security, establishment, configuration, maintenance, and release of point-to-point radio bearers, mobility functions, reporting, and other functions. III. Transport Network Domain Slice Architecture

[0077] Some implementations of the present subject matter provide transport network domain slice performance monitoring, analysis, and SLA guarantee based on AI / ML. The network slice architecture includes integration of the NSMF or NSC / TN domain manager with AI / ML. The NSMF or NSC / TN domain manager is associated with other northbound interfaces and REST-API interfaces between the NSC and the NSMF. The AI / ML integration is used to monitor and analyze TN domain slice performance and generate necessary actions to optimize and guarantee E2E network slice SLAs from TN domain aspects.

[0078] Fine-grained control over existing end-to-end slice architectures can be exercised, and SLA deviations and performance of logical dedicated forwarding planes in the transport domain can be detected and notified to network service providers, thus improving customer service across telecommunications carriers (telcos) and / or ensuring a failure-free network slice deployment across telcos.

[0079] FIG. 6 shows an implementation of a wireless communication system 600 that may include a TN domain slice architecture as described herein. The wireless communication system 600 includes at least one base station 602 (e.g., eNodeB 106 of FIGS. 1b-2, gNodeB of FIG. 5a, a Next Generation RAN (NG-RAN) node such as an eNodeB or gNodeB), at least one transport network 604, and at least one core network 606 (e.g., 5GC 502 of FIG. 5a). At least one UE 608 can access the at least one core network 606 and / or IP services 610 via a connection to one or more base stations 602 over a RAN domain 612 and through the at least one transport network 604. The one or more base stations 602 may be configured to wirelessly communicate with one or more UEs 608 via the RAN domain 612. Examples of a UE include a cellular phone, a smartphone, a Session Initiation Protocol (SIP) phone, a laptop, a personal digital assistant (PDA), a satellite radio, a global positioning system (GPS), a multimedia device, a video device, a digital audio player (e.g., an MP3 player, etc.), a camera, a game console, a tablet, a smart device, a wearable device, a vehicle, an electric meter, a gas pump, a large or small kitchen appliance, a healthcare device, an implant, a sensor / actuator, a display, or any other similarly functioning device. A UE may be an Internet of Things (IoT) device (e.g., a parking meter, a gas pump, a toaster, a vehicle, a heart monitor, etc.).

[0080] One or more base stations 602 may be configured to interface (e.g., establish connections, transfer data, etc.) with at least one core network 606 through at least one transport network 604. The transport network 604 may transfer data (e.g., uplink data, downlink data) and / or signaling between the RAN domain 612 and the core network (CN) domain 616. For example, the at least one transport network 604 may provide one or more backhaul links between the one or more base stations 602 and the at least one core network 606. The backhaul links may be wired or wireless.

[0081] The core network 606 may be configured to provide one or more services (e.g., enhanced mobile broadband (eMBB), ultra-reliable low latency communications (URLLC), massive machine type communications (mMTC), etc.) to one or more UEs 608 connected to the RAN domain 612 via a transport network (TN) domain 614. Alternatively or additionally, the core network 606 may be configured to serve as an entry point for IP services 610. The IP services 610 may include the Internet, an intranet, an IP multimedia subsystem (IMS), streaming services (e.g., video, audio, games, etc.), and / or other IP services.

[0082] The end-to-end network slice 618 may be configured to provide the necessary connectivity between at least one UE 608 and the core network 606 with specified performance commitments. The end-to-end network slice 618 generally refers to a logical network topology that connects multiple endpoints (e.g., at least one UE 608, core network 608) using a set of shared or dedicated network resources (e.g., at least one base station 602, at least one transport network 604) used to meet specific performance commitments. The performance commitments to be met by the end-to-end network slice 618 may be referred to as service level agreements (SLAs), service level objectives (SLOs), service level expectations (SLEs), and / or service level indicators (SLIs). Examples of these performance commitments may include, but are not limited to, a guaranteed minimum bandwidth (e.g., bandwidth between two endpoints in a particular direction), a guaranteed maximum latency (e.g., network latency when transmitting between two endpoints), a maximum tolerable delay variation (PDV) (e.g., maximum difference in one-way delay between sequentially transmitted packets in a flow), a maximum tolerable packet loss rate (e.g., ratio of dropped packets to transmitted packets), and a minimum availability ratio (e.g., ratio of uptime to the sum of uptime and downtime).

[0083] At least one UE 608 can be configured to access multiple network slices 618 via one or more base stations 602. In some implementations, each network slice 618 can be configured to serve a particular service type with a specified performance commitment.

[0084] Each network slice 618 can be identified by a global identifier. The global identifier can be used by the RAN domain 612, the TN domain 614, and the CN domain 616 to identify the network slice 618. The global identifier can be, for example, a Single Network Slice Selection Assistance Information (S-NSSAI). The S-NSSAI can include information about a slice and / or a service type (SST), which can indicate the expected behavior of a particular network slice with respect to capabilities and / or services. The S-NSSAI can also include a slice differentiator (SD), which can enable further differentiation for selecting a network slice instance from one or more network slice instances that may conform to the indicated SST. Alternatively or additionally, the SST and / or SD can use standard values ​​and / or values ​​specific to a particular network provider (e.g., a public land mobile network (PLMN)).

[0085] Figure 7 illustrates an implementation of a high-level network slice architecture 700 in a wireless communication system. The high-level network slice architecture 700 may be implemented by and / or included in the LTE communication system 100 of Figure 1a, the communication system 400 of Figure 4, the 5G wireless communication system 500 of Figure 5a, the wireless communication system 600 of Figure 6, or other communication systems. The network slice architecture 700 of Figure 7 is illustrated with respect to the wireless communication system 600 of Figure 6 for ease of explanation, but may similarly be implemented using another wireless communication system.

