Network data analytics function (NWDAF) assistance for enhanced quality of service (QOS) policies

Abstract

A network device may comprise a processor configured to receive a first request message from a second network function to provide network analytics for observed service experience sustainability (SES), send a second request message to a third network function to obtain a machine learning (ML) model for an SES analytics identifier (ID) that is associated with the observed SES, receive a first response message from the third network function, determine one or more analytics for the SES analytics ID using the trained ML model, and send a response message to the second network function. The response message may indicate, for example, the one or more analytics for the SES analytics ID. The one or more analytics for the SES analytics ID may include, for example, one or more predictions for each of a plurality of quality of service (QoS) parameters.

Description

NETWORK DATA ANALYTICS FUNCTION (NWDAF) ASSISTANCE FOR ENHANCED QUALITY OF SERVICE (QOS) POLICIESCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of United States Provisional Application No. 63 / 574,693 filed on April 4, 2024, the entire contents of each of which is incorporated herein by reference.BACKGROUND

[0002] When a WTRU is registered to the 5G network and / or may want to exchange user plane traffic with an application server via the 5GS, the WTRU may perform a packet data unit (PDU) session establishment procedure and / or certain quality of service (QoS) parameters may be determined for the QoS flow that may carry the application traffic for the WTRU. Such QoS parameters may include packet delay budget, packet error rate, guaranteed bit rate, and / or the like.SUMMARY

[0003] A network device may comprise a processor. The processor may be configured to receive a first request message from a second network function to provide network analytics for observed service experience sustainability (SES). The processor may be configured to select a third network function to obtain a ML model for SES ID and / or SES analytics ID, based on input parameters in first request message. The processor may be configured to send a second request message to a third network function to obtain a machine learning (ML) model for an SES analytics identifier (ID) that is associated with the observed SES. The processor may be configured to receive a first response message from the third network function. The first response message may include, for example, a trained ML model associated with the SES analytics ID. The processor may be configured to determine one or more analytics for the SES analytics ID using the trained ML model. The processor may be configured to send a response message to the second network function. The response message may indicate, for example, the one or more analytics for the SES analytics ID. The one or more analytics for the SES analytics ID may include, for example, one or more predictions for each of a plurality of quality of service (QoS) parameters.

[0004] The one or more analytics for the SES analytics ID may be determined, for example, based on one or more input parameters from the second network function. The one or more analytics for the SES analytics ID may include, for example, QoS sustainability and serviceexperience. The first request message may include, for example, one or more of the SES analytics ID, a wireless transmit / receive unit (WTRU) ID, and / or a single network slice selection assistance information (S-NSSAI) value.

[0005] The third network function may be selected, for example, selected based on a privacy compliance attribute provided in the first request message. The network device may include, for example, a network data analytics function (NWDAF). The second network function may include, for example, a policy control function (PCF) and / or a network exposure function (NEF), and the third network function may include, for example, a NWDAF comprising model training logical function (MTLF).

[0006] The response message may include, for example, Nnwdaf_MLModellnfo_Request response. The processor may be configured to provide the determined analytics to an analytics consumer via a Nnwdaf_Analyticslnfo_Request response.

[0007] A network device may configured to perform a method that includes one or more of the following steps. The method may include receiving a first request message from a second network function to provide network analytics for observed service experience sustainability (SES). The method may include selecting a third network function to obtain a ML model for SES ID and / or SES analytics ID, based on input parameters in first request message. The method may include sending a second request message to a third network function to obtain a machine learning (ML) model for an SES analytics identifier (ID) that is associated with the observed SES. The method may include receiving a first response message from the third network function. The first response message may include, for example, a trained ML model associated with the SES analytics ID. The method may include determining one or more analytics for the SES analytics ID using the trained ML model. The method may include sending a response message to the second network function. The response message may indicate, for example, the one or more analytics for the SES analytics ID. The one or more analytics for the SES analytics ID may include, for example, one or more predictions for each of a plurality of quality of service (QoS) parameters.

[0008] The one or more analytics for the SES analytics ID may be determined, for example, based on one or more input parameters from the second network function. The one or more analytics for the SES analytics ID may include, for example, QoS sustainability and service experience. The first request message may include, for example, one or more of the SES analytics ID, a wireless transmit / receive unit (WTRU) ID, and / or a single network slice selection assistance information (S-NSSAI) value.

[0009] The third network function may be selected, for example, selected based on a privacy compliance attribute provided in the first request message. The network device may include, for example, a network data analytics function (NWDAF). The second network function may include, for example, a policy control function (PCF) and / or a network exposure function (NEF), and the third network function may include, for example, a NWDAF comprising model training logical function (MTLF).

[0010] The response message may include, for example, Nnwdaf_MLModellnfo_Request response. The method may include providing the determined analytics to an analytics consumer via a Nnwdaf_Analyticslnfo_Request response.BRIEF DESCRIPTION OF THE DRAWINGS

[0011] FIG. 1A is a system diagram illustrating an example communications system in which one or more disclosed embodiments may be implemented.

[0012] 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.

[0013] 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.

[0014] FIG. 1 D 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.

[0015] FIG. 2 depicts a call flow diagram illustrating an example observed service experience sustainability based enhanced quality of service (QoS) determination.

[0016] FIG. 3 depicts a call flow diagram illustrating an example network data analytics function (NWDAF) registration supported with feature identifiers (IDs), and / or conditions and / or attributes per analytics ID.

[0017] FIG. 4 depicts a call flow diagram illustrating an example features set based machine learning (ML) model training and / or analytics production using vertical federated learning (VFL).DETAILED DESCRIPTION

[0018] 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 bea 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), single-carrier FDMA (SC-FDMA), zero-tail unique-word DFT-Spread OFDM (ZT UW DTS-s OFDM), unique word OFDM (UW-OFDM), resource block-filtered OFDM, filter bank multicarrier (FBMC), and the like.

[0019] As shown in FIG. 1A, the communications system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, a RAN 104 / 113, a CN 106 / 115, a public switched telephone network (PSTN) 108, the Internet 110, and other networks 112, though it will 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” and / or a “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-Fi 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 WTRU. Further, any description herein that is described with reference to a UE may be equally applicable to a WTRU (or vice versa). For example, a WTRU may be configured to perform any of the processes or procedures described herein as being performed by a UE (or vice versa).

[0020] 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 / 115, the Internet 110, and / or the other networks 112. By way of example, the base stations 114a, 114b may be a basetransceiver station (BTS), a Node-B, an eNode B, a Home Node B, a Home eNode B, a gNB, a NR NodeB, a site controller, an access point (AP), a wireless router, and the like. While the base stations 11 a, 114b are each depicted as a single element, it will be appreciated that the base stations 114a, 114b may include any number of interconnected base stations and / or network elements.

