Methods and apparatus for enabling split AIML computing in wireless systems based on service function chaining

Abstract

In some implementations, a process may include receiving, from a WTRU, a request to create a SC in a split AIML process. The process may include sending, to a network device, a SFC policy identifier to activate a respective SC policy, where the SFC policy identifier is determined according to the request to create the SC. The process may include receiving, from the WTRU, a data set that includes a SCID and a SC profile associated with SFC traffic. The process may include sending the data set to a first AF based on the SC profile, and receiving, from the first AF, a first modified data set. Further, the process may include sending, to a second AF, the first modified data set, where the second AF is determined based on the SC profile. The process may include receiving, from the second AF, a second modified data set.

Description

METHODS AND APPARATUS FOR ENABLING SPLIT AIML COMPUTING IN WIRELESS SYSTEMS BASED ON SERVICE FUNCTION CHAININGCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of U.S. Provisional Application No. 63 / 625,201 filed January 25, 2024 the contents of which are incorporated herein by reference.BACKGROUND

[0002] Artificial Intelligence Machine Learning (AIML) Split Inference (SI) is generally known as a technique for decentralizing the process of performing AIML inference using a trained model. AIML-SI may comprise different AIML models which may be executed on different hardware to derive inference result(s) and / or prediction(s). As an example, in a wireless environment, AIML-SI may enable the offload of compute-intensive operations to the network while keeping privacy sensitive data in the wireless device (e.g., UE). Edge Computing (EC) is an essential component for enabling responsive AIML-SI applications in mobile networks. EC may enable the delivery of extremely low latency services to a UE by provisioning these services near the edge of the network, i.e., in close proximity of the UE.SUMMARY

[0003] A system of one or more computers can be configured to perform particular operations or actions by virtue of having software, firmware, hardware, or a combination of them installed on the system that in operation causes or cause the system to perform the actions. One or more computer programs can be configured to perform particular operations or actions by virtue of including instructions that, when executed by data processing apparatus, cause the apparatus to perform the actions.

[0004] In one general aspect, a method may include receiving, from a wireless transmit / receive unit (WTRU), a request to create a service chain (SC) in a split artificial intelligence machine learning (AIML) process. The method may also include sending, to a network device, a service function chaining (SEC) policy identifier to activate a respective SC policy, where the SFC policy identifier is determined according to the request to create the SC. The method may furthermore include receiving, from the WTRU, a data set, where the data set includes a SC identifier (SCID) and a SC profile associated with SFC traffic. The method may in addition include sending the data set to a first AF based on the SC profile associated with the SFC traffic. The method may moreover include receiving, from the first AF, a first modified data set. The method may also include sending, to a second AF, the first modified data set, where the second AF is determined based on the SC profile. The method may furthermore include receiving, from the second AF, a second modified data set. Other embodiments of this aspect include corresponding computer systems, apparatus, and computerprograms recorded on one or more computer storage devices, each configured to perform the actions of the methods.BRIEF DESCRIPTION OF THE DRAWINGS

[0005] A more detailed understanding may be had from the following description, given by way of example in conjunction with the accompanying drawings, wherein like reference numerals in the figures indicate like elements, and wherein:

[0006] FIG. 1A is a system diagram illustrating an example communications system in which one or more disclosed embodiments may be implemented;

[0007] FIG. 1 B is a system diagram illustrating an example wireless transmit / receive unit (WTRU) that may be used within the communications system illustrated in FIG. 1A according to an embodiment;

[0008] FIG. 1C is a system diagram illustrating an example radio access network (RAN) and an example core network (CN) that may be used within the communications system illustrated in FIG. 1A according to an embodiment;

[0009] FIG. 1D is a system diagram illustrating a further example RAN and a further example CN that may be used within the communications system illustrated in FIG. 1A according to an embodiment;

[0010] FIG. 2 illustrates an example of a sequential AIML-SI where models are chained to form a three stage AIML-SI model;

[0011] FIG. 3 illustrates an example of a data-parallel AIML-SI where a model is used in parallel instances of application functions;

[0012] FIG. 4 illustrates an example of model-parallel AIML-SI for combined prediction;

[0013] FIG. 5 illustrates an example of a model-parallel AIML-SI example for distributed prediction;

[0014] FIG. 6 illustrates a high-level view of the SC lifecycle;

[0015] FIG. 7 illustrates an example of a system flow using the SCMF with SFC traffic forwarding and proxying;

[0016] FIG. 8 illustrates an example of a system flows when 5GC SFC capabilities are not used;

[0017] FIG. 9 illustrates an example of a Service Chain creation via connection capabilities process; and

[0018] FIG. 10 is a flowchart of an example process of a SCMF with SFC traffic forwarding and proxying.DETAILED DESCRIPTION

[0019] The following acronyms may be referred to in the description that follows:5GC 5G Core5GS 5G SystemAC Application ClientACID Application Client IdentifierAl ML Artificial Intelligence Machine LearningAS Application ServerCAS Cloud Application ServerCN Core NetworkDL DownlinkDN Data NetworkEAS Edge Application ServerEASDF Edge Application Server Discovery FunctionECS Edge Configuration ServerEDC Edge Discovery ClientEDN Edge Data NetworkEEC Edge Enabler ClientEEL Edge Enablement LayerEES Edge Enabler ServerFQDN Fully Qualified Domain NameIE Information ElementLTE Long Term Evolution e.g., from 3GPP LTE R8 and upNEF Network Exposure FunctionNF Network FunctionPCF Policy Control FunctionPDU Packet Data UnitPSA PDU Session AnchorRAN Radio Access NetworkSC Service ChainSI Split InferenceSFC Service Function ChainingSFF Service Function ForwardingSMF Session Management FunctionTSP Traffic Steering PoliciesUE User EquipmentUL UplinkUPF User Plane FunctionURI Universal Resource IdentifierURL Universal Resource Locator

[0020] FIG. 1A is a diagram illustrating an example communications system 100 in which one or more disclosed embodiments may be implemented. The communications system 100 may be a multiple access system that provides content, such as voice, data, video, messaging, broadcast, etc., to multiple wireless users. The communications system 100 may enable multiple wireless users to access such content through the sharing of system resources, including wireless bandwidth. For example, the communications systems 100 may employ one or more channel access methods, such as code division multiple access (CDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), singlecarrier FDMA (SC-FDMA), zero-tail unique-word discrete Fourier transform Spread OFDM (ZT-UW-DFT-S- OFDM), unique word OFDM (UW-OFDM), resource block-filtered OFDM, filter bank multicarrier (FBMC), and the like.

[0021] As shown in FIG. 1A, the communications system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, a radio access network (RAN) 104, a core network (ON) 106, a public switched telephone network (PSTN) 108, the Internet 110, and other networks 112, though itwill be appreciated that the disclosed embodiments contemplate any number of WTRUs, base stations, networks, and / or network elements. Each of the WTRUs 102a, 102b, 102c, 102d may be any type of device configured to operate and / or communicate in a wireless environment By way of example, the WTRUs 102a, 102b, 102c, 102d, any of which may be referred to as a station (STA), may be configured to transmit and / or receive wireless signals and may include a user equipment (UE), a mobile station, a fixed or mobile subscriber unit, a subscription-based unit, a pager, a cellular telephone, a personal digital assistant (PDA), a smartphone, a laptop, a netbook, a personal computer, a wireless sensor, a hotspot or Mi-Fl device, an Internet of Things (loT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (e.g., remote surgery), an industrial device and applications (e.g., a robot and / or other wireless devices operating in an industrial and / or an automated processing chain contexts), a consumer electronics device, a device operating on commercial and / or industrial wireless networks, and the like. Any of the WTRUs 102a, 102b, 102c and 102d may be interchangeably referred to as a UE.

[0022] The communications systems 100 may also include a base station 114a and / or a base station 114b. Each of the base stations 114a, 114b may be any type of device configured to wirelessly interface with at least one of the WTRUs 102a, 102b, 102c, 102d to facilitate access to one or more communication networks, such as the CN 106, the Internet 110, and / or the other networks 112. By way of example, the base stations 114a, 114b may be a base transceiver station (BTS), a NodeB, an eNode B (eNB), a Home Node B, a Home eNode B, a next generation NodeB, such as a gNode B (gNB), a new radio (NR) NodeB, a site controller, an access point (AP), a wireless router, and the like. While the base stations 114a, 114b are each depicted as a singleelement, it will be appreciated that the base stations 114a, 114b may include any number of interconnected base stations and / or network elements.

[0023] The base station 114a may be part of the RAN 104, which may also include other base stations and / or network elements (not shown), such as a base station controller (BSC), a radio network controller (RNC), relay nodes, and the like. The base station 114a and / or the base station 114b may be configured to transmit and / or receive wireless signals on one or more carrier frequencies, which may be referred to as a cell (not shown). These frequencies may be in licensed spectrum, unlicensed spectrum, or a combination of licensed and unlicensed spectrum A cell may provide coverage for a wireless service to a specific geographical area that may be relatively fixed or that may change over time. The cell may further be divided into cell sectors. For example, the cell associated with the base station 114a may be divided into three sectors. Thus, in one embodiment, the base station 114a may include three transceivers, i.e., one for each sector of the cell. In an embodiment, the base station 114a may employ multiple-input multiple output (MIMO) technology and may utilize multiple transceivers for each sector of the cell. For example, beamforming may be used to transmit and / or receive signals in desired spatial directions.

[0024] The base stations 114a, 114b may communicate with one or more of the WTRUs 102a, 102b, 102c, 102d over an air interface 116, which may be any suitable wireless communication link (e.g., radio frequency (RF), microwave, centimeter wave, micrometer wave, infrared (IR), ultraviolet (UV), visible light, etc.). The air interface 116 may be established using any suitable radio access technology (RAT).

[0025] More specifically, as noted above, the communications system 100 may be a multiple access system and may employ one or more channel access schemes, such as CDMA, TDMA, FDMA, OFDMA, SC-FDMA, and the like. For example, the base station 114a in the RAN 104 and the WTRUs 102a, 102b, 102c may implement a radio technology such as Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access (UTRA), which may establish the air interface 116 using wideband CDMA (WCDMA). WCDMA may include communication protocols such as High-Speed Packet Access (HSPA) and / or Evolved HSPA (HSPA+). HSPA may include High-Speed Downlink (DL) Packet Access (HSDPA) and / or High-Speed Uplink (UL) Packet Access (HSUPA).

