Dynamic Radio Bearer Selection Associated with AI / ML Operations

Abstract

A wireless transmit / receive unit (WTRU) may receive information indicating a radio bearer of a first radio bearer type associated with the control plane, a radio bearer of a second radio bearer type associated with the user plane, and a condition associated with transmitting data associated with artificial intelligence / machine learning (AI / ML)-related operations. The WTRU may receive an indication to initiate the AI / ML-related operations. The WTRU may determine that data associated with the AI / ML-related operations is available. The WTRU may select a radio bearer type from the first radio bearer type and the second radio bearer type to use for transmitting the data based at least on the condition. The WTRU may transmit at least a portion of the data via a radio bearer of the selected radio bearer type.

Description

[Technical Field]

[0001] This application relates to dynamic radio bearer selection associated with AI / ML operations. [Background technology]

[0002] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims the benefit of U.S. Provisional Patent Application No. 63 / 421,818, filed November 2, 2022, the contents of which are incorporated herein by reference.

[0003] Mobile communications using wireless communications continues to evolve. The fifth generation of mobile communications radio access technology (RAT) is sometimes referred to as 5G New Radio (NR). Previous (legacy) generations of mobile communications RATs may be, for example, fourth generation (4G) Long Term Evolution (LTE). Summary of the Invention

[0004] Described herein are systems, methods, and means related to dynamic radio bearer selection for artificial intelligence / machine learning (AI / ML) operations.

[0005] In an example, a WTRU may include a processor configured to perform one or more actions. For example, the WTRU may perform AI / ML training or data collection for AI / ML training. The WTRU may receive information indicating a first radio bearer configuration indicating a radio bearer of a first radio bearer type associated with the control plane, a second radio bearer configuration indicating a radio bearer of a second radio bearer type associated with the user plane, a condition associated with transmitting data associated with an artificial intelligence / machine learning (AI / ML)-related operation, a first association between the condition and the first radio bearer type, and a second association between the condition and the second radio bearer type. The WTRU may receive an indication to initiate the AI / ML-related operation. The WTRU may determine that data associated with the AI / ML-related operation is available. The WTRU may select a radio bearer type to use to transmit the data from the first radio bearer type and the second radio bearer type based at least on the condition. The WTRU may transmit at least a portion of the data via a radio bearer of the selected radio bearer type.

[0006] The first radio bearer type may be a signaling radio bearer (SRB). The second radio bearer type may be a data radio bearer (DRB). The WTRU may receive an indication of a time to start training the AI ​​model and a deadline for transmitting data. The data may indicate that the AI ​​model has been trained or at least one of parameters associated with the training. When it is time to start training the AI ​​model, the WTRU may perform the AI ​​training. At least a portion of the data may be transmitted according to a deadline threshold.

[0007] The AI / ML-related operations may include training an AI / ML model. The WTRU may receive an indication of a time to start training the AI / ML model and a deadline for transmitting data. The data may indicate at least one of that the AI / ML model has been trained or parameters associated with the training. The WTRU may determine a first estimated transmission time of the data based on the first association and a second estimated transmission time of the data based on the second association. Selecting a radio bearer type to use for transmitting the data from the first radio bearer type and the second radio bearer type based at least on the condition may include selecting the radio bearer type based on whether one or more of the first estimated transmission time or the second estimated transmission time meets a deadline threshold, and performing the AI / ML training at the time to start training the AI / ML model. At least a portion of the data may be transmitted in accordance with the deadline threshold.

[0008] The AI / ML-related operations can include collecting data, and transmitting at least a portion of the data over a radio bearer of the selected radio bearer type can include transmitting the data to a network entity for training an AI / ML model.

[0009] The WTRU may select a radio bearer of the selected radio bearer type from the first radio bearer and the second radio bearer of the selected radio bearer type based on the uplink buffer levels. The WTRU may select the first radio bearer if the combined uplink buffer level of the first radio bearer and the second radio bearer is above a threshold. The WTRU may select the second radio bearer if the combined uplink buffer level of the first radio bearer and the second radio bearer is below a threshold. The WTRU may select the first radio bearer if the uplink buffer level of the first radio bearer is below the uplink buffer level of the second radio bearer. The WTRU may select the second radio bearer if the uplink buffer level of the second radio bearer is below the uplink buffer level of the first radio bearer.