[0086] As shown in FIG. 7, the high-level network slice architecture 700 includes a network slice management function (NSMF) 702. The network slice management function (NSMF) 702 can be configured to request each domain of the network architecture (e.g., RAN, TN, and CN domains) to create a portion (e.g., a subnet) of the network slice 618 in each network domain 612, 614, 616. The network slice 618 can be implemented by a combination of the subnets created in each domain 612, 614, 616 of the network to establish a communication path across the communication system. The NSMF 702 can be configured to generate a global identifier, such as an S-NSSAI, that uniquely identifies the network slice 618. Alternatively or additionally, the NSMF 702 can be configured to create one or more service profiles that request dedicated resources for the network slice 618 in each network domain 612, 614, 616. The service profile can be determined according to one or more services to be provided via the network slice 618 and / or a specified performance commitment of the network slice 618.

[0087] In some implementations, the NSMF 702 can be configured to use a Representational State Transfer Application Programming Interface (REST-API) to request each of the domains 612, 614, 616 to create a respective portion of the network slice 618. Alternatively or additionally, the NSMF 702 can be configured to transmit and / or send a message including a slice creation request to a network element corresponding to each of the network domains 612, 614, 616.

[0088] 7, each of the RAN, TN, and CN domains 612, 614, 616 of the network architecture 700 can include an independent network slice management function. As shown in this illustrated implementation, the independent network slice management functions can include an access network-network slice subnet management function (AN-NSSMF) 704, a transport network-network slice subnet management function (TN-NSSMF) 706, such as a network slice controller (NSC) or TN domain manager or orchestrator, and a core network-network slice subnet management function (CN-NSSMF) 708. These management functions can be configured to manage or orchestrate their respective portions of the network slice 618 without coordination and / or collaboration between them. The AN-NSSMF 704 can include a RAN domain management function configured to manage the RAN network 602, the TN-NSSMF 706 can include a TN domain management function configured to manage the TN 604, and the CN-NSSMF 708 can include a CN domain management function configured to manage the CN 606.

[0089] The NSMF 702 can be configured to send a network slice creation request to each of the AN-NSSMF 704, the NSC 706, and the CN-NSSMF 708, so that the AN-NSSMF 704, the NSC 706, and the CN-NSSMF 708 can reserve resources for the network slice 618 of their respective associated domains 612, 614, 616. The NSMF 702 can be configured to send the slice creation request to the AN-NSSMF 704, such as a RAN path computation element and / or a RAN orchestrator, to create the RAN domain portion of the network slice 618. For example, the slice creation request sent by the NSMF 702 to the AN-NSSMF 704 can include an S-NSSAI (or other global identifier) ​​that identifies the network slice 618 and / or a service profile determined for the RAN domain 612. In response to receiving the slice creation request from the NSMF 702, the AN-NSSMF 704 can be configured to allocate one or more resources (e.g., a time period, a frequency range, a bandwidth, etc.) of the RAN domain 612 to the network slice 618. That is, the AN-NSSMF 704 can be configured to configure one or more base stations 602 of the RAN domain 612 and / or other network elements of the RAN domain 612 to provide a network path between at least one UE 608 and the transport network 604 in accordance with the performance commitment specified for the network slice 618. Alternatively or additionally, the AN-NSSMF 704 can be configured to further allocate RAN resources according to other performance factors, such as, but not limited to, the available processing throughput of the allocated device, latency considerations, the geographic location of the allocated device, the priority of the service associated with the network slice 618, etc.

[0090] The NSMF 702 may be configured to send a slice creation request to the CN-NSSMF 708, such as a CN path computation element and / or a CN orchestrator, to create the CN domain portion of the network slice 618. For example, the slice creation request sent by the NSMF 702 to the CN-NSSMF 708 may include an S-NSSAI (or other global identifier) ​​that identifies the network slice 618 and / or a service profile determined for the CN domain 616. In response to receiving the slice creation request from the NSMF 702, the CN-NSSMF 708 may be configured to compute and / or allocate one or more core network paths for the network slice 618 to provide a network path between at least one UE 908 and one or more services indicated by the slice creation request. For example, the CN-NSSMF 708 may be configured to select a core network path based at least on a source address indicated by the slice creation request, a destination address indicated by the slice creation request, and / or network path constraints (e.g., service profile, performance commitment, etc.) indicated by the slice creation request. Alternatively or additionally, the CN-NSSMF708 may be configured to configure one or more network elements of the CN network 606 to provide one or more services indicated by the slice creation request to at least one UE608 in accordance with the performance commitments specified for the network slice 618.

[0091] The NSMF 702 may be configured to send a slice creation request to a TN-NSSMF 706, such as a network slice controller (NSC) and / or a TN domain manager or orchestrator, to create the TN domain portion of the network slice 618. For example, the slice creation request sent by the NSMF 702 to the TN-NSSMF 706 may include an S-NSSAI (or other global identifier) ​​that identifies the network slice 618 and / or a service profile determined for the TN domain 614. In response to receiving the slice creation request from the NSMF 702, the TN-NSSMF 706 may be configured to calculate and / or allocate one or more transport network paths for the network slice 618. For example, the TN-NSSMF 706 may be configured to select a transport network path based at least on a source address indicated by the slice creation request, a destination address indicated by the slice creation request, and / or network path constraints (e.g., service profile, performance commitment, etc.) indicated by the slice creation request. Alternatively or additionally, the TN-NSSMF 706 may be configured to configure one or more network elements of the TN network 604 to provide one or more transport network paths between the RAN domain 612 and the core network 606 in accordance with performance commitments specified for the network slice 618.

[0092] Aspects of slice creation and resource reservation in the RAN and CN domains 612, 616 are defined by standards, such as 3GPP and IETF standards. However, aspects of slice creation and resource reservation in the TN domain 614 are not defined by standards, such as 3GPP and IETF standards. For example, network slicing is addressed by 3GPP in 3GPP TS 28.531 and 3GPP TS 28.533, and by the IETF in Traffic Engineering Architecture and Signaling (TEAS) IETF Working Group (WG) documents such as the TEAS-IETF WG Framework for IETF Network Slicing, but neither covers the impact on end-to-end (E2E) SLAs due to performance deviations in the transport domain.