[0026] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as Evolved UMTS Terrestrial Radio Access (E-UTRA), which may establish the air interface 116 using Long Term Evolution (LTE) and / or LTE-Advanced (LTE-A) and / or LTE-Advanced Pro (LTE-A Pro).

[0027] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as NR Radio Access , which may establish the air interface 116 using NR.

[0028] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement multiple radio access technologies. For example, the base station 114a and the WTRUs 102a, 102b, 102c may implement LTE radio access and NR radio access together, for instance using dual connectivity (DC) principles. Thus, the air interface utilized by WTRUs 102a, 102b, 102c may be characterized by multiple types of radioaccess technologies and / or transmissions sent to / from multiple types of base stations (e.g , an eNB and a gNB).

[0029] In other embodiments, the base station 114a and the WTRUs 102a, 102b, 102c may implement radio technologies such as IEEE 802.11 (i.e , Wireless Fidelity (WiFi), IEEE 802.16 (i.e., Worldwide Interoperability for Microwave Access (WiMAX)), CDMA2000, CDMA2000 1X, CDMA2000 EV-DO, Interim Standard 2000 (IS-2000), Interim Standard 95 (IS-95), Interim Standard 856 (IS-856), Global System for Mobile communications (GSM), Enhanced Data rates for GSM Evolution (EDGE), GSM EDGE (GERAN), and the like.

[0030] The base station 114b in FIG 1A may be a wireless router, Home Node B, Home eNode B, or access point, for example, and may utilize any suitable RAT for facilitating wireless connectivity in a localized area, such as a place of business, a home, a vehicle, a campus, an industrial facility, an air corridor (e.g., for use by drones), a roadway, and the like. In one embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.11 to establish a wireless local area network (WLAN). In an embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.15 to establish a wireless personal area network (WPAN). In yet another embodiment, the base station 114b and the WTRUs 102c, 102d may utilize a cellular-based RAT (e.g., WCDMA, CDMA2000, GSM, LTE, LTE-A, LTE-A Pro, NR etc.) to establish a picocell or femtocell. As shown in FIG. 1A, the base station 114b may have a direct connection to the Internet 110. Thus, the base station 114b may not be required to access the Internet 110 via the CN 106.

[0031] The RAN 104 may be in communication with the CN 106, which may be any type of network configured to provide voice, data, applications, and / or voice over internet protocol (VoIP) services to one or more of the WTRUs 102a, 102b, 102c, 102d. The data may have varying quality of service (QoS) requirements, such as differing throughput requirements, latency requirements, error tolerance requirements, reliability requirements, data throughput requirements, mobility requirements, and the like. The CN 106 may provide call control, billing services, mobile location-based services, pre-paid calling, Internet connectivity, video distribution, etc., and / or perform high-level security functions, such as user authentication. Although not shown in FIG. 1A, it will be appreciated that the RAN 104 and / or the CN 106 may be in direct or indirect communication with other RANs that employ the same RAT as the RAN 104 or a different RAT. For example, in addition to being connected to the RAN 104, which may be utilizing a NR radio technology, the CN 106 may also be in communication with another RAN (not shown) employing a GSM, UMTS, CDMA 2000, WiMAX, E-UTRA, or WiFi radio technology.

[0032] The CN 106 may also serve as a gateway for the WTRUs 102a, 102b, 102c, 102d to access the PSTN 108, the Internet 110, and / or the other networks 112. The PSTN 108 may include circuit-switched telephone networks that provide plain old telephone service (POTS). The Internet 110 may include a global system of interconnected computer networks and devices that use common communication protocols, such as the transmission control protocol (TCP), user datagram protocol (UDP) and / or the internet protocol (IP) in the TCP / IP internet protocol suite. The networks 112 may include wired and / or wireless communications networksowned and / or operated by other service providers. For example, the networks 112 may include another CN connected to one or more RANs, which may employ the same RAT as the RAN 104 or a different RAT.

[0033] Some or all of the WTRUs 102a, 102b, 102c, 102d in the communications system 100 may include multi-mode capabilities (e.g., the WTRUs 102a, 102b, 102c, 102d may include multiple transceivers for communicating with different wireless networks over different wireless links). For example, the WTRU 102c shown in FIG. 1 A may be configured to communicate with the base station 114a, which may employ a cellularbased radio technology, and with the base station 114b, which may employ an IEEE 802 radio technology.

[0034] FIG. 1 B is a system diagram illustrating an example WTRU 102. As shown in FIG. 1 B, the WTRU 102 may include a processor 118, a transceiver 120, a transmit / receive element 122, a speaker / microphone 124, a keypad 126, a display / touchpad 128, non-removable memory 130, removable memory 132, a power source 134, a global positioning system (GPS) chipset 136, and / or other peripherals 138, among others. It will be appreciated that the WTRU 102 may include any sub-combination of the foregoing elements while remaining consistent with an embodiment.

[0035] The processor 118 may be a general purpose processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), a plurality of microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs), any other type of integrated circuit (IC), a state machine, and the like. The processor 118 may perform signal coding, data processing, power control, input / output processing, and / or any other functionality that enables the WTRU 102 to operate in a wireless environment. The processor 118 may be coupled to the transceiver 120, which may be coupled to the transmit / receive element 122. While FIG. 1 B depicts the processor 118 and the transceiver 120 as separate components, it will be appreciated that the processor 118 and the transceiver 120 may be integrated together in an electronic package or chip.

[0036] The transmit / receive element 122 may be configured to transmit signals to, or receive signals from, a base station (e.g., the base station 114a) over the air interface 116. For example, in one embodiment, the transmit / receive element 122 may be an antenna configured to transmit and / or receive RF signals. In an embodiment, the transmit / receive element 122 may be an emitter / detector configured to transmit and / or receive IR, UV, or visible light signals, for example. In yet another embodiment, the transmit / receive element 122 may be configured to transmit and / or receive both RF and light signals. It will be appreciated that the transmit / receive element 122 may be configured to transmit and / or receive any combination of wireless signals.

[0037] Although the transmit / receive element 122 is depicted in FIG. 1 B as a single element, the WTRU 102 may include any number of transmit / receive elements 122. More specifically, the WTRU 102 may employ MIMO technology. Thus, in one embodiment, the WTRU 102 may include two or more transmit / receive elements 122 (e g., multiple antennas) for transmitting and receiving wireless signals over the air interface 116.

[0038] The transceiver 120 may be configured to modulate the signals that are to be transmitted by the transmit / receive element 122 and to demodulate the signals that are received by the transmit / receive element122. As noted above, the WTRU 102 may have multi-mode capabilities. Thus, the transceiver 120 may include multiple transceivers for enabling the WTRU 102 to communicate via multiple RATs, such as NR and IEEE 802.11 , for example.

[0039] The processor 118 of the WTRU 102 may be coupled to, and may receive user input data from, the speaker / microphone 124, the keypad 126, and / or the display / touchpad 128 (e.g., a liquid crystal display (LCD) display unit or organic light-emitting diode (OLED) display unit) The processor 118 may also output user data to the speaker / microphone 124, the keypad 126, and / or the display / touchpad 128. In addition, the processor 118 may access information from, and store data in, any type of suitable memory, such as the non-removable memory 130 and / or the removable memory 132. The non-removable memory 130 may include random-access memory (RAM), read-only memory (ROM), a hard disk, or any other type of memory storage device. The removable memory 132 may include a subscriber identity module (SIM) card, a memory stick, a secure digital (SD) memory card, and the like. In other embodiments, the processor 118 may access information from, and store data in, memory that is not physically located on the WTRU 102, such as on a server or a home computer (not shown).

[0040] The processor 118 may receive power from the power source 134, and may be configured to distribute and / or control the power to the other components in the WTRU 102. The power source 134 may be any suitable device for powering the WTRU 102. For example, the power source 134 may include one or more dry cell batteries (e.g., nickel-cadmium (NiCd), nickel-zinc (NiZn), nickel metal hydride (NiMH), lithium-ion (Li- ion), etc.), solar cells, fuel cells, and the like.

[0041] The processor 118 may also be coupled to the GPS chipset 136, which may be configured to provide location information (e.g., longitude and latitude) regarding the current location of the WTRU 102. In addition to, or in lieu of, the information from the GPS chipset 136, the WTRU 102 may receive location information over the air interface 116 from a base station (e.g., base stations 114a, 114b) and / or determine its location based on the timing of the signals being received from two or more nearby base stations. It will be appreciated that the WTRU 102 may acquire location information by way of any suitable location-determination method while remaining consistent with an embodiment

[0042] The processor 118 may further be coupled to other peripherals 138, which may include one or more software and / or hardware modules that provide additional features, functionality and / or wired or wireless connectivity. For example, the peripherals 138 may include an accelerometer, an e-compass, a satellite transceiver, a digital camera (for photographs and / or video), a universal serial bus (USB) port, a vibration device, a television transceiver, a hands free headset, a Bluetooth® module, a frequency modulated (FM) radio unit, a digital music player, a media player, a video game player module, an Internet browser, a Virtual Reality and / or Augmented Reality (VR / AR) device, an activity tracker, and the like. The peripherals 138 may include one or more sensors. The sensors may be one or more of a gyroscope, an accelerometer, a hall effect sensor, a magnetometer, an orientation sensor, a proximity sensor, a temperature sensor, a time sensor; a geolocationsensor, an altimeter, a light sensor, a touch sensor, a magnetometer, a barometer, a gesture sensor, a biometric sensor, a humidity sensor and the like.

[0043] The WTRU 102 may include a full duplex radio for which transmission and reception of some or all of the signals (e g., associated with particular subframes for both the UL (e.g., for transmission) and DL (e.g., for reception) may be concurrent and / or simultaneous. The full duplex radio may include an interference management unit to reduce and or substantially eliminate self-interference via either hardware (e.g., a choke) or signal processing via a processor (e.g., a separate processor (not shown) or via processor 118). In an embodiment, the WTRU 102 may include a half-duplex radio for which transmission and reception of some or all of the signals (e.g., associated with particular subframes for either the UL (e g., for transmission) or the DL (e g., for reception)).

[0044] FIG. 1C is a system diagram illustrating the RAN 104 and the CN 106 according to an embodiment. As noted above, the RAN 104 may employ an E-UTRA radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 104 may also be in communication with the ON 106.