[0010] The WTRU may select a first radio bearer of a selected radio bearer type as a radio bearer of the selected radio bearer type when radio conditions of the serving cell are above a threshold, and may select a second radio bearer of the selected radio bearer type as a radio bearer of the selected radio bearer type when radio conditions of the serving cell are below a threshold.

[0011] The WTRU may select a radio bearer of the selected radio bearer type from a first radio bearer and a second radio bearer of the selected radio bearer type based on the payload of the data. The WTRU may select the first radio bearer if the payload size of the data is above a threshold. The WTRU may select the second radio bearer if the payload size of the data is below a threshold. The WTRU may select the first radio bearer if the payload type of the data is the first payload type. The WTRU may select the second radio bearer if the payload type of the data is the second payload type.

[0012] The WTRU may select a first radio bearer of the selected radio bearer type as a radio bearer of the selected radio bearer type if a data reliability or security criterion is above a threshold, and may select a second radio bearer of the selected radio bearer type as a radio bearer of the selected radio bearer type if the data reliability or security criterion is below a threshold.

[0013] The radio bearer of the selected radio bearer type may be a first radio bearer of the selected radio bearer type. The at least some of the data may be the first portion of the data. The WTRU may select a second radio bearer of the selected radio bearer type. The WTRU may transmit the second portion of the data over the second radio bearer of the selected radio bearer type.

[0014] The WTRU may determine a radio bearer for transmitting data associated with the AI / ML training based on the transmission parameters. The WTRU may transmit the data on the determined radio bearer.

[0015] The WTRU may receive configuration information associated with training the AI / ML model. An indication of when to start training the AI / ML model may be received. The WTRU may receive an indication of a deadline for transmitting data. The data may indicate the trained AI / ML model or metadata associated with the training. The data may be transmitted according to the deadline.

[0016] The transmission parameters may include one or more of the following: the time remaining until the deadline, the current radio conditions between the WTRU and the serving cell, the amount of data to be transmitted, the security requirements for the data, or the current uplink buffer level. [Brief explanation of the drawings]

[0017] Additionally, like reference numbers in the figures refer to like elements.

[0018] [Figure 1A] FIG. 1 is a system diagram illustrating an example communication system in which one or more disclosed embodiments may be implemented. [Figure 1B] 1B is a system diagram illustrating an example wireless transmit / receive unit (WTRU) that may be used within the communications system shown in FIG. 1A, according to an embodiment. [Figure 1C] 1B is a system diagram illustrating an example radio access network (RAN) and an example core network (CN) that may be used within the communication system shown in FIG. 1A, according to an embodiment. [Figure 1D] 1B is a system diagram illustrating a further exemplary RAN and a further exemplary CN that may be used within the communications system shown in FIG. 1A, according to an embodiment. [Figure 2] FIG. 1 illustrates an example of high-level federated learning interactions between participants and a central AI server. [Figure 3] FIG. 1 illustrates an example functional relationship between multiple agents and multiple collection devices. [Figure 4] FIG. 1 illustrates an exemplary input data disturbance scenario. [Figure 5] 10 is a diagram of an example call flow illustrating a WTRU selecting / determining whether to use the control plane or the user plane and on which radio bearer to transmit data. [Figure 6] FIG. 1 illustrates an exemplary timeline for data transmission. [Figure 7] 10 is a diagram of an example call flow illustrating a WTRU selecting / determining a radio bearer for transmitting data. DETAILED DESCRIPTION OF THE INVENTION

[0019] 1A illustrates an exemplary communication system 100 in which one or more disclosed embodiments may be implemented. The communication system 100 may be a multiple-access system that provides content, such as voice, data, video, messaging, broadcasts, and the like, to multiple wireless users. The communication system 100 may enable multiple wireless users to access such content through sharing of system resources, including wireless bandwidth. For example, the communication system 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-tailed unique word DFT spread OFDM (ZT UW DTS-s OFDM), unique word OFDM (UW-OFDM), resource block filtered OFDM, and filter bank multicarrier (FBMC).