[0093] The network slice architectures described herein, such as the network slice architectures 800, 802 shown in Figures 8a and 8b and further described below, can enable dedicated forwarding plane (DFP) resource utilization in the TN domain and track SLA violations due to performance impairments.

[0094] Currently, the Internet of Things (IoT) is being used to implement domain slicing using the DFP architecture. Transport domain slices are deployed using the DFP architecture. Each DFP is based on a per-application basis. The slice forwarding plane is logical and delivers virtual resources from physical network resources. For example, one DFP may be based on an enhanced mobile broadband (e-MBB) application slice, while another may be based on an ultra-reliable low-latency (uRLLC) or IoT slice. DFPs are assigned either through existing mechanisms, such as a Flex-Algo mechanism-based architecture that divides physical network resources into multiple logical resources by assigning dedicated forwarding algorithms, or by creating multiple virtual local area network (VLAN)-based logical interfaces with their own given quality of service (QoS) and infrastructure resources, and by creating segment routing (SR) traffic engineering policies.

[0095] In the first scenario, measuring DFP performance in the transport domain is a key challenge for telcos and operators offering end-to-end network slice solutions, including RAN, transport, and core domains. The downside of transport domain slice architectures for telcos / operators is how to track DFP resource utilization before reaching a limit where slice applications start to suffer either due to excessive logical resource consumption or performance impacts due to device malfunctions, software bugs, and distributed denial of service (DDoS) attacks against the network infrastructure.

[0096] The second scenario in the end-to-end slice architecture is SLA monitoring and guarantee of DFP performance. During DFP performance impact, the end-to-end slice SLA may be violated, which may affect the entire network slice application. Such violations are ignored in the slice architecture defined by 3GPP in 3GPP TS 28.531 and 3GPP TS 28.533. Currently, there is no mechanism defined by 3GPP to monitor the transport domain SLA from the UE to the user plane function (UPF) and enable the network slice management system to take SLA guarantee actions for the network's transport domain. Currently, with the increasing use of server clusters, network operators need to improve and optimize energy efficiency and minimize power consumption.

[0097] Current methods improve efficiency by using either a first-fit or best-fit algorithm to place an incoming application on a target cluster or node. For example, one conventional method places an incoming application, task, job, operation, or program on the first available cluster and node that matches the resource requirements of the incoming application. However, a drawback of this method is that energy efficiency is not optimized when resource-intensive clusters or nodes are utilized. The transport network domain slice architecture described herein may mitigate this drawback.

[0098] 8a and 8b illustrate various implementations of a network slice architecture including integration of an NSMF or an NSC / TN domain manager with AI / ML. The implementations of Figures 8a and 8b are described with respect to the wireless communication system 600 of Figure 6 and the network slice architecture 700 of Figure 7, but as also described above, may be similarly implemented by and / or included in other wireless communication systems. As described above, AI / ML integration may be used to monitor and analyze TN domain slice performance and generate actions necessary to optimize and guarantee E2E network slice SLAs from TN domain aspects.

[0099] Integrating the AI / ML with the NSC / TN domain manager may reduce latency compared to integrating the AI / ML with the NSMF because the NSC / TN domain manager is closer to the underlying network, as shown in Figure 7. Therefore, integrating the AI / ML with the NSC / TN domain manager may also save bandwidth in transferring data compared to integrating the AI / ML with the NSMF because the NSC / TN domain manager is closer to the underlying network.

[0100] For example, as shown in Figure 7, integrating an AI / ML with an NSMF may be easier to implement than integrating an AI / ML with an NSC / TN domain manager because network information is traditionally available to the NSMF, since the NSMF is communicatively coupled to the RAN, TN, and CN domains, while the NSC / TN domain manager is communicatively coupled to the TN domain but not to the RAN and CN domains. Thus, when an AI / ML is integrated with an NSC / TN domain manager, at least some network information may need to be provided to the NSC / TN domain manager, unlike when the AI / ML is integrated with an NSMF.

[0101] 8a illustrates an example implementation of a network slice architecture 800 that incorporates AI / ML 804 (e.g., AI / ML models or algorithms stored in a memory and executable by a processor) in the NSMF 702. Thus, the AI / ML 804 is deployed in the NSMF 702 in this implementation. The AI / ML 804 integrated with the NSMF 702 can be deployed within the NSMF 702 or can run on an external application server. A RESTful interface (REST-API interface) 806 between the NSMF 702 and the NSC 706 allows the NSMF 702 to collect input data for the AI / ML 804 for AI / ML workflows such as model training and inference.

[0102] The AI / ML 804 is configured to track the performance status of the DFP and monitor whether specific SLAs of the end-to-end network slice are being met from the perspective of the TN domain. The AI / ML 804 is configured to generate a performance score for the TN slice after evaluating the performance of the DFP (logical forwarding resource) and the met / deviant SLAs per logical / slice topology.

[0103] A low performance score on a TN slice can be either an SLA violation or a poor performance indicator. An administrator / operator or slice management system, i.e., NSMF 702, can be configured to use the report to take at least one corrective action, which can be either creating a new forwarding plane as desired by the network's application or allocating additional network resources as desired by the slice application.