[0045] The RAN 104 may include eNode-Bs 160a, 160b, 160c, though it will be appreciated that the RAN 104 may include any number of eNode-Bs while remaining consistent with an embodiment. The eNode-Bs 160a, 160b, 160c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In one embodiment, the eNode-Bs 160a, 160b, 160c may implement MIMO technology. Thus, the eNode-B 160a, for example, may use multiple antennas to transmit wireless signals to, and / or receive wireless signals from, the WTRU 102a.

[0046] Each of the eNode-Bs 160a, 160b, 160c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in the UL and / or DL, and the like. As shown in FIG. 1 C, the eNode-Bs 160a, 160b, 160c may communicate with one another over an X2 interface.

[0047] The CN 106 shown in FIG. 1C may include a mobility management entity (MME) 162, a serving gateway (SGW) 164, and a packet data network (PDN) gateway (PGW) 166. While the foregoing elements are depicted as part of the CN 106, it will be appreciated that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0048] The MME 162 may be connected to each of the eNode-Bs 162a, 162b, 162c in the RAN 104 via an S1 interface and may serve as a control node. For example, the MME 162 may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, bearer activation / deactivation, selecting a particular serving gateway during an initial attach of the WTRUs 102a, 102b, 102c, and the like. The MME 162 may provide a control plane function for switching between the RAN 104 and other RANs (not shown) that employ other radio technologies, such as GSM and / or WCDMA

[0049] The SGW 164 may be connected to each of the eNode Bs 160a, 160b, 160c in the RAN 104 via the S1 interface. The SGW 164 may generally route and forward user data packets to / from the WTRUs 102a, 102b, 102c. The SGW 164 may perform other functions, such as anchoring user planes during inter-eNode Bhandovers, triggering paging when DL data is available for the WTRUs 102a, 102b, 102c, managing and storing contexts of the WTRUs 102a, 102b, 102c, and the like.

[0050] The SGW 164 may be connected to the PGW 166, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices.

[0051] The CN 106 may facilitate communications with other networks For example, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to circuit-switched networks, such as the PSTN 108, to facilitate communications between the WTRUs 102a, 102b, 102c and traditional land-line communications devices. For example, the CN 106 may include, or may communicate with, an IP gateway (e.g., an IP multimedia subsystem (IMS) server) that serves as an interface between the CN 106 and the PSTN 108. In addition, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to the other networks 112, which may include other wired and / or wireless networks that are owned and / or operated by other service providers.

[0052] Although the WTRU is described in FIGS. 1A-1 D as a wireless terminal, it is contemplated that in certain representative embodiments that such a terminal may use (e.g., temporarily or permanently) wired communication interfaces with the communication network.

[0053] In representative embodiments, the other network 112 may be a WLAN.

[0054] A WLAN in Infrastructure Basic Service Set (BSS) mode may have an Access Point (AP) for the BSS and one or more stations (STAs) associated with the AP. The AP may have access or an interface to a Distribution System (DS) or another type of wired / wireless network that carries traffic in to and / or out of the BSS. Traffic to STAs that originates from outside the BSS may arrive through the AP and may be delivered to the STAs. Traffic originating from STAs to destinations outside the BSS may be sent to the AP to be delivered to respective destinations. Traffic between STAs within the BSS may be sent through the AP, for example, where the source STA may send traffic to the AP and the AP may deliver the traffic to the destination STA The traffic between STAs within a BSS may be considered and / or referred to as peer-to-peer traffic. The peer-to- peer traffic may be sent between (e.g., directly between) the source and destination STAs with a direct link setup (DLS). In certain representative embodiments, the DLS may use an 802.11e DLS or an 802.11z tunneled DLS (TDLS). A WLAN using an Independent BSS (IBSS) mode may not have an AP, and the STAs (e.g., all of the STAs) within or using the IBSS may communicate directly with each other. The IBSS mode of communication may sometimes be referred to herein as an “ad-hoc” mode of communication.

[0055] When using the 802.11 ac infrastructure mode of operation or a similar mode of operations, the AP may transmit a beacon on a fixed channel, such as a primary channel. The primary channel may be a fixed width (e.g., 20 MHz wide bandwidth) or a dynamically set width. The primary channel may be the operating channel of the BSS and may be used by the STAs to establish a connection with the AP. In certain representative embodiments, Carrier Sense Multiple Access with Collision Avoidance (CSMA / CA) may be implemented, for example in 802.11 systems. For CSMA / CA, the STAs (e.g., every STA), including the AP, may sense the primary channel. If the primary channel is sensed / detected and / or determined to be busy by aparticular STA, the particular STA may back off. One STA (e.g., only one station) may transmit at any given time in a given BSS.

[0056] High Throughput (HT) STAs may use a 40 MHz wide channel for communication, for example, via a combination of the primary 20 MHz channel with an adjacent or nonadjacent 20 MHz channel to form a 40 MHz wide channel.

[0057] Very High Throughput (VHT) STAs may support 20MHz, 40 MHz, 80 MHz, and / or 160 MHz wide channels The 40 MHz, and / or 80 MHz, channels may be formed by combining contiguous 20 MHz channels. A 160 MHz channel may be formed by combining 8 contiguous 20 MHz channels, or by combining two noncontiguous 80 MHz channels, which may be referred to as an 80+80 configuration. For the 80+80 configuration, the data, after channel encoding, may be passed through a segment parser that may divide the data into two streams. Inverse Fast Fourier Transform (IFFT) processing, and time domain processing, may be done on each stream separately The streams may be mapped on to the two 80 MHz channels, and the data may be transmitted by a transmitting STA. At the receiver of the receiving STA, the above described operation for the 80+80 configuration may be reversed, and the combined data may be sent to the Medium Access Control (MAC).

[0058] Sub 1 GHz modes of operation are supported by 802.11 af and 802.11 ah. The channel operating bandwidths, and carriers, are reduced in 802.11 af and 802.11ah relative to those used in 802.11n, and 802.11ac. 802.11 af supports 5 MHz, 10 MHz, and 20 MHz bandwidths in the TV White Space (TVWS) spectrum, and 802.11 ah supports 1 MHz, 2 MHz, 4 MHz, 8 MHz, and 16 MHz bandwidths using non-TVWS spectrum. According to a representative embodiment, 802.11 ah may support Meter Type Control / Machine- Type Communications (MTC), such as MTC devices in a macro coverage area. MTC devices may have certain capabilities, for example, limited capabilities including support for (e.g , only support for) certain and / or limited bandwidths The MTC devices may include a battery with a battery life above a threshold (e.g., to maintain a very long battery life).

[0059] WLAN systems, which may support multiple channels, and channel bandwidths, such as 802 11 n, 802.11ac, 802.11 af, and 802.11 ah, include a channel which may be designated as the primary channel. The primary channel may have a bandwidth equal to the largest common operating bandwidth supported by all STAs in the BSS. The bandwidth of the primary channel may be set and / or limited by a STA, from among all STAs in operating in a BSS, which supports the smallest bandwidth operating mode. In the example of 802.11 ah, the primary channel may be 1 MHz wide for STAs (e.g., MTC type devices) that support (e.g., only support) a 1 MHz mode, even if the AP, and other STAs in the BSS support 2 MHz, 4 MHz, 8 MHz, 16 MHz, and / or other channel bandwidth operating modes. Carrier sensing and / or Network Allocation Vector (NAV) settings may depend on the status of the primary channel. If the primary channel is busy, for example, due to a STA (which supports only a 1 MHz operating mode) transmitting to the AP, all available frequency bands may be considered busy even though a majority of the available frequency bands remains idle.

[0060] In the United States, the available frequency bands, which may be used by 802.11 ah, are from 902 MHz to 928 MHz. In Korea, the available frequency bands are from 917.5 MHz to 923.5 MHz. In Japan, the available frequency bands are from 916.5 MHz to 927.5 MHz. The total bandwidth available for 802.11 ah is 6 MHz to 26 MHz depending on the country code.

[0061] FIG. 1 D is a system diagram illustrating the RAN 104 and the CN 106 according to an embodiment. As noted above, the RAN 104 may employ an NR radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 104 may also be in communication with the CN 106.

[0062] The RAN 104 may include gNBs 180a, 180b, 180c, though it will be appreciated that the RAN 104 may include any number of gNBs while remaining consistent with an embodiment. The gNBs 180a, 180b, 180c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, 102c over the air interface 116. In one embodiment, the gNBs 180a, 180b, 180c may implement MIMO technology. For example, gNBs 180a, 108b may utilize beamforming to transmit signals to and / or receive signals from the gNBs 180a, 180b, 180c. Thus, the gNB 180a, for example, may use multiple antennas to transmit wireless signals to, and / or receive wireless signals from, the WTRU 102a. In an embodiment, the gNBs 180a, 180b, 180c may implement carrier aggregation technology. For example, the gNB 180a may transmit multiple component carriers to the WTRU 102a (not shown). A subset of these component carriers may be on unlicensed spectrum while the remaining component carriers may be on licensed spectrum. In an embodiment, the gNBs 180a, 180b, 180c may implement Coordinated Multi-Point (CoMP) technology. For example, WTRU 102a may receive coordinated transmissions from gNB 180a and gNB 180b (and / or gNB 180c).

[0063] The WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using transmissions associated with a scalable numerology. For example, the OFDM symbol spacing and / or OFDM subcarrier spacing may vary for different transmissions, different cells, and / or different portions of the wireless transmission spectrum. The WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using subframe or transmission time intervals (TTIs) of various or scalable lengths (e.g., containing a varying number of OFDM symbols and / or lasting varying lengths of absolute time).

[0064] The gNBs 180a, 180b, 180c may be configured to communicate with the WTRUs 102a, 102b, 102c in a standalone configuration and / or a non-standalone configuration. In the standalone configuration, WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c without also accessing other RANs (e.g., such as eNode-Bs 160a, 160b, 160c). In the standalone configuration, WTRUs 102a, 102b, 102c may utilize one or more of gNBs 180a, 180b, 180c as a mobility anchor point. In the standalone configuration, WTRUs 102a, 102b, 102c may communicate with gNBs 180a, 180b, 180c using signals in an unlicensed band. In a non-standalone configuration WTRUs 102a, 102b, 102c may communicate with / connect to gNBs 180a, 180b, 180c while also communicating with / connecting to another RAN such as eNode-Bs 160a, 160b, 160c. For example, WTRUs 102a, 102b, 102c may implement DC principles to communicate with one or more gNBs 180a, 180b, 180c and one or more eNode-Bs 160a, 160b, 160c substantially simultaneously. In the non- standalone configuration, eNode-Bs 160a, 160b, 160c may serve as a mobility anchor for WTRUs 102a, 102b,102c and gNBs 180a, 180b, 180c may provide additional coverage and / or throughput for servicing WTRUs 102a, 102b, 102c.