[0020] 1A, communications system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, RANs 104 / 113, CNs 106 / 115, public switched telephone networks (PSTNs) 108, the Internet 110, and other networks 112, although it will be understood that the disclosed embodiments contemplate any number of WTRUs, base stations, networks, and / or network elements. Each of 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 “STA,” may be configured to transmit and / or receive wireless signals and may include user equipment (UE), a mobile station, a fixed or mobile subscriber unit, a subscription-based unit, a pager, a cellular phone, 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 (IoT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and application (e.g., remote surgery), an industrial device and application (e.g., robots and / or other wireless devices operating in an industrial and / or automated processing chain context), a consumer electronic device, and a device operating in a commercial and / or industrial wireless network. Any of the WTRUs 102a, 102b, 102c, and 102d may be referred to interchangeably as a UE.

[0021] The communications system 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 communications networks, such as the CN 106 / 115, the Internet 110, and / or other networks 112. By way of example, the base stations 114a, 114b may be a base transceiver station (BTS), a Node-B, an eNode B, a Home Node B, a Home eNod B, a gNB, an NR NodeB, a site controller, an access point (AP), a wireless router, etc. While the base stations 114a, 114b are each shown as a single element, it will be understood that the base stations 114a, 114b may include any number of interconnected base stations and / or network elements.

[0022] 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 base station 114b may be configured to transmit and / or receive wireless signals on one or more carrier frequencies, sometimes referred to as a cell (not shown). These frequencies may be within the licensed spectrum, the unlicensed spectrum, or a combination of the licensed and unlicensed spectrum. A cell may provide coverage for wireless services in a particular geographic area, which may be relatively fixed or may change over time. A cell may be further 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 transceiver for each sector of the cell. In an embodiment, the base station 114a may employ multiple-input multiple-output (MIMO) technology and 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.

[0023] 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 communications 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).

[0024] More specifically, as noted above, the communication system 100 may be a multiple-access system and may employ one or more channel access schemes, such as CDMA, TDMA, FDMA, OFDMA, and SC-FDMA. For example, the base station 114a and the WTRUs 102a, 102b, and 102c in the RAN 104 / 113 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).

[0025] 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).

[0026] In an embodiment, the base station 114a and the WTRUs 102a, 102b, 102c may implement a radio technology such as New Radio (NR) radio access, which may establish the air interface 116 using NR.

[0027] 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 jointly implement LTE and NR radio access, e.g., using a dual connectivity (DC) principle. Thus, the air interface utilized by the 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., eNBs and gNBs).

[0028] In other embodiments, the base station 114a and the WTRUs 102a, 102b, 102c may implement wireless technologies such as IEEE 802.11 (i.e., Wireless Fidelity (Wi-Fi)), IEEE 802.16 (i.e., Worldwide Interoperability for Microwave Access (WiMAX)), CDMA2000, CDMA2000 1X, CDMA2000 EV-DO, Interim Standard 2000 (IS-2000), Interim Standard 95 (IS-95), Interim Standard 856 (IS-856), Global System for Mobile Communications (GSM), Enhanced Data Rates for GSM Evolution (EDGE), and GSM EDGE (GERAN).

[0029] 1A may be, for example, a wireless router, a Home Node B, a Home eNode B, or an access point and may utilize any suitable RAT for facilitating wireless connectivity within a localized area, such as a business, a home, a vehicle, a campus, an industrial facility, an air corridor (e.g., for use by drones), and a road. In one embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.11 to establish a wireless local area network (WLAN). In an embodiment, the base station 114b and the WTRUs 102c, 102d may implement a radio technology such as IEEE 802.15 to establish a wireless personal area network (WPAN). In yet another embodiment, the base station 114b and the WTRUs 102c, 102d may utilize a cellular-based RAT (e.g., WCDMA, CDMA2000, GSM, LTE, LTE-A, LTE-A Pro, NR, etc.) to establish a picocell or femtocell. 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.