[0021] The base station 114a may be part of the RAN 104 / 113, 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, etc. 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.

[0022] 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).

[0023] 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 / 113 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 115 / 116 / 117 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 UL Packet Access (HSUPA).

[0024] 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).

[0025] 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 New Radio (NR).

[0026] 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 radio access technologies and / or transmissions sent to / from multiple types of base stations (e.g., a eNB and a gNB).

[0027] 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 1 X, 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.

[0028] The base station 114b in FIG. 1 A 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 cellularbased 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 / 115.

[0029] The RAN 104 / 113 may be in communication with the CN 106 / 115, which may be any type of network configured to provide voice, data, applications, and / or voice over internetprotocol (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 / 115 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. 1 A, it will be appreciated that the RAN 104 / 113 and / or the CN 106 / 115 may be in direct or indirect communication with other RANs that employ the same RAT as the RAN 104 / 113 or a different RAT. For example, in addition to being connected to the RAN 104 / 113, which may be utilizing a NR radio technology, the CN 106 / 115 may also be in communication with another RAN (not shown) employing a GSM, UMTS, CDMA 2000, WiMAX, E-UTRA, or WiFi radio technology.

[0030] The CN 106 / 115 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 networks owned 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 / 113 or a different RAT.

[0031] 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. 1A may be configured to communicate with the base station 114a, which may employ a cellular-based radio technology, and with the base station 114b, which may employ an IEEE 802 radio technology.

[0032] FIG. 1B 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 mayinclude any sub-combination of the foregoing elements while remaining consistent with an embodiment.

[0033] 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) circuits, 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.

[0034] 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.

[0035] Although the transmit / receive element 122 is depicted in FIG. 1B 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.

[0036] 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 element 122. 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.

[0037] 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).

[0038] 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.

[0039] 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.

[0040] 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 geolocation sensor; an altimeter, a light sensor, a touchsensor, a magnetometer, a barometer, a gesture sensor, a biometric sensor, and / or a humidity sensor.

[0041] 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 downlink (e.g., for reception) may be concurrent and / or simultaneous. The full duplex radio may include an interference management unit 139 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 WRTU 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 downlink (e.g., for reception)).

[0042] 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 CN 106.

[0043] 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.

[0044] 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.

[0045] 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 (or PGW) 166. While each of 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.

[0046] 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 theWTRUs 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.

[0047] 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 B handovers, 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.

[0048] 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.

[0049] 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.

[0050] 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.

[0051] In representative embodiments, the other network 112 may be a WLAN.

[0052] 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 an 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) thesource 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.

[0053] When using the 802.11ac 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 via signaling. 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 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 a particular STA, the particular STA may back off. One STA (e.g., only one station) may transmit at any given time in a given BSS.

[0054] 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.

[0055] 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 non-contiguous 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).

[0056] 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 802.11 n, and 802.11ac. 802.11af supports 5 MHz, 10 MHz and 20 MHz bandwidths in the TV White Space (TVWS) spectrum, and 802.11ah supports 1 MHz, 2 MHz, 4 MHz, 8 MHz, and 16 MHz bandwidths using non-TVWS spectrum. According to a representativeembodiment, 802.11ah may support Meter Type Control / Machine-Type Communications, 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).

[0057] WLAN systems, which may support multiple channels, and channel bandwidths, such as 802.11n, 802.11ac, 802.11af, and 802.11ah, 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, the entire available frequency bands may be considered busy even though a majority of the frequency bands remains idle and may be available.

[0058] In the United States, the available frequency bands, which may be used by 802.11ah, 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.

[0059] FIG. 1 D is a system diagram illustrating the RAN 113 and the CN 115 according to an embodiment. As noted above, the RAN 113 may employ an NR radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 113 may also be in communication with the CN 115.

[0060] The RAN 113 may include gNBs 180a, 180b, 180c, though it will be appreciated that the RAN 113 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).

[0061] 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 varying number of OFDM symbols and / or lasting varying lengths of absolute time).

[0062] 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.

[0063] 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, dual connectivity, 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 MobilityManagement Function (AMF) 182a, 182b and the like. As shown in FIG. 1 D, the gNBs 180a, 180b, 180c may communicate with one another over an Xn interface.

[0064] The CN 115 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 each of the foregoing elements are depicted as part of the CN 115, it will be appreciated that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0065] The AMF 182a, 182b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 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 PDU sessions with different requirements), selecting a particular SMF 183a, 183b, management of the registration area, termination of 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 machine type communication (MTC) access, and / or the like. The AMF 162 may provide a control plane function for switching between the RAN 113 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.

[0066] The SMF 183a, 183b may be connected to an AMF 182a, 182b in the CN 115 via an N11 interface. The SMF 183a, 183b may also be connected to a UPF 184a, 184b in the CN 115 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 WTRU IP address, managing PDU sessions, controlling policy enforcement and QoS, providing downlink data notifications, and the like. A PDU session type may be IP-based, non-IP based, Ethernet-based, and the like.

[0067] The UPF 184a, 184b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via an N 3 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 downlink packets, providing mobility anchoring, and the like.

[0068] The CN 115 may facilitate communications with other networks. For example, the CN 115 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 115 and the PSTN 108. In addition, the CN 115 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 Data Network (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.

[0069] In view of Figures 1A-1 D, and the corresponding description of Figures 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-ab, 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.

[0070] 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 may performing testing using over-the-air wireless communications.

[0071] 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.

[0072] The 5GS analytics services may be augmented to provide new analytics. One such new analytics, service experience sustainability analytics, may use data related to QoS sustainability and service experience to train a ML model to provide analytics output related to service experience sustainability. A NWDAF may receive a request to provide analytics for observed service experience sustainability (SES). The NWDAF may determine to obtain a ML model for such analytics to other NWDAFs. An NWDAF containing model training logical function (MTLF) may be triggered to train and / or retrain a ML model for these analytics. The NWDAF containing MTLF may perform data collection from different network functions and / or train the ML model. The NWDAF containing MTLF may provide the first NWDAF with the ML model. The First NWDAF may determine the analytics result and may provide the analytics result to the analytics consumer.

[0073] A network data analytics function (NWDAF) may be configured for machine learning (ML) model training and / or inference for other (e.g., new) observed service experience sustainability (SES) analytics.