[0065] Each of the gNBs 180a, 180b, 180c may be associated with a particular cell (not shown) and may be configured to handle radio resource management decisions, handover decisions, scheduling of users in the UL and / or DL, support of network slicing, DC, interworking between NR and E-UTRA, routing of user plane data towards User Plane Function (UPF) 184a, 184b, routing of control plane information towards Access and Mobility Management Function (AMF) 182a, 182b and the like. As shown in FIG. 1D, the gNBs 180a, 180b, 180c may communicate with one another over an Xn interface.

[0066] The CN 106 shown in FIG. 1 D may include at least one AMF 182a, 182b, at least one UPF 184a, 184b, at least one Session Management Function (SMF) 183a, 183b, and possibly a Data Network (DN) 185a, 185b. While the foregoing elements are depicted as part of the CN 106, it will be appreciated that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0067] The AMF 182a, 182b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 104 via an N2 interface and may serve as a control node. For example, the AMF 182a, 182b may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, support for network slicing (e.g., handling of different protocol data unit (PDU) sessions with different requirements), selecting a particular SMF 183a, 183b, management of the registration area, termination of non-access stratum (NAS) signaling, mobility management, and the like. Network slicing may be used by the AMF 182a, 182b in order to customize CN support for WTRUs 102a, 102b, 102c based on the types of services being utilized WTRUs 102a, 102b, 102c. For example, different network slices may be established for different use cases such as services relying on ultra-reliable low latency (URLLC) access, services relying on enhanced massive mobile broadband (eMBB) access, services for MTC access, and the like The AMF 182a, 182b may provide a control plane function for switching between the RAN 104 and other RANs (not shown) that employ other radio technologies, such as LTE, LTE-A, LTE-A Pro, and / or non-3GPP access technologies such as WiFi.

[0068] The SMF 183a, 183b may be connected to an AMF 182a, 182b in the CN 106 via an N11 interface. The SMF 183a, 183b may also be connected to a UPF 184a, 184b in the CN 106 via an N4 interface. The SMF 183a, 183b may select and control the UPF 184a, 184b and configure the routing of traffic through the UPF 184a, 184b. The SMF 183a, 183b may perform other functions, such as managing and allocating UE IP address, managing PDU sessions, controlling policy enforcement and QoS, providing DL data notifications, and the like. A PDU session type may be IP-based, non-IP based, Ethernet-based, and the like.

[0069] The UPF 184a, 184b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 104 via an N3 interface, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices. The UPF 184, 184b may perform other functions, such as routing and forwarding packets, enforcing user plane policies, supporting multi-homed PDU sessions, handling user plane QoS, buffering DL packets, providing mobility anchoring, and the like.

[0070] The CN 106 may facilitate communications with other networks For example, the CN 106 may include, or may communicate with, an IP gateway (e.g., an IP multimedia subsystem (IMS) server) that serves as an interface between the CN 106 and the PSTN 108. In addition, the CN 106 may provide the WTRUs 102a, 102b, 102c with access to the other networks 112, which may include other wired and / or wireless networks that are owned and / or operated by other service providers In one embodiment, the WTRUs 102a, 102b, 102c may be connected to a local DN 185a, 185b through the UPF 184a, 184b via the N3 interface to the UPF 184a, 184b and an N6 interface between the UPF 184a, 184b and the DN 185a, 185b.

[0071] In view of FIGs. 1A-1 D, and the corresponding description of FIGs. 1A-1 D, one or more, or all, of the functions described herein with regard to one or more of: WTRU 102a-d, Base Station 114a-b, eNode-B 160a-c, MME 162, SGW 164, PGW 166, gNB 180a-c, AMF 182a-b, UPF 184a-b, SMF 183a-b, DN 185a-b, and / or any other device(s) described herein, may be performed by one or more emulation devices (not shown). The emulation devices may be one or more devices configured to emulate one or more, or all, of the functions described herein. For example, the emulation devices may be used to test other devices and / or to simulate network and / or WTRU functions.

[0072] The emulation devices may be designed to implement one or more tests of other devices in a lab environment and / or in an operator network environment. For example, the one or more emulation devices may perform the one or more, or all, functions while being fully or partially implemented and / or deployed as part of a wired and / or wireless communication network in order to test other devices within the communication network. The one or more emulation devices may perform the one or more, or all, functions while being temporarily implemented / deployed as part of a wired and / or wireless communication network The emulation device may be directly coupled to another device for purposes of testing and / or performing testing using over-the-air wireless communications.

[0073] The one or more emulation devices may perform the one or more, including all, functions while not being implemented / deployed as part of a wired and / or wireless communication network. For example, the emulation devices may be utilized in a testing scenario in a testing laboratory and / or a non-deployed (e.g., testing) wired and / or wireless communication network in order to implement testing of one or more components. The one or more emulation devices may be test equipment. Direct RF coupling and / or wireless communications via RF circuitry (e.g., which may include one or more antennas) may be used by the emulation devices to transmit and / or receive data.

[0074] Edge computing for wireless cellular networks is a feature described in 3GPP specifications; it was introduced in Rel-17 and subsequently enhanced in Rel-18 and Rel-19. The edge computing feature enables a WTRU to discover low latency services that are offered in proximity of a WTRU; the feature also defines service continuity capabilities that maintain low latency services connectivity as WTRU mobility happens.

[0075] Two distinct edge computing frameworks have been specified by 3GPP.

[0076] An edge computing framework is available within the 5G core network and is described in 3GPP TS 23.548 - 5G System Enhancements for Edge Computing (Release 18). This framework is mostly networkbased and offers a basic set of edge computing capabilities designed to have minimal impacts on WTRU implementation. On the WTRU, an optional Edge Discovery Client (EDC) is defined as a support function to help with DNS discovery of edge servers. On the network side, the Edge Application Server Discovery Function (EASDF) may act as a DNS server to help resolve DNS requests for discovery of Edge Application Servers (EAS). The framework main functions include EAS discovery and EAS relocation.

[0077] A different edge computing framework is available as an application Edge Enablement Layer (EEL) above the 5G core network and below the application layer. This framework is described in 3GPP TS 23.558 - Architecture for enabling Edge Applications (Release 18) and follows the Service Enablement Architecture Layer (SEAL) principles and offers a richer set of edge computing capabilities. On the WTRU, an Edge Enabler Client (EEC) acts as an agent that interacts with edge functional entities located in the network to provide Application Clients (ACs) with edge functionality. On the network side, the Edge Configuration Server (ECS) and Edge Enabler Server (EES) functional entities provide the EEC with the necessary functionality to discover and use edge services offered throughout the network. The framework main functions include service provisioning, EAS discovery, service continuity and planning, dynamic EAS instantiation, support for various group use cases (e.g., group of WTRU instances using an EAS, bundles of EAS providing a service, etc.).

[0078] Both frameworks may co-exist and have different functional entities and capabilities. Comparatively, the EAS discovery offered in each framework differs; for example, in the 5G core network, EAS discovery is based on DNS protocols and use the EASDF, while in the edge enablement layer, EAS discovery is realized using a dedicated HTTP procedure between the EEC (WTRU) and an EES.

[0079] The delivery of end-to-end services often require using diverse services; the steering of traffic through these services is termed Service Function Chaining (SFC). In 3GPP wireless networks, SFC is a capability offered by the 5G core network that allows an Application Function (AF) to use the Network Exposure Function (NEF) Traffic Influence API to indicate an SFC Policy identifier in order to activate traffic classifiers in the data path. It is to be noted that the SFC functionality defined in 3GPP is limited to traffic classification and excludes the service function forwarding functionality related to SFC.

[0080] SFC policies are (pre-)provisioned in the Policy Control Function (PCF) and indicate a set of Traffic Steering Policies (TSP); on SFC policy activation, the PCF requests the Session Management Function (SMF) to configure the UPF with traffic steering rules according to the defined TSP(s). The AF are pre-configured with available SFC policy identifiers.

[0081] SFC in the wireless network requires a business agreement between the operator and the Application Service Provider (ASP) such that SFC policies are provisioned in the PCF. An operator needs to provision SFC policies in the PCF, and the ASP needs to configure the SFC policy identifiers in the AF, according to the operator provisioned SFC policies.

[0082] Operation splitting between AIML endpoints has been identified as promising technology that should be supported in wireless systems. Split AIML inference is a technique for decentralizing the process of performing AIML inference using a trained model. AIML Split Inference (AIML-SI) consist in using different AIMLmodels, usually executed on different hardware, to derive inference result(s) and / or prediction(s) For example, in a wireless environment, the benefits may be to keep privacy sensitive data in the WTRU while offloading compute intensive data to the network.

[0083] FIG. 2 illustrates an example of a sequential AIML-SI where models are chained to form a three stage AIML-SI model. The first stage, 202, may be located on a WTRU 204 as an Application Client or service of WTRU 204, and Model A 206 may represent the chain head. Model A 206 may produce stage 1 intermediate results 210 (e.g., stage 1 intermediate dataset) based on analytics 208 available at WTRU 204. The stage 1 intermediate dataset 210 may be delivered to a second stage of inference 212. Stage 2, 212, inference may be offered by an AF as a service, and stage 2 may use Model B 214 to perform inference based on stage 1 intermediate dataset 210 and analytics 216 available in the network. Stage 2 inference 212 may produce a stage 2 intermediate dataset 218 that may be delivered to a third stage 220 of inference. Stage 3, 220, inference may be offered by an AF as a service, stage 3 inference 220 may represent the tail of the AIML-SI, stage 3 may use Model C 222 to perform inference based on stage 2 intermediate dataset 218, and stage 3 inference may derive a result 224. The result of the AIML-SI may be consumed by WTRU 204 or AF 226 to perform an action according to the AIML-SI result.