[0030] The RAN 104 / 113 can communicate with the CN 106 / 115, which may be any type of network configured to provide voice, data, application, and / or Voice over Internet Protocol (VoIP) services to one or more of the WTRUs 102a, 102b, 102c, 102d. The data may have varying quality of service (QoS) requirements, such as different throughput, latency, error resilience, reliability, data throughput, and mobility requirements. The CN 106 / 115 may provide call control, billing services, mobile location services, prepaid calling, Internet connectivity, video distribution, etc., and / or perform high-level security functions such as user authentication. Although not shown in FIG. 1A , it will be understood that the RAN 104 / 113 and / or the CN 106 / 115 may communicate directly or indirectly with other RANs employing 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 NR radio technology, the CN 106 / 115 may also communicate with another RAN (not shown) employing GSM, UMTS, CDMA2000, WiMAX, E-UTRA, or WiFi radio technology.

[0031] 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 other networks 112. The PSTN 108 may include a circuit-switched telephone network providing 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 Transmission Control Protocol (TCP), User Datagram Protocol (UDP), and / or Internet Protocol (IP) in the TCP / IP Internet protocol suite. The network 112 may include wired and / or wireless communication networks owned and / or operated by other service providers. For example, the network 112 may include another CN connected to one or more RANs that may employ the same RAT as the RAN 104 / 113 or a different RAT.

[0032] 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 a base station 114a that may employ cellular-based wireless technology and a base station 114b that may employ IEEE 802.11 wireless technology.

[0033] 1B is a system diagram illustrating an example WTRU 102. As shown in FIG. 1B, the WTRU 102 may include, among other things, 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. It will be understood that the WTRU 102 may include any sub-combination of the above elements while remaining consistent with an embodiment.

[0034] The processor 118 may be a general-purpose processor, a special-purpose processor, a conventional processor, a digital signal processor (DSP), multiple microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) circuit, any other type of integrated circuit (IC), a state machine, etc. 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. 1B depicts the processor 118 and the transceiver 120 as separate components, it will be understood that the processor 118 and the transceiver 120 may be incorporated together, for example, in an electronic package or chip.

[0035] The transmit / receive element 122 may be configured to transmit signals to or receive signals from a base station (e.g., 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, for example, IR signals, UV signals, or visible light signals. In yet another embodiment, the transmit / receive element 122 may be configured to transmit and / or receive both RF signals and light signals. It will be understood that the transmit / receive element 122 may be configured to transmit and / or receive any combination of wireless signals.

[0036] 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.

[0037] The transceiver 120 may be configured to modulate signals to be transmitted by the transmit / receive element 122 and demodulate signals received by the transmit / receive element 122. As mentioned above, the WTRU 102 may have multi-mode capabilities. Thus, the transceiver 120 may include multiple transceivers to enable the WTRU 102 to communicate via multiple RATs, such as, for example, NR and IEEE 802.11.

[0038] The processor 118 of the WTRU 102 may be coupled to and may receive user input data from a speaker / microphone 124, a keypad 126, and / or a display / touchpad 128 (e.g., a liquid crystal display (LCD) display unit or an 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. Additionally, the processor 118 may access information from and store data in any type of suitable memory, such as non-removable memory 130 and / or 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, etc. In other embodiments, the processor 118 may access information in memory that is not physically located on the WTRU 102, such as on a server or home computer (not shown), and may store data in that memory.

[0039] The processor 118 may receive power from the power source 134 and may be configured to distribute and / or control power to 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 batteries (e.g., nickel-cadmium (NiCd), nickel-zinc (NiZn), nickel-metal hydride (NiMH), lithium-ion (Li-ion), etc.), solar cells, fuel cells, etc.