[0074] A policy control function (PCF) may perform one or more of the following. For example, a PCF may receive from an application function (AF) (e.g., via network exposure function (NEF)), a request for a service operation that may involve artificial intelligence or machine learning (AI / ML) interactions (e.g., a joint determination of observed service experience, using vertical federated learning (VFL). This may be used by the PCF to determine whether additional analytics and / or predictions may be requested, when setting QoS parameters. Additionally and / or alternatively, the PCF may identify (e.g., using an operator configured threshold), that it has received a large amount of session management function (SMF) interactions requesting changes to the policy and charging control (PCC) rules, within a certain time period. This time period may be based on the revalidation time limit used by the PCF to trigger an SMF interaction (e.g., due to an enforced PCC rule request).

[0075] A NDWAF service consumer may perform one or more of the following. The NWDAF service consumer may receive a request to provide network analytics for SES from a network function (e.g., policy control function (PCF), network exposure function (NEF), etc.). For example, an analytics ID value may be observed service experience analytics and / or SES. The target of analytics reporting may be a certain WTRU ID. Analytics filtering Information may include a single network slice selection assistance information (S-NSSAI) value. The NWDAF service consumer may send a request to a NWDAF including model training logical function(MTLF) to obtain ML model for the SES analytics ID. The NWDAF service consumer may receive from the NWDAF including MTLF a trained ML model for the SES analytics ID. The NWDAF service consumer may determine analytics output, for example, based on the obtained ML model and / or the input parameter(s) from the PCF and / or NEF. The NWDAF service consumer may send a response message to the network function (NF) (e.g., PCF, NEF, etc.) with SES analytics with predictions per QoS parameter(s) and / or one or more other parameters (e.g., flow bit rate, aggregated bit rate, maximum packet loss rate) and / or notification control (e.g., the SES analytic may be used by the PCF to set the QoS notification control parameter (QNC)).

[0076] A NWDAF including MTLF may perform one or more of the following. The NWDAF including MTLF may receive a request from a NWDAF service consumer to provide ML model for SES analytics. This request message may include a WTRU ID and / or a S-NSSAI value. The NWDAF including MTLF may check whether a ML model is available to provide to the NWDAF service consumer. The NWDAF including MTLF may determine that a ML model is not available and / or may (e.g., need to) be trained and / or an existing ML model is available that may (e.g., need to) be retrained. The NWDAF including MTLF may interact with different network entities to collect data relevant for the ML model training process. The NWDAF including MTLF may use the data collected to train a ML model for the SES. The NWDAF including MTLF may send a response message to the NWDAF service consumer with the trained ML model for the SES analytics ID.

[0077] An analytics service consumer (e.g., PCF) and / or an analytics service producer (e.g., NWDAF) may interact for ML model training and / or inference with custom features sets and / or with attributes.

[0078] A NWDAF node may perform one or more of the following. The NWDAF node may receive from an analytics consumer a request to provide analytics. The request may include the analytics ID, and / or a set of requested feature IDs to be used as dataset features for ML model training and / or inference. The request may include attributes and / or conditions that the analytics may (e.g., need to) satisfy. The NWDAF may determine (e.g., find) available ML models for the requested analytics ID, set of feature IDs, and / or attributes. The NWDAF node may send a discovery message to a network repository function (NRF), and / or may include the analytics ID, requested set of feature IDs and / or attributes, to discover supporting NWDAF IDs. The NWDAF node may receive a response message from the NRF. The response message may include NWDAF IDs, supported feature IDs per NWDAF ID, and / or supported attributes per NWDAF ID. The NWDAF node may consolidate the information received from the NRF to determine a list ofavailable feature IDs and / or supported attributes for the requested analytics ID. The NWDAF node may send a message to the analytics consumer, with a list of available feature IDs from the originally requested feature IDs and / or supported attributes. The message may solicit the analytics consumer to confirm whether the provided feature IDs and / or a subset of the provided feature IDs is acceptable. The NWDAF node may receive a confirmation message from the analytics consumer that the available feature IDs are acceptable for the requested analytics ID. The NWDAF node may determine to perform network function (NF) selection for ML model training, and / or may determine the ML training method (e.g., VFL) based on the features ID location and / or based on the attribute(s). The NWDAF may request the selected NWDAF IDs to perform ML model training (e.g., using VFL method). Once the ML model training is completed by the selected NWDAFs, the NWDAF may obtain the ML model. The NWDAF may determine analytics output based on the obtained trained ML model. The NWDAF node may send analytics result to the analytics consumer.

[0079] An application function can provide one or more QoS parameters (e.g., such as packet delay budget, packet error rate, guaranteed bit rate, and / or the like) for the application traffic to the 5GS, using NEF services, such as application function (AF) session with required QoS service. When the AF provides these parameters to the 5GS via the NEF, for example, the PCF may generate policy and charging control (PCC) rules which may include QoS parameters derived based on the parameters provided by the AF. The PCF may send the PCC rules to the session management function (SMF) which (e.g., in turn) may generate N4 rules and / or QoS profile and / or QoS rules to send to the user plane function (UPF), radio access network (RAN), and / or WTRU, respectively. The SMF may perform PDU session modification, in which another (e.g., new) QoS flow may be created to help carry the user plane traffic with the requested parameters (e.g., usually a default QoS flow is established when the PDU Session is first established).

[0080] The PDU session may undergo PDU session modification procedure for different purposes, for example, to change and / or update an existing QoS flow with another (e.g., new) QoS flow parameters, and / or to create another (e.g., new) QoS flow with other (e.g., new) QoS parameters, and / or to remove a QoS flow that no longer has bound PCC rules. The specification may define one or more (e.g., several) conditions that trigger the interaction of SMF toward the PCF to modify and / or updated policy and charging control rules, e.g., a WTRU IP address and / or MAC address change, the guaranteed flow bit rate (GFBR) of the QoS Flow can no longer (or can again) be guaranteed. This may result in (e.g., substantial) signaling messages between 5GS entities, including 5GC, RAN, and WTRU, and / or (e.g., noticeable) degradation of userexperience. It may be desirable to enhance the handling and / or determination of QoS parameters at 5GC, to enable the identification of a (e.g., large) amount of interactions, resulting from trigger conditions at the SMF, and / or the selection of optimal QoS parameters that are sustainable, (e.g., thereby) reducing the amount of SMF-PCF interactions, while enhancing user experience.