[0084] As illustrated in FIG. 3, The first stage, 302, may be located on a WTRU 304 as an Application Client or service of WTRU 304, and Model A 306 may represent the chain head. Model A 306 may produce stage 1 intermediate results 310a, 310b, and 310c (e.g., stage 1 intermediate datasets) based on analytics 308 available at WTRU 304. The stage 1 intermediate dataset 310a may be delivered to a first stage 2 inference 312a, a second stage 2 inference 312b, and a third stage 2 inference 312c. The first stage 2 inference 312a may use Model B 314a to perform inference based on stage 1 intermediate dataset 310a and analytics 316a available in the network. First stage 2 inference 312a may produce result 318a.

[0085] The stage 1 intermediate dataset 310b may be delivered to a second stage 2 inference 312b. Second stage 2 inference 312b may use Model B 314b to perform inference based on stage 1 intermediate dataset 310b and analytics 316b available in the network. Second stage 2 inference 312b may produce result 318b. The stage 1 intermediate dataset 310c may be delivered to a third stage 2 inference 312c Third stage 2 inference 312c may use Model B 314c to perform inference based on stage 1 intermediate dataset 310c and analytics 316c available in the network. Third stage 2 inference 312c may produce result 318c. Model 314c may represent the chain tail. Each data set 310a, 310b, and 310c may be different. The result of the AIML-SI, 320a and / or 320b, may be consumed by WTRU 304 or AF 322 to perform an action according to the AIML-SI result.

[0086] FIG. 4 illustrates an example of model-parallel AIML-SI for combined prediction In the example of FIG. 4, different AIML models are used in parallel instances of application functions. The model-parallel AIML- SI illustrated in FIG. 4 may consume intermediate results from different domains, for example from the WTRU, the RAN, and the CN, to produce a combined inference result or prediction.

[0087] As illustrated in FIG. 4, The first stage of inference, 402, may be located on a WTRU 404 as an Application Client or service of WTRU 404, and Model A 406 may represent the chain head. Model A 406 may produce stage 1 intermediate results 410 (e.g., stage 1 intermediate datasets) based on analytics 408 available at WTRU 404. The stage 1 intermediate dataset 410 may be delivered to a fourth stage of inference 428. A second stage of inference 412 includes Model B 414 that may produce stage 2 intermediate results 418 based on analytics 416 available at second stage 412. Second stage 412 may deliver stage 2 intermediate results 418 to fourth stage 428.

[0088] A third stage of inference 420 includes Model C 422 that may produce stage 3 intermediate results 426 based on analytics 424 available at third stage 420. Third stage 420 may deliver stage 3 intermediate results 426 to fourth stage 428. Fourth stage of inference 428 includes Model D 430 that may produce stage 4 results 434 based on intermediate results 410, 418, and 426 Model 430 may represent the chain tail. Stage 4 results 434a and / or 434b may be provided to WTRU 404 or AF 436

[0089] FIG. 5 illustrates and example of a model-parallel AIML-SI example for distributed prediction.

[0090] In the examples of FIG. 4 and FIG. 5, different AIML models are used in parallel instances of application functions. The model-parallel AIML-SI illustrated in FIG. 5 may consume intermediate results from a single domain, for example from the WTRU, to produce distributed inference results or predictions. The result(s) of the AIML-SI may be consumed by a WTRU or an AF to perform an action according to the AIML-SI result.

[0091] As illustrated in FIG. 5, the first stage, 502, may be located on a WTRU 504 as an Application Client or service of WTRU 504, and Model A 506 may represent the chain head. Model A 506 may produce stage 1 intermediate results 510a, 510b, and 510c (e.g., stage 1 intermediate datasets) based on analytics 508 available at WTRU 504. The stage 1 intermediate dataset 310a may be delivered to a second stage of inference 512, a third stage of inference 514, and a fourth stage of inference 516. The stage 2 inference 512 may use Model B 518 to perform inference based on stage 1 intermediate dataset 510a and analytics 520 available in stage 2 512. Stage 2 inference 512 may produce result 522.

[0092] The stage 1 intermediate dataset 310b may be delivered to third stage of inference 514. Third stage of inference 514 may use Model C 542 to perform inference based on stage 1 intermediate dataset 510b and analytics 526 available in stage 3. Stage 3 inference 514 may produce result 528. The stage 1 intermediate dataset 310c may be delivered to fourth stage of inference 516. Fourth stage inference 516 may use Model D 530 to perform inference based on stage 1 intermediate dataset 310c and analytics 532 available in stage 4. Stage 4 inference 516 may produce result 534. Model D 530 may represent the chain tail. Each data set 510a, 510b, and 510c may be different. The result of the AIML-SI 536a and / or 536b may be consumed by WTRU 504 or AF 538 to perform an action according to the AIML-SI result.

[0093] It should be appreciated that in the above examples of AIML-SI, the consumer(s) of the AIML-SI results may be the tails of the AIML-SI chain and may be a single entity such as a WTRU or an AF or may be multiple consumers.

[0094] The 5G Core Network (5GC) EEL framework provides capabilities for discovering groups of EAS, referred to as EAS bundles. The EEL supports two types of EAS bundle: the direct EAS bundle and the composite EAS bundle.

[0095] The direct EAS bundle is represented by a group of EAS instances (e.g., AFs) accessed directly by a WTRU and managed as a group; examples of a topology similar to a direct bundle are the ones shown in FIG. 3 and FIG. 5.

[0096] In the examples of FIG. 4 and FIG. 5, different AIML models are used in parallel instances of application functions. The model-parallel AIML-SI presented on FIG. 4 may consume intermediate results from different domains, for example from the WTRU, the RAN, and the CN, to produce a combined inference result or prediction. The model-parallel AIML-SI presented on FIG. 5 may consume intermediate results from a single domain, for example from the WTRU, to produce distributed inference results or predictions. The result(s) of the AIML-SI may be consumed by a WTRU or an AF to perform an action according to the AIML-SI result.

[0097] Support for EAS bundles: The 5G Core Network (5GC) EEL framework provides capabilities for discovering groups of EAS, referred to as EAS bundles. The EEL supports two types of EAS bundle: the direct EAS bundle and the composite EAS bundle.

[0098] The direct EAS bundle is represented by a group of EAS instances (e.g., AFs) accessed directly by a WTRU and managed as a group; examples of a topology similar to a direct bundle are the ones shown in FIG. 3 and FIG. 5.

[0099] The composite EAS bundle is represented by a group of EAS instances where only one instance may be accessed by the WTRU; FIG. 2 shows an example of a topology similar to a composite bundle

[0100] EAS bundles may be topologically similar to split AI / ML models but have limitations preventing the realization of split AI / ML computing scenarios.

[0101] It can be appreciated that in all examples of AIML-SI, the consumer(s) of AIML-SI results may be the tail of the AIML-SI chain, may be a single entity such as a WTRU or an AF, or may be multiple consumers.

[0102] To benefit from usage of Al ML technology, wireless networks need to provide capabilities to support AIML applications that can be implemented using various AIML models. As AIML models complexify, it is necessary to support decentralized AIML models to minimize power consumption on the WTRU (e.g., by limiting inference processing and data transmission), and to preserve privacy of sensitive information. Support of applications that use split AIML models represent an opportunity for mobile networks operators to allow users to benefit from complex AIML models while retaining battery life and preserving privacy.

[0103] Supporting applications that use split AIML models in mobile networks presents several challenges. A first challenge is related to discovery and chaining of application functions to form AIML split inference pipelines. Specifically, existing Edge Application Server (EAS) discovery capabilities need to be enhanced to support the different split AIML models, SFC is a CN capability which may not be available (e.g., it is optional, it is not supported when roaming and needs pre-provisioned SFC policies by the operator).

[0104] A second challenge is related to determining and informing entities participating in the AIML split inference chain about the chain structure and configuration (e.g., head, tail, result consumer, next stage and related WTRU(s)). For example, the result consumer(s) (e.g , WTRU, AF, or both) need to be informed of the split AIML chain tail to subscribe for obtaining inference results, in another example, split AIML chain intermediate nodes or tail need to know the WTRU for which the result applies to. A third challenge is related to supporting AFs that are SFC encapsulation aware and unaware or a combination of both.

[0105] Accordingly, Service Function Chaining and Edge Computing enhancements are motivated by requirements of AIML applications. Usage of complex AIML models on a WTRU may not be possible due to the WTRU limited capabilities, such as WTRU reduced computing capabilities, constrained battery life and limited availability of network analytics. Split AIML inferencing is a technique that may be utilized to enable usage of complex AIML models on WTRUs with such capability limitations. A WTRU AIML inferencing is a use case that may leverage existing network capabilities such as Edge Computing (EC) and Service Function Chaining (SFC). EC may allow offloading compute-heavy inferencing while maintaining low communication latency; SFC may allow forming Service Chains dynamically which may be needed when AIML models needs to be updated. A Service Chain Management Function (SCMF) capability may be offered as a service. In one example, the SCMF may be implemented as a standalone service, e.g., as an Application Function (AF) or Network Function (NF) In another example, the SCMF may be implemented as an extension of an existing service. The SCMF framework may not be limited to AIML split inferencing; the framework may be applicable to other split computing use cases.

[0106] The Service Chain Management Function (SCMF) allows a WTRU or an Application Function (AF) to configure and manage Service Chain(s) within the mobile network The SCMF may offer a service to manage SC chains, the service may be offered to SC users via an Application Programming Interface (API) The SCMF functionality may be implemented as a standalone Application Function (AF) or as a Network Function (NF). The SCMF functionality may be combined with an existing AF or NF, and the API may be offered as an extension of an existing API.

[0107] The SCMF service may be offered using a communication protocol, for example the Hyper Text Transfer Protocol (HTTP) or the Non-Access Stratum (NAS) protocol for 5G systems may provide the capabilities for offering the SCMF service.

[0108] The SCMF may create SC profile resources and may offer capabilities to manage SC profile resources. There may be one SC profile for each SC managed by the SCMF. The SC profile resource may be created, discovered, enabled, disabled, modified, or deleted at the SCMF. The SCMF may enable concurrent management of multiple SC profiles (e.g., SC chains) and may offer the SCMF service to multiple concurrent SC owners and SC consumers.

[0109] FIG. 6 illustrates a high-level view of the service chain lifecycle. The Service Chain (SC) owner may be a WTRU or an AF, and the SC lifecycle may be composed of three phases. At 602, the SC owner may request the SCMF to create a SC, and the SCMF may create a SC profile based on information provided bythe SC owner. The SC profile may include information that uniquely identifies the SC and may include information describing the SC structure and operation.