[0040] The processor 118 may also be coupled to a GPS chipset 136 that 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 place of information from the GPS chipset 136, the WTRU 102 may receive location information from base stations (e.g., base stations 114a, 114b) over the air interface 116 and / or determine its location based on the timing of signals 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.

[0041] 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 electronic compass, a satellite transceiver, a digital camera (for photos and / or videos), a universal serial bus (USB) port, a vibration device, a television transceiver, a hands-free headset, a Bluetooth module, a frequency modulation (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, etc. The peripherals 138 may include one or more sensors, which 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 touch sensor, a magnetometer, a barometer, a gesture sensor, a biometric sensor, and / or a humidity sensor.

[0042] 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 a particular subframe for both the UL (e.g., for transmission) and the downlink (e.g., for reception)) may be parallel and / or simultaneous. The full-duplex radio may include an interference management unit for reducing and / or substantially eliminating self-interference via hardware (e.g., a choke) or via signal processing by a processor (e.g., by a separate processor (not shown) or the processor 118). In an embodiment, the WTRU 102 may include a half-duplex radio, for which transmission and reception of some or all of the signals (e.g., associated with a particular subframe for either the UL (e.g., for transmission) or the downlink (e.g., for reception)) may be parallel and / or simultaneous.

[0043] 1C is a system diagram illustrating the RAN 104 and the CN 106 according to an embodiment. As mentioned above, the RAN 104 may employ E-UTRA radio technology to communicate with the WTRUs 102a, 102b, 102c over the air interface 116. The RAN 104 may also communicate with the CN 106.

[0044] The RAN 104 may include eNode-Bs 160a, 160b, and 160c, although it will be understood that the RAN 104 may include any number of eNode-Bs while remaining consistent with an embodiment. The eNode-Bs 160a, 160b, and 160c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, and 102c over the air interface 116. In one embodiment, the eNode-Bs 160a, 160b, and 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.

[0045] 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, and scheduling of users in the UL and / or DL, etc. As shown in FIG. 1C, the eNode-Bs 160a, 160b, 160c may communicate with one another via an X2 interface.

[0046] 1C may include a mobility management entity (MME) 162, a serving gateway (SGW) 164, and a packet data network (PDN) gateway (i.e., PGW) 166. While each of the above elements is shown as part of the CN 106, it will be understood that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0047] 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 act 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 initial attach of the WTRUs 102a, 102b, 102c, etc. 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.

[0048] The SGW 164 may be connected to each of the eNode Bs 160a, 160b, 160c in the RAN 104 via an S1 interface. The SGW 164 may generally route and forward user data packets to / from the WTRUs 102a, 102b, 102c. The SGW 164 may also perform other functions, such as anchoring the user plane during inter-eNode B handovers, triggering paging when DL data is available to the WTRUs 102a, 102b, 102c, and managing and storing the context of the WTRUs 102a, 102b, 102c.

[0049] The SGW 164 may be connected to a PGW 166, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, to facilitate communication between the WTRUs 102a, 102b, 102c and IP-enabled devices.

[0050] 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 landline communications devices. For example, the CN 106 may include or communicate with an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server) that acts as an interface between the CN 106 and the PSTN 108. The CN 106 may also provide the WTRUs 102a, 102b, 102c with access to other networks 112, which may include other wired and / or wireless networks owned and / or operated by other service providers.

[0051] Although the WTRUs are described in Figures 1A-1D as wireless terminals, it is contemplated that in certain representative embodiments such terminals may use a wired communication interface (e.g., temporarily or permanently) with a communication network.

[0052] In an exemplary embodiment, the other network 112 may be a WLAN.