[0081] Embodiments described herein may relate to enhanced policy control procedures, using other (e.g., new) and / or existing network analytics to assist in QoS policies determination. Enhancing the 5GS to enable the detection of SMF interactions with the PCF above a configured threshold, and / or may determine that the use of other (e.g., new) and / or existing network analytics for QoS determination may be warranted, ensuring sustainable QoS conditions, and / or enhancing user experience, may be described herein. For example, enhancing the 5GS with other (e.g., new) procedures to detect either an unusual amount of events triggering SMF interactions with the PCF within a period of time (e.g., within the existing revalidation time), and / or determine whether the use of other (e.g., new) and / or existing network analytics for QoS determination may be warranted (e.g., ensuring sustainable QoS conditions and / or enhancing user experience). Additionally and / or alternatively, enhancing the 5GS to determine the use of other (e.g., new) and / or existing analytics, when an AF request for a service operation such as Observed Service Experience may indicate that the service operation may use AI / ML procedures, such as vertical federated learning. The PCF may request, from the NWADF, observed service experience and / or QoS sustainability (e.g., separately) and / or may correlate their impact on QoS determination, and / or request a combined / joined analytic from the NWDAF and / or may take the (e.g., new) combined analytic into consideration when configuring QoS parameters.

[0082] The other (e.g., new) analytics may provide output in the form of statistics and / or predictions jointly determining observed service experience and / or QoS sustainability. For example, the other (e.g., new) procedures may trigger a request for network analytics in the form of statistics and / or predictions linking service experience and QoS sustainability (e.g., once the PCF has determined that additional network analytics are warranted). The PCF may (e.g., either) request other (e.g., new) analytics (e.g., QoS sustainability multiplied by service experience), and / or request QoS sustainability and / or Observed Service Experience (e.g., separately), and / or may correlate these analytics to determine optimal value. The (e.g., new) analytic may be referred to as Service Experience Sustainability (SES). One example may be QoS sustainability multiplied by observed service experience (SE). For example, the output may be QoS sustainability multiplied by the observed service experience. From the output expression, finding QoS parameters that optimize (e.g., maximize) QoS sustainability and / or QoS parameters that optimize (e.g., maximize) observed service experience separately may notbe achievable. For example, the QoS1 that maximized QoS sustainability and / or QoS2 that maximized observed service experience, QoS1 and / or QoS2 may not be the optimal QoS that maximizes QoS sustainability multiplied by observed service experience. It may be that training another (e.g., new) ML model that provides analytics on a function (e.g., such as the one described herein) of the one or more (e.g., two) analytics (QoS sustainability and observed service experience) may be useful.

[0083] An (e.g., another) advantage of this (e.g., new) analytics may be that the data collected for the other (e.g., new) analytics, which may include data related to observed service experience, QoS, and / or QoS parameters, may be used for data collection of the existing analytics (e.g., SE and / or QoS sustainability). The data collection process for this other (e.g., new) analytic may be beneficial to data collection for the one or more (e.g., two) existing analytics.

[0084] Additionally and / or alternatively, the data collected that is related to QoS sustainability may be enhanced to be more granular compared to the data collected to train the existing QoS sustainability analytic. The current QoS sustainability analytic may have the target of analytics reporting set to one or more (e.g., any) WTRU, which may not provide a per WTRU ID granularity. The current analytic may not include filter information related to application information, such as application ID.

[0085] A more granular data collection may be used to train ML models to generate existing analytic if the scope of the target of analytics reporting is reduced, (e.g., data collected for specific WTRU IDs can be included to train a ML model that is trained for one or more (e.g., any) WTRU).

[0086] To obtain such joint analytics, a NF (e.g., usually NWDAF), may (e.g., need to) perform data collection ML model training and / or procedure analytics (e.g., for this case). This NF may reside in one or more NWDAF functions, and / or different network functions. For simplicity, for example, the NWDAF may be used in examples (e.g., as described herein).

[0087] To provide these analytics, the NWDAF may train one or more ML models. The NWDAF may collect data to train such ML models.

[0088] The consumer of these analytics may indicate in the request: Analytics ID = Observed service experience Sustainability (SES).

[0089] The interpretation of the analytics ID may be to provide information about QoS parameters that fulfill certain observed service experience values, such that these QoS parameters have a certain (e.g., minimum or so) QoS sustainability. The target of analyticsreporting may be one or more of: a specific WTRU, a group of WTRU s, and / or one or more (e.g., any) WTRU.

[0090] Analytics filter information may include one or more of the following. Analytics filter information may include a 5G QoS Identifier (5QI) and / or QoS parameters. Analytics filter information may include an application ID. Analytics filter information may include a S-NSSAI. Analytics filter information may include a data network name (DNN). Analytics filter information may include an area of interest. Analytics filter information may include location information.

[0091] Analytics target period may represent the relative time interval in the past and / or in the future, for which analytic is requested.

[0092] Reporting threshold(s) representing threshold values for the SES may be provided by the NF consumer when requesting the service operation, so that the NF producer (e.g., an NWDAF) may notify the NF consumer (e.g., a PCF) predictions as to when such thresholds are expected to be crossed, and / or how often they are crossed.

[0093] In examples, the NF may estimate the time it takes a WTRU, having a QoS flow matching certain QoS parameter values, to change their values by a certain margin (e.g., value x), and / or the predicted time it may take the QoS flow to change below the QoS parameter values by a margin (e.g., value y), while the observed service experience is maintained (e.g., with a certain value and / or within a certain range).

[0094] This predicted time may be different in the critical and / or non-critical directions. The critical direction may be when the observed service experience sustainability decreases and / or the QoS parameters that maintain a certain observed service experience in a time window t, are reduced. The non-critical condition (e.g., in this case) may be when the observed service experience sustainability increases and / or when (e.g., similarly) the QoS parameters that maintain a certain observed service experience within a certain time window, improves.

[0095] For example, a 5QI may change (e.g., much) slower in the non-critical direction (e.g., QoS improves) and / or may change (e.g., much) higher in the critical direction (e.g., QoS deteriorates). In examples, the time before a crossing threshold may be similar in both directions of the QoS parameters.

[0096] These thresholds and / or margin values (e.g., x and y as described herein) may (e.g., also) be provided by the analytics consumer to the NWDAF, (e.g., in addition to the reporting thresholds), as these may be different types of thresholds.

[0097] For the analytic ID observed service experience sustainability, the NWDAF may use data collected to train existing network analytics (e.g., QoS sustainability analytics) such as one or more of the following. Observed service experience for a WTRU, in certain conditions (e.g.,for certain S-NSSAI, DNN, application ID). The NWDAF may collect data related to the QoS parameters of the QoS flow that carries the application traffic for WTRU, as well as quality of experience (QoE) analytics. Data related to QoS parameters may be collected from the PCF for the PDU session of the WTRU. Data related to QoE for the WTRU for a certain application and / or S-NSSAI / DNN may be collected (e.g., eventually) from an AF. The NWDAF may (e.g., also) collect data, regarding observed performance, in terms of QoS, such as observed data rate, observed delay, and / or the like. Other data similar to data collected for the existing QoS sustainability analytics may be collected (e.g., RAN WTRU throughput, QoS flow retainability, delay in RAN). The data collected related to QoS sustainability may be enhanced to have a better (e.g., more fine) granularity, to allow for a WTRU, group of WTRUs, one or more (e.g., any) WTRU, an application, and / or group of applications and / or WTRU location specific data collection.