[0104] The AI / ML 804 can be configured to use input data available within the NSMF 702 or collected by the NSMF 702 from the NSC 706 and TN 604 to derive performance scores and network slice SLA guarantee decisions. Examples of input data include: 1) Data mapping between RAN and core slice aggregations using S-NSSAI and transport slice identifier (Tx-Slice-ID). Implementation forms of data mapping between RAN and core slice aggregations using S-NSSAI and transport slice identifier are further described, for example, in International Patent Application No. PCT / US22 / 28951, entitled "Transport Slice Identifier for End-to-End Network Slice Mapping," filed May 12, 2022, the entire contents of which are incorporated herein by reference for all purposes. 2) Data mapping between Tx-Slice-IDs and logical DFP paths used in the network. Implementation forms of data mapping between Tx-Slice-IDs and logical DFP paths used in the network are further described, for example, in the aforementioned International Patent Application No. PCT / US22 / 28951, filed May 12, 2022, entitled "Transport Slice Identifiers for End-to-End Network Slice Mapping." 3) Telemetry data providing forwarding plane health such as central processing unit (CPU) consumption, memory utilization, route limits, MAC limits etc. for each DFP. Telemetry is a well-known mechanism for the automatic recording and transmission of data from remote systems / nodes to a monitoring system. 4) A traffic matrix that provides the bandwidth consumption of all slice flows for each transport link. The traffic matrix can be used to determine bandwidth usage SLAs. FIG. 9 illustrates an implementation of a traffic matrix label, according to some implementations of the present subject matter. The traffic matrix can be used to determine per-flow bandwidth at the network-to-network interface (NNI) of the transport network. At a given interface level, using segment routing accounting functions (e.g., segment routing over IPv6 (SRv6) DM counters) or NetFlow or access list counters (ACLs), a given node can identify slice flows and bandwidth usage, as shown in FIG. 9 between R1 and R2. 5) SRv6 Transport Network Performance Management (SRv6-PM) Reports, which are probes sent by an ingress provider edge (PE) 808, a node connected to the RAN domain 612, to an egress PE 810, a node connected to the core domain 616, to determine latency, packet drops, and packet delay variation.

[0105] In some implementations, all five types of input data 1)-5) are used by the AI / ML 804. The five types of input data 1)-5) can be the only input data used by the AI / ML 804, or one or more additional types of input data can be used by the AI / ML 804. In some implementations, fewer than all five types of input data 1)-5) are used by the AI / ML 804. One, two, three, or four types of input data 1)-5) can be used by the AI / ML 804, with or without one or more additional types of input data.

[0106] As shown in FIG. 8a, the integration between the NSMF 702 and the AI / ML 804 can provide input data to the AI / ML 804, including the required SLAs assigned to each S-NSSA ID. Using this information, the AI / ML 804 knows the actual slice SLAs requested by the application. An interface between the NSC 706 and the AI / ML 804, e.g., the REST-API interface 806, allows the AI / ML 804 to know the status of transport domain slice performance in the transport domain 614 (e.g., the health of the DFP and SLAs achieved using the Tx-Sice-ID and its mapping with the S-NSSA ID). Using this framework, the AI / ML 804 can determine whether the transport domain slice model meets the actual end-to-end SLA requirements between the UE 608 and the UPF and whether the transport domain slice model complies with the overall SLA targets. The AI / ML 804 can use this information to train an AI / ML model to predict transport domain network slice performance metrics. The transport domain slice performance score can be seen as an indicator for corrective action and more visibility into the end-to-end slice model.

[0107] 8b shows an example implementation of a network slice architecture 800 incorporating an AI / ML 804 in an NSC / TN domain manager 706. Thus, in this implementation, the AI / ML 804 is deployed in the NSC / TN domain manager 706 (e.g., in the NSC, in the TN domain manager, or in both the NSC and the TN domain manager). The AI / ML 804 integrated with the NSC / TN domain manager 706 can be deployed within the NSC / TN domain manager 706 or can run on an external application server. A RESTful interface (REST-API interface) 806 between the NSMF 702 and the NSC 706 enables the NSC 706 to collect input data from the NSMF 702, such as slice mapping and application SLA information from the NSMF 702. The NSMF 706 can also provide high-level policy guidance to the TN Domain Manager / NSC 706 via a REST-API interface 806, influencing TN Domain Slice management from a high level by taking into account the full picture of the network E2E Slice environment.

[0108] FIG. 10 illustrates an exemplary implementation of an AI / ML 804 configured to run integrated with the NSMF 702 (FIG. 8a) or the NSC 706 (FIG. 8b) and provide transport network domain slice performance monitoring, analysis, and SLA guarantees, according to various implementations disclosed herein. The AI / ML 804 includes a data collection / pre-processing module 1000 configured to receive input data 1002 via at least one port 1004. The input data 1002 illustrated in FIG. 10 includes the five types of data (1) through (5) described above. Accordingly, five ports 1004 are illustrated in FIG. 10, with each port 1004 configured to communicate one of the input data 1002. The data collection / pre-processing module 1000 is configured to collect the input data 1002 from the network and pre-process the collected input data. The data collection / pre-processing performed by the data collection / pre-processing module 1000 can be performed according to standard data processing techniques.

[0109] The data collection / preprocessing module 1000 is configured to deliver structured data packets ready to be processed by AI / ML to the model selection / training module 1006 of the AI / ML 804 for AI / ML model training. The training performed by the model selection / training module 1006 can be done either offline or online.

[0110] The model selection / training module 1006 is configured to select an AI / ML model from a plurality of AI / ML models 1010 stored in an AI / ML model repository 1012 accessible to the model selection / training module 1006. Although three types of AI / ML models 1010 are shown in FIG. 10 (linear regression model, feedforward network (FFN) / convolutional neural network (CNN) model, and long short-term memory (LSTM) model), the AI / ML model repository 1012 may include fewer than three types of AI / ML models or more than three types of AI / ML models. Additionally, the AI / ML models 1010 stored in the AI / ML model repository 1012 may include zero, one, two, or three of the linear regression, FFN / CNN, and LSTM AI / ML model types shown in FIG. 10. In some implementations, CNNs can be used by the AI / ML 804 for classification and pattern recognition tasks that recognize hidden patterns in input data and derive a performance score by classifying performance levels. In some implementations, for prediction tasks, the AI / ML 804 can use either linear regression models for simplicity, or FFN and LSTM models for powerful predictive performance and accuracy at the cost of complexity.