[0110] At 604, the SC owner may request the SCMF to perform management operations on the Service Chain, and the SCMF may provide the SC owner or SC consumers with requested information or information related to event of the SC. Management operations may include creating, configuring, enabling, disabling, or modifying the SC Requested or notified information may include SC discovery information, SC results information, SC usage information or SC analytics information. At 606, the SC owner may request the SCMF to terminate the SC, and the SCMF may release resources associated with the SC.

[0111] A SC profile may describe how services are chained together and may reflect the operational status of the SC. The SC profile may be composed of multiple Information Elements (lEs) reflecting static and dynamic aspects of the SC. For example, static aspects may include SC nodes (e.g., head, tail, intermediate), the SC owner, and the SC consumers. For example, dynamic lEs may include current SC consumers or SC analytics, such as the average combined SC inference time or the average inference time of each SC stage.

[0112] The Service Chain Management Function (SCMF) provides capabilities for supporting user plane with or without Service Function Chaining (SFC) capabilities in the wireless network.

[0113] In one example, when SFC capabilities are used, the SCMF may receive a SC create request from a WTRU. The request may include the SC characteristics. The SC characteristics may indicate that 5GC SFC functionality is used and may indicate a SFC policy ID. The SCMF may create a SC profile and assign a SC profile identifier.

[0114] The SCMF may use the NEF Traffic Influence API. The API may indicate that the SFC policy ID needs to be activated. The API may indicate that the SC identifier is the metadata. The SCMF may receive a SFC traffic flow. The SFC traffic flow may be SFC encapsulated (e.g., by the UPF), based on the activated SFC policy. The SFC traffic flow may include a SC identifier in the SFC metadata.

[0115] The SCMF may determine a first service and determine that the first service does not need a SFC proxy. The first service may be determined based on the SC profile and the SC identifier from the SFC metadata. The need for a SFC proxy may be determined based on the capabilities of the first service (e.g., supporting SFC). The SCMF may send the SFC traffic flow to the determined first service. The SCMF may receive a modified SFC traffic flow from the first service. The modified SFC traffic flow including a SC identifier in the metadata.

[0116] The SCMF may determine a second service and determine that the second service needs a SFC proxy. The second service determined based on the SC profile and the SC identifier included in the SFC metadata of the first service. The need for a SFC proxy determined based on the capabilities of the second service (e.g., not supporting SFC)

[0117] The SCMF may send the traffic flow to the second service. The traffic may be without SFC encapsulation, and the SFC encapsulation may be removed by the SFC proxy of the SCMF. The SCMF mayreceive a modified traffic flow from the second service. The modified traffic flow may be SFC encapsulated by the SFC proxy of the SCMF. The modified SFC traffic flow may include a SC identifier in the SFC metadata. The SCMF may determine a third service and determine that the third service does not need a SFC proxy The third service determined based on the SC profile and the SC identifier included in the SFC metadata of the SCMF proxy. The need for a SFC proxy determined based on the capabilities of the third service (e.g., supporting SFC). The SCMF may receive a modified SFC traffic flow from the third service. The SFC traffic flow indicating a SC response. The SCMF may notify subscribers for SC response.

[0118] Service Function Chaining (SFC) may require SFC traffic encapsulation, which in turn may require that SC nodes of the SC be SFC encapsulation aware (e.g., encapsulation capable). Services that are SFC encapsulation unaware may require a separate SFC proxy to process SFC encapsulation.

[0119] In 3GPP systems, the support for SFC may be enabled via usage of traffic classifiers in the UPF. The traffic classifiers may be defined in SFC policies provisioned in the PCF, and the SFC policies may be activated by an AF. 3GPP SFC support may cover SFC traffic classification aspects. Service Function Forwarding (SFF) aspects need to be defined.

[0120] The SCMF may have Service Function Forwarding (SFF) capabilities and SFC proxy capabilities. These capabilities may be needed when 5GC SFC capabilities are available in the mobile network.

[0121] The need for using the SFF capabilities of an SCMF may be determined based on a requirement of the application (e.g., the AC or AFs implementation may require use of SFF) and based on a requirement of the network deployment (e.g., the network deployment may require use of SFF).

[0122] The need for using the SFC proxy capabilities of an SCMF may be determined based on a requirement of the AF implementation; when an AF does not supportSFC encapsulation and the SFF capability is used, the SCMF may insert a SFC proxy such that SFC decapsulation is performed prior to sending traffic to the AF, and such that SFC encapsulation is performed on the traffic received from the AF.

[0123] FIG. 7 illustrates an example of a system flow using the SCMF with SFC traffic forwarding and proxying. In this example, an SFC traffic flow refers to traffic which is SFC encapsulated; the uplink and downlink traffic classifiers in the UPF may perform the SFC encapsulation and decapsulation of the traffic received from the AC, respectively.

[0124] At 706, an AC 704 located on a WTRU 702 may send a SC create request to the SCMF 708. WTRU 702 may indicate to SCMF 708 that the 5GC SFC capability is used and provide a SFC policy identifier in the request sent to the SCMF 708; alternatively, SCMF 708 may determine the SFC policy identifier based on SCMF configuration. The SCMF may send a SC create response to the WTRU including the created SC profile or the SCID of the SC profile.

[0125] The SC profile may contain a Service Chain 5GC SFC Policy Information, which may include a SFC policy identifier that indicates the provisioned policy that may be used, traffic descriptors to which the policyapplies, the identifiers of WTRUs to which the policy applies, spatial validity conditions, and may contain information about AF supporting SFC.

[0126] Although not shown in FIG. 7, the WTRU may subscribe with the SCMF to receive SC results if the WTRU needs the results of the SC processing. Alternatively, the WTRU may use information provided in the SC profile to identify tail of the SC, and may subscribe with the tail AF (e.g., AF3 (738) in FIG. 7) to receive SC results when needed.

[0127] At 710, based on the SCF policy ID, SCMF 708 may invoke the Nnef_Trafficlnfluence API of the NEF 712 to activate the corresponding SFC policy. SCMF 708 may provide to NEF 710 information needed to identify to which traffic the SFC policy applies; the information may include a SFC policy identifier (e.g., received from the WTRU 702 or determined by SCMF 708), a SCID of the SC profile as the SFC metadata, a traffic descriptor, identifier(s) of the WTRU, and spatial validity condition(s).

[0128] At 714, NEF 712 may send to the PCF 716 the information received from SCMF 708, and PCF 716 may retrieve the indicated SFC policies 740 to obtain the associated Traffic Steering Policies (TSP).

[0129] At 718, PCF 716 may provide SMF 720 with Policy and Charging Control (PCC) rules that are based on the retrieved TSP policy(s), SFC metadata, traffic description, WTRU identifiers and spatial validity conditions. At 722, SMF 720 may instruct UPF 724 to enable traffic classifier(s); the traffic classifiers may be based on Packet Detection Rule(s) (PDR), Forwarding Action Rule(s) (FAR), and other traffic classification rules that may be supported by the UPF, or a combination thereof.

[0130] It is noted that at 710 to 722, the SFC policy mechanism may be used to determine and apply traffic classifiers to the user data plane; it can be appreciated that traffic classifiers may be configured in the UPF using other means (e.g., pre-configuration, traffic influence, etc ) to achieve the same result.

[0131] At 726, WTRU 702 may send a traffic flow to a SC to be processed For example, an AIML model from an AIML application on the WTRU may produce an intermediate AIML dataset and send it to the network for obtaining split AIML inferencing results. The UPF traffic classifiers associated with the SFC policy may identify the traffic flow originating from the WTRU based on the traffic descriptors, WTRU identifiers and spatial validity conditions used to configure the traffic classifiers at 722. Additionally, the classifiers may perform SFC encapsulation on the identified traffic flow, the SFC encapsulation including the SFC metadata (e.g., the SCID). The UPF traffic classifiers may send the identified traffic flow to the SCMF based on the SFC policy. Upon receiving the SFC traffic flow, the SCMF may identify that the received flow is SFC encapsulated, the detection may be based on the SCMF endpoint where the traffic is received, or by detecting the SFC metadata. The SCMF may use the SCID included in the SFC metadata to identify the SC profile associated with the received SFC traffic.

[0132] At 728, SCMF 708 may determine that the SFC traffic received from WTRU 702 may be sent to a first AF 730; the determination may be based on the identified SC profile, and the first AF may be identified based on the SC nodes of the SC profile. SCMF 708 may determine that the first AF is SFC aware based on the SC Profile, and SCMF 708 may send the SFC encapsulated traffic to the first AF 730. The first AF 730 mayremove the SFC encapsulation from the SFC traffic, may use the SFC metadata to identify the corresponding SC profile, may perform its function on the received dataset, may return to SCMF 708 a modified dataset after performing the SFC encapsulation. For example, the first AF 730 may be an AIML AF participating in split AIML inference; the received data may be an intermediate AIML dataset; the first AF 730 may perform an inference on the received dataset and return inference results. Upon receiving the modified dataset from the first AF 730, the SCMF may use the SCID from the metadata to identify a SC profile, and the SCMF may use the SC profile to identify a second AF 734 in the SC.

[0133] At 732, SCMF 708 may determine that the SFC traffic received from the first AF 730 may be sent to second AF 734; the determination may be based on the identified SC profile, and second AF 734 may be identified based on the SC nodes of the SC profile. SCMF 708 may determine that second AF 734 is SFC unaware based on the SC profile, and SCMF 708 may perform the SFC proxy function to remove SFC encapsulation on traffic to be sent to the second AF. The second AF may perform its function on the received dataset and may return to the SCMF a modified dataset. The SCMF may perform the SFC proxy function to perform SFC proxy encapsulation on the modified dataset received from second AF 734. For example, second AF 734 may be an AIML AF participating in split AIML inference; the received data may be an intermediate AIML dataset; second AF 734 may perform an inference on the received dataset and return inference results. Upon receiving the modified dataset from second AF 734, SCMF 708 may use the SCID from the metadata (e g., added by the SFC proxy) to identify a SC profile, and SCMF 708 may use the SC profile to identify a third AF 738 in the SC.