[0098] A (e.g., main) feature for the ML model to be trained for observed service experience sustainability analytics may be the QoS parameters. The data collected for existing analytics, such as observed service experience and / or (e.g., a more granular) service sustainability can be used to collect the data for the ML model (e.g., with only QoS parameters as input).

[0099] Once the NWDAF collects the data (e.g., as described herein), for example, with desired granularity, the NWDAF may train an ML model for the observed service experience sustainability analytic using one or more of: a sample ID, an input feature, and / or output variables. Sample ID may include timestamps (e.g., of data collection), for a given WTRU ID and / or application, etc.. Input feature may include QoS parameters, which may represent the QoS parameters used for the QoS flow that carries application traffic for the WTRU at the time of the data collection (e.g., at timestamp). Related QoS flow parameters may include allocation and retention priority (ARP) value. One or more values and / or parameters described herein may be (e.g., collectively) referred to as QoS parameters (e.g., for simplicity purposes). Output variables may include SES = QoS sustainability multiplied by observed service experience. The SES and / or output of the analytic can be a different function of the two analytics. Although these analytics may be provided separately, the consumer of the data analytics function may request a joint prediction and / or statistic, (e.g., as requesting them separately may not achieve the desired effect). For example, requesting observed service experience and / or QoS sustainability, separately may not characterize how observed service experience is being impacted, (e.g., when QoS sustainability at a particular time, in a particular location, and / or for a specific application is inferred).

[0100] FIG. 2 depicts an example call flow 200 that illustrates requesting the other (e.g., new) observed service experience sustainability analytics ML model training and / or inference.

[0101] In call flow 200 at 202, the PCF may receive from an AF (e.g., via a network exposure function (NEF)), a request for a service operation that includes AI / ML interactions. For example, the service operation may be an observed service experience determination, using VFL. This may be used by the NEF and / or the PCF to determine whether additional analytics and / or predictions may be used, (e.g., when setting QoS parameters).

[0102] At 204, additionally and / or alternatively, the PCF may identify (e.g., using an operator configured threshold), that it has received a (e.g., large) amount of SMF interaction requesting changes to the policy and charging control rules, for example, within a certain time period). The time period can be based on the revalidation time limit used by the PCF to trigger an SMF interaction, due to enforced PCC rule request.

[0103] At 206, the PCF may be triggered to send a request to an NWDAF network function to request the training of an ML model for observed service experience sustainability analytics. The PCF may be triggered when another (e.g., new) PDU session establishment request is received by an SMF function for a certain WTRU. When the SMF receives the PDU session request establishment message, for example, the SMF may interact with the PCF serving the WTRU for the PDU session to create a session management (SM) context association between the SMF and the PCF for the PDU Session of interest. The SMF may use the Npcf_SMPolicyControl_Create service operation. The PCF may have (e.g., also) received a request message from the NEF when an application function contacts the 5GS via the NEF, to request, for example, to reserve network resources for an AF session. The NEF may interact with the PCF using the Npcf_PolicyAuthorization_Create request, for example.

[0104] The PCF may have received input parameters from the AF via the NEF, such as QoS parameters for the AF session. Input parameters may include different QoS parameters to be considered, such as packet delay budget, packet error rate, and / or guaranteed bit rate etc. The input parameters may include analytics target period (e.g., which may represent the relative time interval in the past and / or in the future, for which the analytic may be requested). The input parameters may include the target of the analytics output (e.g., a WTRU ID), and / or application ID, and / or S-NSSAI / DNN, area of interest, etc. The PCF may have (e.g., also) received an indication that optimal QoS determination using observed service experience sustainability related analytics is request and / or desired and / or preferred. The AF may (e.g., also) provide to the PCF via the NEF, a range of values for the observed service experience that are acceptable to the AF.

[0105] The PCF may be triggered to perform SES assisted QoS determination for certain S- NSSAI and / or DNN values. For example, when a specific network slice with S-NSSAI is used, the PCF may determine that this network slice requires and / or recommends QoS optimization using SES analytics. Additionally and / or alternatively, an indication in the 5GS (e.g., in the unified data management (UDM) and / or unified data repository (UDR), that indicates optimizing QoS based on SES analytics may be preferred for the user and / or subscriber of interest.

[0106] The PCF may send a request to the NWDAF to request SES analytics for the WTRU of interest. The PCF may use NWDAF service operations such as Nnwdaf_AnalyticsSubscription_Subscribe and / or Nnwdaf_Analyticslnfo_Request. The PCF may provide the analytics ID for the analytics of interest. In examples, the PCF may include analytics ID = observed service experience sustainability. The PCF (e.g., also) may include the target of analytics reporting (e.g., WTRU ID), to obtain analytics specific to the WTRU ID of interest. The PCF may (e.g., also) include analytics reporting parameters, such as analytics target period.The PCF may include a value for the analytic target period that reflects the expected duration of the AF session, for example, if such information is available at the PCF, and / or by using input parameter from the AF request (e.g., when AF requests an AF session and / or indicates that optimal QoS determination is active, the AF may provide an indication of the time window(s) during which the application session is expected to be maintained).

[0107] The PCF may (e.g., also) include analytics filter information, such as S-NSSAI value and / or DNN value, and / or application ID of the application of interest.

[0108] At 208, a first NWDAF may receive the request from the PCF and / or other analytics consumer. The first NWDAF may interact with a second NWDAF including MTLF to request information about ML model for the analytics ID of interest. The first NWDAF may send a Nnwdaf_MLModellnfo_Request message to the second NWDAF.

[0109] At 210, the NWDAF including MTLF may check whether such ML model is available and / or if it may (e.g., need to) be further trained. In examples, the NWDAF including MTLF may determine that the ML model is not available and / or may (e.g., need) to be re-trained and / or may initiate data collection from different entities (e.g., UPF, SMF, operations, administration, and maintenance (QAM) for ML model training.

[0110] At 212, the NWDAF including MTLF may perform ML model training using the data collected from the NFs and / or QAM. At 214, once the ML model training is complete and / or the ML model is ready, for example, the NWDAF including MTLF may send the ML model to the first NWDAF (e.g., by sending Nnwdaf_MLModellnfo_Request response message to the first NWDAF).

[0111] At 216, the first NWDAF may use the received ML model for analytics ID of interest, for example, to determine analytics for the SES. At 218, the first NWDAF may provide the determined analytics to the analytics consumer and / or PCF, via a Nnwdaf_Analyticslnfo_Request response. At 220, the PCF may use the SES analytics, for example, to determine an optimal QoS for the WTRU ID and / or the application traffic of interest. In examples (e.g., additionally and / or alternatively), a PCF function may try to use existing analytics provided by the 5GS, such as existing QoS sustainability analytics and / or observed service experience analytics.