[0111] The model selection / training module 1006 can select one of the AI / ML models 1010 in any of a variety of ways. In some implementations of the present subject matter, the model selection / training module 1006 can randomly select one of the AI / ML models 1010. In some implementations of the present subject matter, a user (e.g., user 1014) can input initial configuration requirements (e.g., target performance / accuracy desired to achieve, etc.) to the AI / ML 804 via the NSMF 702 ( FIG. 8 a) or the NSC 706 ( FIG. 8 b). The model selection / training module 1006 can be configured to select one of the AI / ML models 1010 based on the initial configuration requirements. In implementations in which the AI / ML model repository 1012 includes only one AI / ML model, the model selection / training module 1006 can be configured to select one of the AI / ML models 1010 regardless of the input initial configuration requirements.

[0112] The model selection / training module 1006 is configured to deliver the trained and selected AI / ML model 1010 to a key performance indicator (KPI) evaluation / prediction module 1008 of the AI / ML 804. The data collection / preprocessing module 1000 is configured to deliver structured data packets to the KPI evaluation / prediction module 1008. Thus, the KPI evaluation / prediction module 1008 has data to evaluate and an AI / ML model to perform the evaluation. The KPI evaluation / prediction module 1008 can also access top-level network configuration information 1016, e.g., data stored in one or more databases, one or more memories, etc., so that the KPI evaluation / prediction module 1008 is aware of the configuration parameters of the network. The top-level network configuration information 1016 in this illustrated implementation includes TN topology information, TN configuration information, high-level policy information, and subnet information. 10 shows four types of top-level network configuration information 1016, the top-level network configuration information 1016 may include fewer than four types of top-level network configuration information or may include more than four types of top-level network configuration information. Additionally, the top-level network configuration information 1016 available to the KPI evaluation / prediction module 1008 may include zero, one, two, three, or four of the four types of top-level network configuration information shown in FIG.

[0113] The KPI evaluation / prediction module 1008 is configured to generate a performance score for the TN slice after evaluating the performance of DFP (logical forwarding resource) and met / violated SLAs for each logical / slice topology using the AI / ML model 1010 received from the model selection / training module 1006 in evaluating the data received from the data collection / preprocessing module 1000. A low performance score on a TN slice can be either an SLA violation or a poor performance indicator.

[0114] The KPI evaluation / prediction module 1008 can also be configured to predict future performance of DFPs and SLAs based on historical data inputs for proactive action.

[0115] The KPI evaluation / prediction module 1008 is configured to provide the evaluated (current) and predicted (future) performance scores and KPIs to a user 1014 (e.g., administrator, operator, etc.) dashboard or reporting / logging subsystem 1018. Providing the evaluated and predicted performance scores and KPIs to the dashboard or reporting / logging subsystem 1018 allows the user to take any necessary corrective action. The corrective action can be, for example, either creating a new forwarding plane as desired by the network's application or allocating additional network space as desired by the slicing application.

[0116] The KPI evaluation / prediction module 1008 is configured to provide evaluated (current) and predicted (future) performance scores and KPIs to the SLA assurance actor 1020. The SLA assurance actor 1020 is configured to generate automated slice management and SLA assurance actions.

[0117] 11 illustrates an implementation of a UE 1100 configured for AI / ML-based transport network domain slice performance monitoring, analysis, and SLA guarantees in accordance with implementations disclosed herein. As shown in FIG. 11, the UE 1100 may include at least one storage device or memory 1102, at least one processor 1104, at least one communication unit 1106, and at least one network slice controller 1108.

[0118] The memory 1102 is configured to store instructions executed by the processor 1104. The memory 1102 may include non-volatile storage elements. Examples of such non-volatile storage elements may include magnetic hard disks, optical disks, floppy disks, flash memory, or forms of electrically programmable memory (EPROM) or electrically erasable programmable memory (EEPROM). Additionally, the memory 1102 may, in some examples, be considered a non-transitory storage medium. The term "non-transitory" may indicate that the storage medium is not embodied in a carrier wave or propagating signal. However, the term "non-transitory" should not be interpreted as meaning that the memory 1102 is non-removable. In some examples, the memory 1102 is configured to store larger amounts of information. In particular examples, the non-transitory storage medium may store data that may change over time (e.g., in random access memory (RAM) or cache).

[0119] The processor 1104 may be a CPU, a general-purpose processor such as an application processor (AP), a graphics-specific processing unit such as a graphics processing unit (GPU) or a visual processing unit (VPU), and / or an AI-specific processor such as a neural processing unit (NPU). The processor 1104 may include multiple cores and is configured to execute instructions stored in the memory 1102.

[0120] Communications unit 1106 is configured to communicate internally between internal hardware components of user equipment 1100 and with external devices via one or more networks. Communications unit 1106 may include standard-specific electronic circuitry that enables wired or wireless communication.

[0121] The network slice controller 1108 is configured to include AI / ML (e.g., AI / ML 804, etc.) as described herein to monitor and analyze TN domain slice performance and generate any corrective actions necessary to optimize and guarantee E2E network slice SLAs from TN domain aspects.

[0122] In some implementations, the present subject matter can be configured to be implemented in a system 1200, as shown in FIG. 12 . The system 1200 can include one or more of a processor 1210, a memory 1220, a storage device 1230, and an input / output device 1240. Each of the components 1210, 1220, 1230, and 1240 can be interconnected using a system bus 1250. The processor 1210 can be configured to process instructions for execution within the system 600. In some implementations, the processor 1210 can be a single-threaded processor. In alternative implementations, the processor 1210 can be a multi-threaded processor. The processor 1210 can be further configured to process instructions stored in the memory 1220 or the storage device 1230, including receiving or sending information through the input / output device 1240. The memory 1220 can store information within the system 1200. In some implementations, the memory 1220 can be a computer-readable medium. In alternative implementations, memory 1220 may be a volatile memory unit. Further, in some implementations, memory 1220 may be a non-volatile memory unit. Storage device 1230 may be capable of providing mass storage for system 1200. In some implementations, storage device 1230 may be a computer-readable medium. In alternative implementations, storage device 1230 may be a floppy disk device, a hard disk device, an optical disk device, a tape device, a non-volatile solid-state memory, or any other type of storage device. Input / output device 1240 may be configured to provide input / output operations for system 1200. In some implementations, input / output device 1240 may include a keyboard and / or a pointing device. In alternative implementations, input / output device 1240 may include a display unit for displaying a graphical user interface.