[0134] Although not shown in FIG. 7, it can be appreciated that in some implementation the SFC proxy functionality may not be part of the SCMF, that in such implementation the SCMF may use a standalone SFC proxy AF, that the SFC proxy AF may be inserted by the SCMF between the SCMF and the AF that is SFC unaware (e.g., the second AF 734), that the determination to insert a SFC proxy AF may be determined by the SCMF based on AF capabilities provided to the SCMF in the SC profile.

[0135] At 736, SCMF 708 may determine that the SFC traffic received from second AF 734 may be sent to third AF 738; the determination may be based on the identified SC profile, and third AF 738 may be identified based on the SC nodes of the SC profile. SCMF 708 may determine that third AF 738 is SFC aware based on the SC Profile, and SCMF 708 may send the SFC encapsulated traffic to third AF 738. The third AF 738 may remove the SFC encapsulation from the SFC traffic, may use the SFC metadata to identify the corresponding SC profile, may perform its function on the received dataset, may return to SCMF 708 a modified dataset after performing the SFC encapsulation. For example, third AF 738 may be an AIML AF participating in split AIML inference; the received data may be an intermediate AIML dataset; first AF 730 may perform an inference on the received dataset and return inference results. Upon receiving the modified dataset from third AF 738, SCMF 708 may use the SCID from the metadata to identify a SC profile, and SCMF 708 may use the SC profile (e.g., SC nodes) to determine that the SC processing is completed.

[0136] While not shown in FIG. 7, based on identifying that SC processing is completed, SCMF 708 may identify subscribers for SC results and may notify the subscribers with the SC results.

[0137] As described at 726, the SCMF may invoke an NEF API to configure how the 5GC processes traffic from the WTRU which may be triggered by receiving a SC create request from the WTRU. The SCMF may also be triggered or influenced based on metadata that is received from one of the services in the chain (i.e., an AF)

[0138] For example, an AF may update the metadata to indicate that there is a considerable number of TCP retransmissions in the data flow. This information may trigger the SCMF to invoke an NEF that changes the QoS that is associated with the WTRU’s traffic flow such that failed transmissions will be decreased. Thus, the likelihood of TCP retransmissions being needed is lowered.

[0139] In another example, a SC chain may be composed of a series of increasingly complex models such that simpler models produce faster and imprecise inferencing while complex models may produce slower and precise inferencing. Such a SC chain may be used to provide adaptive dynamic inferencing, i e., it may obtain valid inference results without deferring to the complex models. Adaptive dynamic inferencing may be realized when an intermediate SC node (e.g , less complex SC node) indicates to the SCMF in the metadata that a result has been obtained with a high confidence level and that further processing is not needed. The SCMF may use such indication to notify the SC consumer(s) with the intermediate result and stop processing the data down the SC chain. This behavior allows to optimize resource usage while remaining precise when complex data samples need to be processed. Adaptive dynamic inferencing may be useful for rapidly changing environments such as autonomous vehicle applications.

[0140] In some scenarios, the network deployment may not provide 5GC SFC capabilities or 5GC SFC capability may not be supported or used by the AC, SCMF or AF. In an example, the 5GC Edge Enablement Layer (EEL) may provide capabilities for the WTRU to discover and use EAS bundles; the EEL may support a direct bundle type and a composite bundle type.

[0141] The direct bundle type may be represented by a group of EAS instances (e.g., AF instances) accessed directly by a WTRU and managed as a group as shown on FIG. 3 and FIG. 5, and may represent a topology similar to a data-parallel SC or a model-parallel SC. The composite EAS bundle type may be shown in FIG. 8 and may be represent a topology similar to a sequential SC. Both bundle types supported by the EEL present issues preventing from being used as sequential, data-parallel or model parallel SC EAS bundles may require the use of SCMF to enable the SC functionality. For example, the direct bundle type may not allow to discover multiple AFs of the same type preventing the use of EAS bundles for data-parallel SCs For example, the composite bundle type may not provide the capability to collect results from the SC tail. For example, all bundle types may not provide KPI analytics or allow to form adaptive dynamic inferencing SCs.

[0142] FIG. 8 illustrates an example of a system flows when 5GC SFC capabilities are not used.

[0143] At 802, the WTRU 802 hosting an application, AC 804, or service may send a SC create request toSCMF 812. WTRU 804 may indicate to SCMF 812 that the 5GC SFC capability is not used. SCMF 812 maysend a SC create response to WTRU 804 including the created SC profile or the SCID of the SC profile. In an example, SCMF 812 may be included in a data network (DN) / edge data network (EDN) 810.

[0144] Although not shown in FIG. 8, the SC participants (e.g., AF1 (818), AF2 (822), and AF3 (826)) may subscribe with SCMF 812; SCMF 812 may notify the SC participants of the SC creation and may provide the SC profile to the SC participants.

[0145] Also not shown in FIG. 8, WTRU 804 may subscribe with SCMF 812 to receive SC results if WTRU 804 needs the results of SC processing. Alternatively, WTRU 804 may use information provided in the SC profile to identify tail of the SC, and may subscribe with the tail AF (e.g , AF3 (826)) to receive SC results when needed.

[0146] At 816, WTRU may send a traffic flow to a SC to be processed by the SC; WTRU 804 may determine a first AF 818, which is the head of the SC, based on the node information included in the SC profile received at SC creation. Additionally, the traffic flow may include the SCID associated with the SC profile For example, an AIML model from an AIML application (804) on WTRU 802 may produce an intermediate AIML dataset and send it to the network for obtaining split AIML inferencing results.

[0147] Upon receiving the traffic flow, first AF 818 may determine a SC profile corresponding to the traffic flow; the determination may be based on the SCID included in the traffic flow, may be based on detection of traffic using information (e.g., WTRU descriptor, traffic descriptor) included in the SC profile, or may be determined by requesting SCMF 812 for a SC profile based on the received traffic (e.g., the first AF provides traffic to the SCMF and the SCMF responds with a SC profile).

[0148] First AF 818 may perform processing on the received dataset, may produce a modified dataset, and may determine a next node to send the traffic to at 820. The determination of the next node may be based on information (e g., SC node, SC node role, SC node position) included in the determined SC profile, and first AF 818 may send the modified dataset to the determined next node.

[0149] The AF (e.g SC node) may send information about the SC session or the SC node to the SCMF where it is subscribed (e.g., where it obtained the SC profile from); the information may include SC session KPIs (ex. number of packet treated, average inference time, etc.), SC node KPIs (ex. number of SC sessions, processing load, etc.), and communication metrics (ex. TCP timeout, dropped packets, etc.). The SCMF may provide these metrics to SC consumers or use these metrics.

[0150] For example, an AF indicate that there is a considerable number of TCP retransmissions in the data flow. This information may trigger the SCMF to invoke a NEF to change the QoS that is associated with the WTRU’s traffic flow such that failed transmissions will be decreased. Thus, the likelihood of TCP retransmissions being needed is lowered.

[0151] In a second example, adaptive dynamic inferencing may be realized when an intermediate SC node (e g., less complex SC node) indicates to the SCMF that a result has been obtained with a high confidencelevel and that further processing is not needed (e.g., the AF does not provide data to the next node) The SCMF may use such indication to notify the SC consumer(s) with the intermediate result.

[0152] AF 822 upon receiving the dataset produced by the AF 818 may perform processing on the received dataset, may produce a modified dataset, and may determine a next node to send the traffic at 824. AF 826 upon receiving the dataset produced by the AF 822 may perform processing on the received dataset. AF 826 may be a tail AF and may notify SCMF 812 about the SC result upon identifying that the SC processing is completed. While not shown in FIG. 8, SCMF 812 may identify subscribers, for example WTRU 802, for SC results and notify the subscriber of the results.

[0153] Each AF in the SC, upon receiving the dataset produced by the previous AF, may perform inference, may produce a modified dataset, may identify a next AF, may provide subscribers with subscription information and may send the modified dataset to the next AF or to the SCMF in a similar manner. Additionally, the SC tail AF may notify the SCMF about the SC result based on identifying that the SC processing is completed Not shown on the figure, the SCMF may identify subscribers for SC results and may notify the subscribers with the SC (e.g., SC report).

[0154] Service Chain creation may be performed via the provisioning of connection capabilities, i.e., the 5G core network may support the WTRU requesting creation of a SC by providing connection capabilities. For example, the WTRU may provide connection capabilities information when requesting a PDU session establishment or modifying an existing PDU session.

[0155] In one example, the WTRU may provide connection capability information in a NAS message; connection capability information may be any of a connection capability value, connection capability modifiers.

[0156] A connection capability value may indicate that a specific SFC policy configuration is requested. For example, the WTRU may provide a connection capability value (e.g., connection capability ‘X’) that may correspond to a specific SFC policy available to the PCF, and resulting in a SFC policy being applied.

[0157] Connection capability modifiers may indicate that SC capabilities is requested according to a configuration indicated by the modifiers The connection capability modifiers may be associated with a connection capability value such that a connection capability value may indicate that SC capability is requested according to the connection capability modifiers.

[0158] The connection capability modifiers may include the Service Chain Type (SCT) that may uniquely identify a type of service chain. The connection capability modifiers may include the Service Chain Identifier (SCID) that may uniquely identify a service chain instance.

[0159] The connection capability modifiers may include the SFC Policy Identifier that may uniquely identify a SFC policy provisioned in the PCF. The WTRU may include a SFC Policy Identifier in the connection capabilities to indicate to the AMF that it wants to use such policy The AMF may communicate the SFC policy identifier to the SFM such that the SMF may obtain PCC rules associated with the SFC policy identifier from the PCF.

[0160] The connection capability modifiers may include the SFC Metadata, which is information that may be added to SFC encapsulated traffic. The WTRU may include a SFC Metadata in connection capabilities to indicate to the AM F that it wants the metadata information to be added to the traffic indicated by the SFC Policy Identifier. The AMF may communicate the SFC metadata to the SFM to configure the SFC traffic encapsulation accordingly

[0161] The connection capability modifiers may include the Service Chain Traffic Descriptor which may describe the traffic characteristics to be included in the SC. The WTRU may include SC traffic descriptor(s) in connection capabilities to indicate to the AMF that it wants a subset (e.g., not all) traffic of the PDU session to be sent through the SC. The AMF may communicate the SC traffic descriptor(s) to the SMF to configure the traffic classifiers accordingly.

[0162] Connection capability information may include any of a connection capability value and its associated connection capability modifiers.

[0163] FIG. 9 illustrates an example of a Service Chain creation via connection capabilities information.