[0112] Since these (e.g., two) analytics may be trained separately with one or more (e.g., two) different L models, for example, the PCF may adopt a certain process to leverage these analytics and / or determine QoS parameters that may be optimal for a sustainable observed service experience. For example, the PCF may have a set of QoS parameters that it may preselect for a possible use for the QoS flow that may carry the application traffic of the WTRU.

[0113] The PCF may request separately the observed service experience analytics and / or the QoS sustainability analytics. The PCF may try to find an optimal QoS parameter (e.g., as described herein). The PCF may determine the subset of QoS parameters values from the preselected set of QoS parameters, such as the determined QoS parameters values satisfy that the observed SES (OSE) is within a certain acceptable range. The PCF may (e.g., then) select from that subset of QoS parameters value, the QoS parameters that have the best QoS sustainability (e.g., preserve the desired QoS parameter values for the longest period of time), using the QoS sustainability analytics.

[0114] Embodiments described herein may relate to (e.g., further) network analytics enhancements for an optimal choice of alternative QoS profiles (AQP) parameters. In examples, for a certain QoS flow, a first set of QoS parameters may be provided for the QoS flow, and / or one or more other sets of alternative QoS parameters may (e.g., also) be provided for the QoS flow, to allow for when the QoS flow conditions change, the appropriate QoS flow parameters may be applied to the QoS flow.

[0115] When the QoS parameters of the QoS flow cannot be met by the serving RAN node, and / or there is a set of alternative QoS parameters that can be fulfilled, for example, (e.g., then) the RAN may inform the 5GC (e.g., the SMF) that the QoS parameters have changed and / or may provide a reference to the AQP parameters set. This may incur a PDU Session modification procedure, to allow the SMF to update the QoS flow related rules such as N4 rules at the UPF and / or QoS rules at the WTRU, with the other (e.g., new) AQP parameters.

[0116] The RAN node may (e.g., also need to) check whether the original QoS parameters and / or an AQP that is more prioritized than the currently used AQP parameters, can be fulfilled again, and / or may notify the SMF when this is the case. This may (e.g., also) incur a PDU Session modification procedure.

[0117] The RAN may determine that a certain QoS parameter QoS1 can no longer be fulfilled, for example, if the QoS parameter QoS2 that can be fulfilled is below a certain margin x from the original QoS parameters (e.g., QoS1). The margin value may be based (e.g., depend) on implementation by the RAN node.

[0118] A supported QoS3 may be determined to fulfil QoS2 (e.g., one QoS parameter may be considered as an example), if the QoS3 is within a certain margin from QoS2. For example, Q2 - x < Q3 < Q2 +y with x and y are two margins, which can have the same value (e.g., depending on RAN implementation).

[0119] Depending on the values of the QoS parameters for the QoS flow and / or the alternative QoS parameters, when AQP feature is enabled for the QoS flow and the value of the margins x and y, the PDU Session modification procedures may take place often or less often.

[0120] To determine a certain configuration of QoS parameters with the set of alternative QoS parameters, it may be possible to use an enhanced version of the new observed service experience sustainability analytics to determine such parameters. These analytics may be called Enhanced SES and / or ESES.

[0121] The QoS and / or alternative QoS parameters can be determined as per the following. One or more (e.g., all) of the QoS and / or alternative QoS parameters may provide a similar observed service experience sustainability (SES). The QoS and / or alternative QoS parameters may incur the least signaling related to QoS flow update / PDU session modification procedures. For example, the QoS variability of such QoS parameters may incur the least signaling related to QoS flow update.

[0122] To train a ML model to provide such analytics, a NF, such as an NWDAF may (e.g., need to) collect data, similar to the SES analytics, with the one or more of following modifications and / or additions. A NF may collect data about the thresholds at RAN node, for one or more (e.g., each) QoS parameter(s). The threshold may refer to the margins x and y for parameter QoS1 , based on which a RAN node determines that a QoS parameter is not fulfilled and / or cannot be fulfilled. These margins may be different for different values of the parameters QoS1. For example, a packet delay budget (PDB) = 20ms is fulfilled is 20ms-5 < measured delay 20ms +5 and PDB = 5ms is fulfilled if 5ms - 2 < measured delay < 5ms+ 1. The NWDAF may collect for one or more (e.g., each) QoS parameters, the margins used by RAN todetermine whether the QoS is fulfilled or not. A NF may collect data from OAM related to the number QoS flow updates that are performed for a QoS flow. The NWDAF can collect, from OAM, the number of QoS flow updates for each set of QoS parameters (available), including number of attempts, successful, and / or failed attempts. The NF may collect from the OAM data related to the QoS flow release, including number of QoS flow release, attempts, successful, and / or failed attempts, as well as abnormal release. The NF may collect data related to QoS parameters and / or related parameters (e.g., ARP, and / or the like).

[0123] Once a ML model is trained with such data, for example, the ML model can produce enhanced observed service experience sustainability (ESES) analytics in the form of statistics and / or predictions for the ESES.

[0124] A NF consumer, such as a PCF, can provide the margins (x,y) for each QoS parameters to the NWDAF when requesting the ESES analytics. These margin values can be provided as Reporting threshold(s) for the ESES analytics.

[0125] An example of use of the analytics is as follows. If AQP feature is considered for a certain WTRU using a certain application traffic, and a number of AQP levels is provided (e.g., 3 levels), there may be QoS parameters QoS1 , and two alternative QoS parameters sets (e.g., QoS2 and QoS3).

[0126] The PCF can determine with one exchange and / or interaction with the NWDAF the optimal values for QoS1 , QoS2 and QoS3, to allow for QoS parameters that optimize / maximize the ESES observed service experience with the least QoS flow update related signaling.

[0127] Embodiments described here may relate to a feature set based analytics ML model training and / or inference. A mechanism to enable a NF, such as a PCF, to specify (e.g., provide) one or more (e.g., some) conditions related to the analytics that the NF (e.g., PCF) requests from another NF, such as a NWDAF, may be described herein.

[0128] The NF and / or PCF can include different conditions and / or restrictions for the analytics production. For example, the PCF may want that the analytics that are produced for observed service experience sustainability to determine QoS parameters for a QoS flow, that are privacy compliant. In examples, the PCF may expect the NWDAF not to share network data with other NFs such as an AF and / or may expect the NWDAF not to collect data from other NFs, for example, an AF (e.g., QoE data related to user experience), to train the ML model for the requested analytic.