[0123] An apparatus according to some implementations of the present subject matter may include an NSMF and a TN-NSSMF. The NSMF is configured to request at least a TN domain of a network architecture in a wireless communication system to create a TN portion of a network slice. The TN-NSSMF is configured to manage the TN portion of the network slice. One of the NSMF and the TN-NSSMF has AI / ML integrated therein that is configured to enable the one of the NSMF and the TN-NSSMF to monitor and analyze performance of the network slice of the TN domain.

[0124] In some implementations, the present subject matter can include one or more of the following optional features.

[0125] In some implementations, the device may further include a REST-API interface between the NSMF and the TN-NSSMF.

[0126] In some implementations, one of the NSMF and the TN-NSSMF in which the AI / ML is integrated may be the NSMF. Furthermore, the NSMF may be configured to collect input data for the AI / ML, and the input data may include one or more of the following: data mapping between radio access network (RAN) and core slice aggregations by S-NSSAI and Tx-Slice-ID, data mapping between Tx-Slice-ID and logical DFP paths, telemetry data providing forwarding plane health for each DFP, a traffic matrix providing bandwidth consumption of all slice flows for each transport link, and an SRv6-PM report. Furthermore, the device may also include a REST-API interface between the NSMF and the TN-NSSMF, and the NSMF may be configured to collect at least a portion of the input data for the AI / ML via the REST-API interface.

[0127] In some implementations, one of the NSMF and the TN-NSSMF in which the AI / ML is integrated may be the TN-NSSMF. Furthermore, the TN-NSSMF may include an NSC, a TN domain manager, or both an NSC and a TN domain manager. The TN-NSSMF may be configured to collect input data for the AI / ML, and the input data may include one or more of the following: data mapping between RAN and core slice aggregations by S-NSSAI and Tx-Slice-ID, data mapping between Tx-Slice-ID and logical dedicated forwarding plane (DFP) paths, telemetry data providing forwarding plane health for each DFP, a traffic matrix providing bandwidth consumption of all slice flows for each transport link, and an SRv6-PM report. And / or, the device may also include a REST-API interface between the NSMF and the TN-NSSMF, and the TN-NSSMF may include an NSC, and the NSC may be configured to collect slice mapping and application SLA information from the NSMF via the REST-API interface.

[0128] In some implementations, the NSMF can be configured to be communicatively coupled to a TN domain, a RAN domain, and a CN domain. Further, the RAN domain can include at least one base station therein, and the base station can include at least one of an eNodeB and a gNodeB.

[0129] In some implementations, the wireless communication system may include at least one of a 5G NR communication system and an LTE communication system.

[0130] In some implementations, the AI / ML includes a linear regression model, a feed-forward network (FFN) / convolutional neural network (CNN) model, or a long-short-term memory (LSTM) model. Further, the AI / ML may include a model repository including one or more of the linear regression model, the FFN / CNN model, and the LSTM model, and the AI / ML is configured to select a model from the model repository randomly or based on initial configuration requirements input by a user. Further, the AI / ML may be configured to use the selected model to perform an evaluation of structured data packets and / or configuration parameters of the wireless communication system to generate a performance score for the network slice. The configuration parameters may include one or more of TN topology information, TN configuration information, high-level policy information, and subnet information. Further, the AI / ML may be configured to take corrective action based on the performance score of the network slice, and the corrective action may include creating a new forwarding plane or assigning an additional network to the network slice.

[0131] The systems and methods disclosed herein may be embodied in various forms, including, for example, a data processor such as a computer, including a database, digital electronic circuitry, firmware, software, or any combination thereof. Furthermore, the above-described features and other aspects and principles of implementations of the present disclosure may be implemented in a variety of environments. Such environments and associated applications may be specially constructed to perform the various processes and operations in accordance with the disclosed implementations, or they may comprise general-purpose computers or computing platforms selectively activated or reconfigured by code to provide the required functionality. The processes disclosed herein are not inherently related to any particular computer, network, architecture, environment, or other apparatus, but may be implemented by any suitable combination of hardware, software, and / or firmware. For example, various general-purpose machines may be used with programs written in accordance with the teachings of the disclosed implementations, or it may be more convenient to construct specialized apparatus or systems to perform the required methods and techniques.

[0132] The systems and methods disclosed herein can be implemented as a computer program product, i.e., a computer program tangibly embodied in an information carrier, e.g., a machine-readable storage device or a propagated signal, for execution by or to control the operation of a data processing apparatus, e.g., a programmable processor, computer, or multiple computers. The computer program can be written in any type of programming language, including compiled or interpreted languages, and can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. The computer program can be deployed to be executed on one computer or on multiple computers at one site or distributed across multiple sites and interconnected by a communications network.

[0133] As used herein, the term "user" can refer to any entity, including a person or a computer.

[0134] Although ordinal numbers such as first, second, etc. may relate to order in some circumstances, as used in this document, ordinal numbers do not necessarily imply order. For example, ordinal numbers may be used simply to distinguish one item from another. For example, distinguishing a first event from a second event need not imply any chronological order or fixed frame of reference (just as the first event in one paragraph of a description may differ from the first event in another paragraph of the description).

[0135] The foregoing description is intended to illustrate, but not to limit, the scope of the invention, which is defined by the appended claims. Other implementations are within the scope of the following claims.