[0053] A WLAN in infrastructure basic service set (BSS) mode may have an access point (AP) for the BSS and one or more stations (STAs) associated with the AP. The AP may have access or interface to a distribution system (DS) or another type of wired / wireless network that carries traffic within and / or outside the BSS. Traffic to a STA originating from outside the BSS may arrive through the AP and be delivered to the STA. Traffic originating from a STA to a destination outside the BSS may be sent to the AP to be delivered to the respective destination. Traffic between STAs within the BSS may be sent through the AP; for example, a source STA may send traffic to the AP, and the AP may deliver traffic to the destination STA. Traffic between STAs within the BSS may be considered and / or referred to as peer-to-peer traffic. Peer-to-peer traffic may be sent (e.g., directly) between a source STA and a destination STA using direct link setup (DLS). In certain representative embodiments, the DLS may use 802.11e DLS or 802.11z tunneled DLS (TDLS). A WLAN using Independent BSS (IBSS) mode may not have an AP, and STAs within or using the IBSS (e.g., all of the STAs) may communicate directly with each other. IBSS mode communication is sometimes referred to herein as "ad hoc" mode communication.

[0054] When using the 802.11ac infrastructure mode of operation or a similar mode of operation, an AP can transmit beacons on a fixed channel, such as a primary channel. The primary channel may be a fixed width (e.g., 20 MHz bandwidth) or may be dynamically set by signaling. The primary channel may be the operating channel of the BSS and may be used by STAs to establish a connection with the AP. In certain exemplary embodiments, for example, in an 802.11 system, Carrier Sense Multiple Access with Collision Avoidance (CSMA / CA) may be implemented. In CSMA / CA, STAs (e.g., all STAs), including the AP, can sense the primary channel. If a particular STA senses / detects and / or determines that the primary channel is busy, the particular STA may back off. One STA (e.g., only one station) can transmit in a given BSS at any given time.

[0055] High-throughput (HT) STAs may use 40 MHz wide channels for communication, for example, by combining a primary 20 MHz channel with adjacent or non-adjacent 20 MHz channels to form a 40 MHz wide channel.

[0056] A very high throughput (VHT) STA can support 20 MHz, 40 MHz, 80 MHz, and / or 160 MHz wide channels. 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 eight contiguous 20 MHz channels or by combining two non-contiguous 80 MHz channels, sometimes referred to as an 80+80 configuration. In the 80+80 configuration, after channel coding, the data may be passed through a segment parser that can split the data into two streams. Inverse fast Fourier transform (IFFT) processing and time-domain processing may be performed separately for each stream. The streams may be mapped to two 80 MHz channels, and the data may be transmitted by the transmitting STA. At the receiver of the receiving STA, the above operations for the 80+80 configuration may be reversed, and the combined data may be sent to the medium access control (MAC) layer.

[0057] Sub-1 GHz operating modes are supported by 802.11af and 802.11ah. 802.11af and 802.11ah reduce the channel operating bandwidth and carriers compared to those used in 802.11n and 802.11ac. 802.11af supports 5 MHz, 10 MHz, and 20 MHz bandwidths in the TV White Space (TVWS) spectrum, while 802.11ah supports 1 MHz, 2 MHz, 4 MHz, 8 MHz, and 16 MHz bandwidths using non-TVWS spectrum. According to a representative embodiment, 802.11ah can support meter-type control / machine-type communication, such as MTC devices, in macro coverage areas. MTC devices may have specific capabilities, including, for example, specific bandwidths and / or limited bandwidth support (e.g., support only that bandwidth). MTC devices may include batteries with above-threshold battery life (e.g., maintaining a very long battery life).

[0058] WLAN systems capable of supporting multiple channels and channel bandwidths, such as 802.11n, 802.11ac, 802.11af, and 802.11ah, include a channel that may be designated as a 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 the STA that supports the smallest bandwidth operating mode among all STAs operating in the BSS. In an 802.11ah example, the primary channel may be 1 MHz wide for a STA (e.g., an MTC-type device) that supports (e.g., only supports) the 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) setting may depend on the status of the primary channel. If the primary channel is busy, for example due to a STA (that only supports 1 MHz operating mode) transmitting to the AP, the entire available frequency band may be considered busy, even though most of the frequency band may remain idle and available.

[0059] In the United States, the available frequency bands that may be used by 802.11ah are 902MHz to 928MHz. In South Korea, the available frequency bands are 917.5MHz to 923.5MHz. In Japan, the available frequency bands are 916.5MHz to 927.5MHz. The total bandwidth available for 802.11ah is 6MHz to 26MHz depending on the country code.