[0129] Such a condition and / or similar conditions may trigger the NWDAF to determine to produce the requested analytics using specific parameters and / or methods. For example, theNWDAF may determine to not collect data from AF for SES analytics, related to observed service experience, and / or the NWDAF may determine to perform model training for this ML model using a privacy protecting method, for example vertical federated learning.

[0130] The (e.g., existing) filtering mechanisms that may be specified (e.g., for 5G networks), may be used to provide these conditions and / or restrictions. The difference may include that the (e.g., existing) mechanism does not (e.g., explicitly) impose restrictions on the analytics and / or prediction(s) that may be generated, and / or the NFs these analytics may be collected from.

[0131] Additionally and / or alternatively, the 5GS may be able to provide network data analytics, that are generated using different sets of features, for the same sample (e.g., for the a WTRU or a collection of WTRUs, and / or for an area of interest (e.g. a tracking area). For example, when generating network analytics such as QoS sustainability, one set of features to be able to train an ML model to produce these analytics may be, S1 = {observed delay, and / or QoS retainability}. In examples, QoS sustainability analytic may be produced using an ML model trained with features such as S2 = {QoS retainability, requested GBR, observed data rate}. In examples, if a NF function, (e.g., a PCF) wants to train a ML model for QoS sustainability, using features QoS parameters, QoS retainability, GBR, data rate, and / or delay, (e.g., then) an NWDAF may (e.g., need to) have one or more (e.g., all) of these features to be able to perform model training. Otherwise, an NWDAF with a subset of the features, (e.g., S1) may (e.g., need to) collaborate with another NWDAF which trains ML models with S2. In examples, a VFL process between the two NWDAF may (e.g., need to) take place.

[0132] The PCF may provide individual features, for example, by including a feature ID and / or a list of feature IDs. A NWDAF may verify that the list of features (e.g., with the feature IDs) is eligible to be trained for a ML model for the analytic of interest. The NWDAF may respond to the PCF with a list of eligible features from the list provided (e.g., initially) by the PCF.

[0133] A NWDAF may (e.g., also) check feature availability in other NWDAFs, together with their capability to perform methods such as VFL, and / or the first NWDAF may select such NWDAFs to perform the requested model training.

[0134] FIG. 3 depicts a call flow diagram 300 illustrating an example NWDAF registration supported with feature identifiers (IDs), and / or conditions and / or attributes per analytics ID. For example, call flow diagram 300 shows an example procedure of NF registration of a network function (e.g., NWDAF and / or NWDAF that supports MTLF) to the NRF and / or additional information provided by the NWDAF.

[0135] At 302, the NWDAF may send a registration request to the NRF. The NWDAF may include (e.g., usual) information in the registration message, such as NF type, NF instance ID,fully qualified domain name (FQDN), internet protocol (IP) address, and / or the like. The NWDAF may include information related to the supported analytics ID, and / or the supported features (e.g., with feature ID) for each supported analytics ID. The NWDAF may (e.g., also) include which attributes and / or conditions it supports for each analytics ID and / or for one or more (e.g., all) analytics ID. For example, the NWDAF may include data privacy preservation support. At 304. the NRF may store the NWDAF profile. At 306, the NRF may send a registration response message to the NWDAF.

[0136] FIG. 4 depicts an example call flow diagram 400 illustrating an example of features set based machine learning (ML) model training and / or analytics production using vertical federated learning (VFL). Vertical federated learning may refer to a technique where two or more entities and / or nodes (e.g., a network function (NF) such as the NWDAF in a 5G network, and / or an application function (AF)), (e.g., collaboratively) train machine learning models, (e.g., a ML model used to infer observed service experience), sharing overlapping samples (e.g., a WTRU ID, a single network slice selection assistance information (S-NSSAI), and / or a tracking area) but using different data features (e.g.,, variables and / or attributes that make reference to a single property of the dataset, associated to the common sample these entities share. For example, a sample used to train the ML model to obtain observed service experience analytics may be a WTRUJD, and / or its attributes may refer, for example, to QoE metrics (e.g., a mean opinion score (MoS), and service experience contribution weight values (e.g., a value that indicates the relative importance of the QoE metric (e.g., MoS)).

[0137] For example, call flow diagram 400 illustrates a scenario where an analytics consumer (e.g., PCF) may interact with the NWDAF to request certain analytic ID, and / or where the PCF may provide features and / or attributes related information. Call flow diagram 400 may depict how the NWDAF may handle such requests.

[0138] At 402, the PCF may send a request to the NWDAF service consumer to obtain analytics output. The PCF may use the Nnwdaf_Analyticslnfo_Request service operation. The PCF may include the analytic ID for the analytics of interest. The PCF (e.g., also) may include a list of features, identified with feature IDs, that the PCF wants to be used for the ML model training for the analytic ID. If the PCF is requesting one or more (e.g., multiple) analytic IDs, for example, (e.g., then) the PCF may provide a different list of features for each analytic ID. In examples, the PCF may include feature IDs, f1 to f5 as requested features for the ML model trained for the analytic ID1 of interest. The PCF may (e.g., also) include a minimum number of features that are required for the ML model training. For example, the PCF may indicate that at least 3 of the features provided may (e.g., need to) be used for the ML training for analytic ID1.The PCF may (e.g., also) include attributes and / or conditions related to the ML model trained for the analytics ID. For example, if the PCF requires that the ML model for this analytic ID complies with data privacy preservation, the PCF may include an attribute field of value privacy compliance in the analytics request.

[0139] At 404, once the NWDAF service consumer receives the analytics request, for example, the NWDAF may interact with the NRF, using discovery service Nnrf_NFDiscovery_Request to obtain information about (e.g., possible) NWDAFs that support ML model training of the analytic of interest and / or using one or more of the features provided by the PCF. The NWDAF may (e.g., also) include certain conditions and / or attributes for the ML model training (e.g., data privacy preservation) if it was received from the PCF.

[0140] At 406, the NRF may provide the NWDAF service consumer with information about NWDAFs service producers that support features that can generate the desired (e.g., by the NWDAF consumer) analytics. The NRF may (e.g., also) provide the NWDAF IDs of such NWDAF producers.

[0141] In examples, the NRF may send a message to the NWDAF indicating that NWDAF2 supports analytic ID1 with available features f1 and f2, and / or NWDAF3 supports training ML model for analytic ID1 , with available features f3 and f4. The NRF may indicate that both NWDAFs can perform ML model training for the analytic of interest that satisfy the attributes of conditions provided by the NWDAF, or else, may indicate which attribute does each NWDAF support, for the analytic ID.