[0136] These computer programs, which may also be referred to as programs, software, software applications, applications, components, or code, include machine instructions for a programmable processor and may be implemented in a high-level procedural and / or object-oriented programming language and / or in assembly / machine language. As used herein, the term “machine-readable medium” refers to any computer program product, apparatus, and / or device used to provide machine instructions and / or data to a programmable processor, such as, for example, a magnetic disk, an optical disk, a memory, and a programmable logic device (PLD), including a machine-readable medium that receives machine instructions as a machine-readable signal. The term “machine-readable signal” refers to any signal used to provide machine instructions and / or data to a programmable processor. A machine-readable medium may non-transitory store such machine instructions, such as, for example, a non-transitory solid-state memory or a magnetic hard drive or any equivalent storage medium. Alternatively or additionally, a machine-readable medium may temporarily store such machine instructions, such as, for example, a processor cache or other random access memory associated with one or more physical processor cores.

[0137] To provide for user interaction, the subject matter described herein can be implemented on a computer having a display device, such as a cathode ray tube (CRT) or liquid crystal display (LCD) monitor, for displaying information to the user, and a keyboard and pointing device, such as a mouse or trackball, by which the user can provide input to the computer. Other types of devices can also be used to provide for user interaction. For example, feedback provided to the user can be any form of sensory feedback, such as visual feedback, auditory feedback, or tactile feedback, and input from the user can be received in any form, including, but not limited to, acoustic, speech, or tactile input.

[0138] The subject matter described herein can be implemented in a computing system that includes back-end components, such as, for example, one or more data servers, or includes middleware components, such as, for example, one or more application servers, or includes front-end components, such as, for example, one or more client computers having a graphical user interface or web browser through which a user can interact with an implementation of the subject matter described herein, or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication, such as, for example, a communications network. Examples of communications networks include, but are not limited to, a local area network ("LAN"), a wide area network ("WAN"), and the Internet.

[0139] A computing system may include clients and servers. Clients and servers are generally, but not exclusively, remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

[0140] The implementations described in the foregoing description do not represent all implementations consistent with the subject matter described herein. Rather, they are merely some examples consistent with aspects related to the described subject matter. While several variations have been described in detail above, other modifications or additions are possible. In particular, additional features and / or variations may be provided in addition to those described herein. For example, the implementations described above may be directed to various combinations and subcombinations of the disclosed features and / or combinations and subcombinations of certain additional features disclosed above. Additionally, the logic flow illustrated in the accompanying figures and / or described herein does not necessarily require the particular order shown, or sequential order, to achieve desirable results. Other implementations may be within the scope of the following claims.

Claims

1. In a wireless communication system, a Network Slice Management Function (NSMF) configured to request at least a Transport Network (TN) domain of a network architecture to create a TN part of a network slice; and a transport network-network slice subnet management function (TN-NSSMF) configured to manage the TN portion of the network slice; An apparatus having artificial intelligence / machine learning (AI / ML) integrated therein, the apparatus being configured to enable one of the NSMF and the TN-NSSMF to monitor and analyze performance of the network slice in the TN domain.

2. The apparatus of claim 1 , further comprising a Representational State Transfer Application Programming Interface (REST-API) interface between the NSMF and the TN-NSSMF.

3. 3. The apparatus of claim 1, wherein the one of the NSMF and the TN-NSSMF in which the AI / ML is integrated is the NSMF.

4. The NSMF is configured to collect input data from the TN-NSSMF for the AI / ML workflow, the input data including one or more of the following: Data mapping between radio access network (RAN) and core slice aggregations via S-NSSAI and transport slice identifier (Tx-Slice-ID); Data mapping between Tx-Slice-ID and logical Dedicated Forwarding Plane (DFP) paths; Telemetry data providing the health of the forwarding plane for each DFP; a traffic matrix providing the bandwidth consumption of all slice flows for each transport link; and Segment Routing over IPv6 (SRv6) Performance Management (SRv6-PM) Report, 4. The apparatus of claim 3.

5. a Representational State Transfer Application Programming Interface (REST-API) interface between the NSMF and the TN-NSSMF; The apparatus of claim 4 , wherein the NSMF is configured to collect at least some of the input data for the workflow of the AI / ML via the REST-API interface.

6. The apparatus of claim 4 or 5, wherein the workflow of the AI / ML includes model training and / or inference.

7. 2. The apparatus of claim 1, wherein the one of the NSMF and the TN-NSSMF in which the AI / ML is integrated is the TN-NSSMF.

8. The apparatus of claim 7 , wherein the TN-NSSMF includes a network slice controller (NSC) or a TN domain manager.

9. The TN-NSSMF is configured to collect input data for the AI / ML, the input data including one or more of the following: Data mapping between radio access network (RAN) and core slice aggregations via S-NSSAI and transport slice identifier (Tx-Slice-ID); Data mapping between Tx-Slice-ID and logical Dedicated Forwarding Plane (DFP) paths; Telemetry data providing the health of the forwarding plane for each DFP; a traffic matrix providing the bandwidth consumption of all slice flows for each transport link; and Segment Routing over IPv6 (SRv6) Performance Management (SRv6-PM) Report, 8. The apparatus of claim 7.

10. a Representational State Transfer Application Programming Interface (REST-API) interface between the NSMF and the TN-NSSMF; The apparatus according to claim 7 or 8, wherein the TN-NSSMF is configured to collect slice mapping and application service level agreement (SLA) information from the NSMF via the REST-API interface.

11. The apparatus of claim 1 , wherein the NSMF is configured to be communicatively coupled to the TN domain, a radio access network (RAN) domain, and a core network (CN) domain.

12. 12. The apparatus of claim 11, wherein the RAN domain includes at least one base station therein, the base station including at least one of an eNodeB and a gNodeB.