[0164] At 922, an AC 904 located on a WTRU 902 may request the establishment of a PDU session via RAN 920; the request may indicate that the AC 904 needs to use SC capabilities of the network. The AC request may trigger WTRU 902 (e.g., the Terminal Equipment (TE) and Mobile Termination (MT) components of the WTRU) to send a PDU session establishment request to AMF 906 associated with WTRU 902. The PDU session establishment request message may include connection capabilities information indicating that the created PDU session requires SC capabilities from the network.

[0165] At 924, the AMF 906 may perform SMF selection, and may send to the selected SMF 908 a PDU Session Create request including the connection capabilities information provided by the WTRU 902.

[0166] At 926, upon receiving the PDU session create request from the AMF 906, the SMF 908 may send a message to the PCF 910 indicating that SC support is needed from the network for a given WTRU; the message may contain the connection capability information received from the WTRU at 922. Based on the message from the SMF 908 and the connection capability information, PCF 910 may identify a SFC policy 912. The PCF may also identify subscribed AFs (e.g., such as the SCMF), and may notify the AFs of PDU session creation requiring SC support. For example, the message sent from SMF 908 to PCF 910 may be a new message or an existing message such as SM policy association establishment.

[0167] At 928, the PCF 910 may determine that at least one AF 916 needs to be notified of requested SC support. The PCF 910 may invoke the NEF API and provide the connection capability information received from the SMF 908 at 926. The NEF 914 may notify the subscribed AF instances (916) providing the connection capabilities information at 930. For example, an application function (e.g., such as the SCMF) may use this information to create a SC.

[0168] It can be appreciated that a trusted network function implementing the SCMF functionality may be registered to the PCF 910 and that the NEF intermediate node may not be needed.-7J -

[0169] At 932, if the PCF 908 may have determined a SFC policy at 926, the PCF 910 may provide the SMF 908 with Policy and Charging Control (PCC) rules. The SMF 908 may configure UPF 918 according to the received PCC rules.

[0170] At 934, the SMF 908 may notify the AMF 906 about the SC policy chain establishment based on information received from the PCF 910 or from the NEF 914. The notification may include information indicating the successful creation of the SC and may include information needed by WTRU 902 to use the SC For example, the information may indicate that the SC was created successfully and may include a SCMF identifier or connectivity information to the SCMF (e.g., IP address, endpoint, etc.) For example, the message sentfrom the SMF to the AMF may be a new message or an existing message such as Communication N1 N2 message transfer.

[0171] At 936, AMF 906 may send a PDU session establishment accept message to WTRU 902 via RAN 920; the message may indicate to WTRU 902 that the PDU session can be used to send traffic If WTRU 902 indicated SC support at 922, the message may also indicate that the SC is available to receive traffic and may include SC information as described at 934.

[0172] At 938, AC 904 present on the WTRU 902 may be notified that the connection is available and may send a traffic flow to the network, using the PDU session established with SC capabilities. Based on the configured service chain information received from AMF 906, AC 904 may be informed of an application function (e.g., such as the SCMF), and may request information from AF 916, for example, AC 904 may request SCMF 916 to provide the SC profile, discover the SC tail and obtain inference results.

[0173] FIG. 10 is a flowchart of an example process 1000 of a SCMF with SFC traffic forwarding and proxying.

[0174] As shown in FIG. 10, process 1000 may include, at 1002, receiving, from a wireless transmit / receive unit (WTRU), a request to create a service chain (SC) in a split artificial intelligence machine learning (AIML) process. For example, a wireless network function may receive, from a WTRU, a request to create a SC in a split Al ML process, as described above. As also shown in FIG. 10, process 1000 may include, at 1004, sending, to a network device, a service function chaining (SFC) policy identifier to activate a respective SC policy, where the SFC policy identifier is determined according to the request to create the SC. For example, the wireless network function may send, to a network device, a SFC policy identifier to activate a respective SC policy, where the SFC policy identifier is determined according to the request to create the SC, as described above. As further shown in FIG. 10, process 1000 may include, at 1006, receiving, from the WTRU, a data set, where the data set includes a SC identifier (SCID) and a SC profile associated with SFC traffic. For example, the wireless network function may receive, from the WTRU, a data set, where the data set includes a SCID and a SC profile associated with SFC traffic, as described above. As also shown in FIG. 10, process 1000 may include, at 1008, sending the data set to a first AF based on the SC profile associated with the SFC traffic. For example, the wireless network function may send the data set to a first AF based on the SC profile associated with the SFC traffic, as described above. As further shown in FIG. 10, process 1000 may include at 1010,receiving, from the first AF, a first modified data set. For example, the wireless network function may receive, from the first AF, a first modified data set, as described above As also shown in FIG. 10, process 1000 may include at 1012, sending, to a second AF, the first modified data set, where the second AF is determined based on the SC profile. For example, device may send, to a second AF, the first modified data set, where the second AF is determined based on the SC profile, as described above. As further shown in FIG. 10, process 1000 may include, at 1014, receiving, from the second AF, a second modified data set. For example, device may receive, from the second AF, a second modified data set, as described above.

[0175] Although features and elements are described above in particular combinations, one of ordinary skill in the art will appreciate that each feature or element can be used alone or in any combination with the other features and elements. In addition, the methods described herein may be implemented in a computer program, software, or firmware incorporated in a computer-readable medium for execution by a computer or processor. Examples of computer-readable media include electronic signals (transmitted over wired or wireless connections) and computer-readable storage media. Examples of computer-readable storage media include, but are not limited to, a read only memory (ROM), a random access memory (RAM), a register, cache memory, semiconductor memory devices, magnetic media such as internal hard disks and removable disks, magnetooptical media, and optical media such as CD-ROM disks, and digital versatile disks (DVDs). A processor in association with software may be used to implement a radio frequency transceiver for use in a WTRU, UE, terminal, base station, RNC, or any host computer.

Claims

CLAIMSWhat is Claimed:

1. A method performed by a network function, the method comprising: receiving, from a wireless transmit / receive unit (WTRU), a request to create a service chain (SC) in a split artificial intelligence machine learning (AIM L) process; sending, to a network device, a service function chaining (SFC) policy identifier to activate a respective SC policy, wherein the SFC policy identifier is determined according to the request to create the SC; receiving, from the WTRU, a data set, wherein the data set includes a SC identifier (SCID) and a SC profile associated with SFC traffic; sending the data set to a first AF based on the SC profile associated with the SFC traffic; receiving, from the first AF, a first modified data set; sending, to a second AF, the first modified data set, wherein the second AF is determined based on the SC profile; and receiving, from the second AF, a second modified data set.

2. The method of claim 1 , further comprising: continuing a SC process of receiving a respective modified data set and sending the respective modified data set to a next AF when the SC profile includes a next AF; completing the SC process when an AF is a last AF in the SC; and notifying the WTRU of SC process results.

3. The method of claims 1 or 2, wherein the network function is a service chain management function (SCMF).

4. The method of any of claims 1 to 3, wherein the SFC policy identifier is received with the request to create the SC.

5. The method of any of claims 1 to 3, wherein the SFC policy identifier is determined based on a configuration of the SCMF.

6. The method of any of claims 1 to 5 claims, wherein the request to create the SC includes information indicating a use of 5G core network (5GC) SFC functionality in the split AIML process7. The method of any of claims 1 to 6, wherein the data set for SC processing is user SFC traffic received from the WTRU via a user plane function (UPF), and wherein the data set includes UPF traffic identifiers.

8. The method of claim 7, wherein the data set received via the UPF function is encapsulated according to the UPF traffic identifiers.

9. The method of claim 8, further comprising: performing a first SFC proxy function to remove SFC encapsulation of a first modified data set before sending the first modified data set to the second AF, andperforming a second proxy function to encapsulate the first modified data set before sending the SFC encapsulated first modified data set to the next AF when the SC profile includes the next AF.

10. The method of claim 9, wherein the SFC proxy function is determined for each AF based on the SC profile, and wherein the SFC proxy function is performed for each AF based on the respective SC policy.

11. A wireless network function comprising: processor circuitry; and a transceiver coupled to the processor circuitry and configured to: receive from a wireless transmit / receive unit (WTRU), a request to create a service chain (SC) in a split artificial intelligence machine learning (AIML) process; send to a network device, a service function chaining (SFC) policy identifier to activate a respective SC policy, wherein the SFC policy identifier is determined according to the request to create the SC; receive, from the WTRU, a data set, wherein the data set includes a SC identifier (SCID) and a SC profile associated with SFC traffic; send the data set to a first AF based on the SC profile associated with the SFC traffic; receive, from the first AF, a first modified data set; send, to a second AF, the first modified data set, wherein the second AF is determined based on the SC profile; and receive, from the second AF, a second modified data set.

12. The wireless network function of claim 11 , wherein the transceiver is further configured to: continue a SC process of receiving a respective modified data set and sending the respective modified data set to a next AF when the SC profile includes a next AF; and the processor circuitry is further configured to complete the SC process when an AF is a last AF in the SC; and the transceiver is configured to notify the WTRU of SC process results.

13. The wireless network function of claims 11 or 12, wherein the wireless network function is a service chain management function (SCMF).

14. The wireless network function of any of claims 11 to 13, wherein the SFC policy identifier is received with the request to create the SC.

15. The wireless network function of any of claims 11 to 13, wherein the processor circuitry is configured to determine the SFC policy identifier based on a configuration of the SCMF.

16. The wireless network function of any of claims 11 to 15, wherein the request to create the SC includes information indicating a use of 5G core network (5GC) SFC functionality in the split AIML process.

17. The wireless network function of any of claims 11 to 16, wherein the data set for SC processing is user SFC traffic received from the WTRU via a user plane function (UPF), and wherein the data set includes UPF traffic identifiers.

18. The wireless network function of claim 17, wherein the data set received via the UPF function is encapsulated according to the UPF traffic identifiers.

19. The wireless network function of claim 18, wherein the processor circuitry is further configured to: perform a first SFC proxy function to remove SFC encapsulation of a first modified data set before sending the first modified data set to the second AF, and perform a second proxy function to encapsulate the first modified data set before sending the SFC encapsulated first modified data set to the next AF when the SC profile includes the nextAF.

20. The wireless network function of claim 19, wherein the processor circuitry is further configured to: determine the SFC proxy function for each AF based on the SC profile; and perform the SFC proxy function for each AF based on the respective SC policy.

Images