[0142] At 408, the NWDAF may consolidate the information received from the NRF regarding the analytic ID model training. The NWDAF may determine the list of available features that can be used to train an ML model for analytic ID, while verifying the conditions and / or attributes. In examples, the NWDAF may determine that an ML model can be trained by NWDAF2 and NWDAF3 collaboratively, using VFL for example, using features f1 to f4 (e.g., f5 may not be included).

[0143] At 410, the NWDAF may provide information about whether training ML model for analytic ID with that satisfies one or more of the attributes and / or using one or more of the features. In examples, the NWDAF may inform the PCF that a data privacy preserving ML model training for analytic ID1 may be possible with features f1-f4. The NWDAF may send this information using a request for confirmation to the PCF, including the ML model training related information.

[0144] At 412, the PCF may determine whether the provided elements regarding the ML model training for the analytic ID of interest are acceptable. For example, the PCF may check if thenumber of available features at the NWDAF is equal or more than a minimum number of features. In examples, the PCF may send a message to the NWDAF to inform the NWDAF that it accepts the set of available features provided by the NWDAF.

[0145] At 414, once the NWDAF receives the confirmation message from the PCF, for example, the NWDAF may perform NF selection for NWDAF2 and / or NWDAF3 to assist with ML model training for the analytic ID of interest. In examples, since feature f1 and f2 may be supported by NWDAF2 and / or features f3 and / or f4 may be supported by NWDAF3, and / or since an attribute with data privacy preservation may be provided, the NWDAF service consumer may determine to use a certain ML model training method. In examples, VFL may be used. In examples, once the NWDAF selects the NWDAF IDs, the NWDAF may configure the NWDAFs with suitable parameters and / or configuration to perform VFL. The NWDAFs may perform data collection to be able to train the ML model. The NWDAFs may perform the ML model training for the analytic ID of interest.

[0146] At 416, the NWDAF may send a Nnwdaf_Analyticlnfo_Request response to the PCF, to inform the PCF that a ML model trained with respect to the agreed upon features and under the specified conditions was successful, and / or may (e.g., eventually) provide the PCF with an ML model ID for the analytics. The NWDAF may (e.g., also) provide the analytics result request by the PCF (e.g., as described herein). The analytics ID may be determined (e.g., assumed) to have datasets that have flexibility in terms of the list of features to be used for the ML model training in order to produce the analytics.

[0147] The 5GS may (e.g., still) be configured with an association between the analytics ID and what possible features can be used, and / or the exhaustive feature Set. This may allow the 5GS to provide flexibility to the analytics consumers and / or ML model training while using one or more procedures / methods (e.g., common sense) with the possible features that can be relevant to certain analytics. In examples, the 5GS may provide flexibility in terms of the loss function and / or the output function expression. The 5GS may (e.g., further provide some flexibility in the output expression. In this regard, a NWDAF that trains a ML model for certain analytics, may use input from an analytics consumer and / or custom analytics consumer, to provide ML model training and / or inference based on (e.g., some) customization of in the expression of the output function. For example, in the case of observed service experience sustainability, one possible analytics output may be QoS sustainability multiplied by observed service experience.Additionally and / or alternatively, other expression of the analytics output may be used. The analytics consumer and / or customer analytics consumer may provide one or more (e.g., some)parameters such as weight, that may (e.g., sometimes) reflect the impact of certain features in the dataset features in the analytics output expression.

Claims

CLAIMS:

1. A network device comprising: a processor configured to: receive a first request message from a second network function to provide network analytics for observed service experience sustainability (SES); send a second request message to a third network function to obtain a machine learning (ML) model for an SES analytics identifier (ID) that is associated with the observed SES; receive a first response message from the third network function, the first response message comprising a trained ML model associated with the SES analytics ID; determine one or more analytics for the SES analytics ID using the trained ML model; and send a response message to the second network function, wherein the response message indicates the one or more analytics for the SES analytics ID, wherein the one or more analytics for the SES analytics ID comprises one or more predictions for each of a plurality of quality of service (QoS) parameters.

2. The network device of claim 1, wherein the one or more analytics for the SES analytics ID are determined based on one or more input parameters from the second network function.

3. The network device of claim 1, wherein the one or more analytics for the SES analytics ID comprises QoS sustainability and service experience.

4. The network device of claim 1, wherein the first request message comprises one or more of the SES analytics ID, a wireless transmit / receive unit (WTRU) ID, or a single network slice selection assistance information (S-NSSAI) value.

5. The network device of claim 1, wherein the third network function is selected based on a privacy compliance attribute provided in the first request message.

6. The network device of claim 1, wherein the network device comprises a network data analytics function (NWDAF).

7. The network device of claim 1, wherein the second network function comprises a policy control function (PCF) or a network exposure function (NEF), and the third network function comprises a NWDAF comprising model training logical function (MTLF).

8. The network device of claim 1, wherein the response message comprises Nnwdaf_MLModellnfo_Request response.

9. The network device of claim 1 , wherein the processor is further configured to: provide the determined analytics to an analytics consumer via a Nnwdaf_Analyticslnfo_Request response.

10. A method performed by a network device, the method comprising: receiving a first request message from a second network function to provide network analytics for observed service experience sustainability (SES); sending a second request message to a third network function to obtain a machine learning (ML) model for an SES analytics identifier (ID) that is associated with the observed SES; receiving a first response message from the third network function, the first response message comprising a trained ML model associated with the SES analytics ID; determining one or more analytics for the SES analytics ID using the trained ML model; and sending a response message to the second network function, wherein the response message indicates the one or more analytics for the SES analytics ID, wherein the one or more analytics for the SES analytics ID comprises one or more predictions for each of a plurality of quality of service (QoS) parameters.

11. The method of claim 10, wherein the one or more analytics for the SES analytics ID are determined based on one or more input parameters from the second network function.

12. The method of claim 10, wherein the one or more analytics for the SES analytics ID comprises QoS sustainability and service experience.

13. The method of claim 10, wherein the first request message comprises one or more of the SES analytics ID, a wireless transmit / receive unit (WTRU) ID, or a single network slice selection assistance information (S-NSSAI) value.

14. The method of claim 10, wherein the third network function is selected based on a privacy compliance attribute provided in the first request message.

15. The method of claim 10, wherein the network device comprises a network data analytics function (NWDAF).

16. The method of claim 10, wherein the second network function comprises a policy control function (PCF) or a network exposure function (NEF), and the third network function comprises a NWDAF comprising model training logical function (MTLF).

17. The method of claim 10, wherein the response message comprises Nnwdaf_MLModellnfo_Request response.

18. The method of claim 10, wherein the method further comprises: providing the determined analytics to an analytics consumer via a Nnwdaf_Analyticslnfo_Request response.

Images