13. 13. The apparatus of claim 1, wherein the wireless communication system comprises at least one of a 5G New Radio (NR) communication system and a Long Term Evolution (LTE) communication system.

14. 14. The apparatus of claim 1, wherein the AI / ML comprises a linear regression model, a feedforward network (FFN) / convolutional neural network (CNN) model, or a long short-term memory (LSTM) model.

15. 15. The apparatus of claim 14, wherein the AI / ML comprises a model repository containing one or more of the linear regression model, the FFN / CNN model, and the LSTM model.

16. The apparatus of claim 15 , wherein the AI / ML is configured to select a model from the model repository randomly or based on initial configuration requirements entered by a user.

17. 17. The apparatus of claim 16, wherein the AI / ML is configured to use the selected model to perform an evaluation of structured data packets and / or configuration parameters of the wireless communication system and generate a performance score for the network slice.

18. 20. The apparatus of claim 17, wherein the configuration parameters include one or more of TN topology information, TN configuration information, high-level policy information, and subnet information.

19. the AI / ML is configured to take corrective action based on the performance score of the network slice; The apparatus of claim 17 or 18, wherein the corrective action comprises creating a new forwarding plane or allocating an additional network to the network slice.

20. An apparatus comprising a network slice management function (NSMF) and a transport network-network slice subnet management function (TN-NSSMF), The Network Slice Management Function (NSMF): at least one first processor; and at least one first non-transitory storage medium storing instructions that, when executed by the at least one first processor, request at least a transport network (TN) domain of a network architecture to create a TN portion of a network slice in a wireless communication system; The Transport Network - Network Slice Subnet Management Function (TN-NSSMF): at least one second processor; and at least one second non-transitory storage medium storing instructions that, when executed by the at least one second processor, manage the TN portion of the network slice; An apparatus having artificial intelligence / machine learning (AI / ML) integrated therein, the apparatus being configured to enable one of the NSMF and the TN-NSSMF to monitor and analyze performance of the network slice in the TN domain.

21. The apparatus of claim 20, further comprising a Representational State Transfer Application Programming Interface (REST-API) interface between the NSMF and the TN-NSSMF.

22. 22. The apparatus of claim 20 or 21, wherein said one of said NSMF and said TN-NSSMF in which said AI / ML is integrated is said NSMF.

23. The NSMF is configured to collect input data from the TN-NSSMF for the AI / ML workflow, the input data including one or more of the following: Data mapping between radio access network (RAN) and core slice aggregations via S-NSSAI and transport slice identifier (Tx-Slice-ID); Data mapping between Tx-Slice-ID and logical Dedicated Forwarding Plane (DFP) paths; Telemetry data providing the health of the forwarding plane for each DFP; a traffic matrix providing the bandwidth consumption of all slice flows for each transport link; and Segment Routing over IPv6 (SRv6) Performance Management (SRv6-PM) Report, 23. The apparatus of claim 22.

24. a Representational State Transfer Application Programming Interface (REST-API) interface between the NSMF and the TN-NSSMF; The apparatus of claim 23 , wherein the NSMF is configured to collect at least some of the input data for the workflow of the AI / ML via the REST-API interface.

25. 25. The apparatus of claim 23 or 24, wherein the workflow of the AI / ML includes model training and / or inference.

26. 21. The apparatus of claim 20, wherein the one of the NSMF and the TN-NSSMF in which the AI / ML is integrated is the TN-NSSMF.

27. The apparatus of claim 26, wherein the TN-NSSMF includes a network slice controller (NSC) or a TN domain manager.

28. The TN-NSSMF is configured to collect input data for the AI / ML, the input data including one or more of the following: Data mapping between radio access network (RAN) and core slice aggregations via S-NSSAI and transport slice identifier (Tx-Slice-ID); Data mapping between Tx-Slice-ID and logical Dedicated Forwarding Plane (DFP) paths; Telemetry data providing the health of the forwarding plane for each DFP; a traffic matrix providing the bandwidth consumption of all slice flows for each transport link; and Segment Routing over IPv6 (SRv6) Performance Management (SRv6-PM) Report, 27. The apparatus of claim 26.

29. a Representational State Transfer Application Programming Interface (REST-API) interface between the NSMF and the TN-NSSMF; The apparatus of claim 26 or 27, wherein the TN-NSSMF is configured to collect slice mapping and application service level agreement (SLA) information from the NSMF via the REST-API interface.

30. 30. The apparatus of claim 2, wherein the NSMF is configured to be communicatively coupled to the TN domain, a radio access network (RAN) domain, and a core network (CN) domain.

31. 31. The apparatus of claim 30, wherein the RAN domain includes at least one base station therein, the base station including at least one of an eNodeB and a gNodeB.

32. 32. The apparatus of any one of claims 20 to 31, wherein the wireless communication system comprises at least one of a 5G New Radio (NR) communication system and a Long Term Evolution (LTE) communication system.

33. 33. The apparatus of any one of claims 20 to 32, wherein the AI / ML comprises a linear regression model, a feedforward network (FFN) / convolutional neural network (CNN) model, or a long short-term memory (LSTM) model.

34. 34. The apparatus of claim 33, wherein the AI / ML comprises a model repository containing one or more of the linear regression model, the FFN / CNN model, and the LSTM model.

35. 35. The apparatus of claim 34, wherein the AI / ML is configured to select a model from the model repository randomly or based on initial configuration requirements entered by a user.

36. 36. The apparatus of claim 35, wherein the AI / ML is configured to use the selected model to perform an evaluation of structured data packets and / or configuration parameters of the wireless communication system and generate a performance score for the network slice.

37. 37. The apparatus of claim 36, wherein the configuration parameters include one or more of TN topology information, TN configuration information, high-level policy information, and subnet information.

38. 38. The apparatus of claim 36 or 37, wherein the AI / ML is configured to take corrective action based on the performance score of the network slice, the corrective action comprising creating a new forwarding plane or allocating an additional network to the network slice.

Images