[0060] 1D is a system diagram illustrating the RAN 113 and the CN 115 according to an embodiment. As described above, the RAN 113 may employ NR radio technology to communicate with the WTRUs 102a, 102b, and 102c over the air interface 116. The RAN 113 may also communicate with the CN 115.

[0061] The RAN 113 may include gNBs 180a, 180b, and 180c, although it will be understood that the RAN 113 may include any number of gNBs while remaining consistent with an embodiment. The gNBs 180a, 180b, and 180c may each include one or more transceivers for communicating with the WTRUs 102a, 102b, and 102c over the air interface 116. In one embodiment, the gNBs 180a, 180b, and 180c may implement MIMO technology. For example, the gNBs 180a and 180b may utilize beamforming to transmit signals to and / or receive signals from the gNBs 180a, 180b, and 180c. Thus, the gNB 180a may, for example, use multiple antennas to transmit wireless signals to and / or receive wireless signals from the WTRU 102a. In an embodiment, the gNBs 180a, 180b, and 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 an unlicensed spectrum, and the remaining component carriers may be on a licensed spectrum. In an embodiment, the gNBs 180a, 180b, and 180c may implement coordinated multipoint (CoMP) technology. For example, the WTRU 102a may receive coordinated transmissions from the gNBs 180a and 180b (and / or 180c).

[0062] The WTRUs 102a, 102b, 102c may communicate with the gNBs 180a, 180b, 180c using transmissions associated with 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 the gNBs 180a, 180b, 180c using subframes or transmission time intervals (TTIs) of various or scalable lengths (e.g., including varying numbers of OFDM symbols and / or lasting for varying lengths of absolute time).

[0063] 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 a standalone configuration, the WTRUs 102a, 102b, 102c can communicate with the gNBs 180a, 180b, 180c without accessing any other RANs (e.g., eNode-Bs 160a, 160b, 160c, etc.). In a standalone configuration, the WTRUs 102a, 102b, 102c can utilize one or more of the gNBs 180a, 180b, 180c as mobility anchor points. In a standalone configuration, the WTRUs 102a, 102b, 102c can communicate with the gNBs 180a, 180b, 180c using signals in unlicensed bands. In a non-standalone configuration, the WTRUs 102a, 102b, 102c may communicate / connect with the gNBs 180a, 180b, 180c while also communicating / connecting with other RANs, such as eNode-Bs 160a, 160b, 160c. For example, the WTRUs 102a, 102b, 102c may implement a DC principle to communicate with one or more gNBs 180a, 180b, 180c and one or more eNode-Bs 160a, 160b, 160c substantially simultaneously. In a non-standalone configuration, the eNode-Bs 160a, 160b, 160c may act as mobility anchors for the WTRUs 102a, 102b, 102c, and the gNBs 180a, 180b, 180c may provide additional coverage and / or throughput for serving the WTRUs 102a, 102b, 102c.

[0064] 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 for network slicing, dual connectivity, interworking between NR and E-UTRA, routing of user plane data to User Plane Functions (UPFs) 184a, 184b, and routing of control plane information to Access and Mobility Management Functions (AMFs) 182a, 182b, etc. As shown in FIG. 1D , the gNBs 180a, 180b, 180c may communicate with each other via an Xn interface.

[0065] 1D 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 above elements is shown as part of the CN 115, it will be understood that any of these elements may be owned and / or operated by an entity other than the CN operator.

[0066] 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 act as a control node. For example, the AMF 182a, 182b may be responsible for authenticating users of the WTRUs 102a, 102b, 102c, supporting network slicing (e.g., handling different protocol data unit (PDU) sessions with different requirements), selecting a particular SMF 183a, 183b, managing registration areas, terminating NAS signaling, and mobility management. Network slicing may be used by the AMF 182a, 182b to customize CN support for the WTRUs 102a, 102b, 102c based on the type of service being utilized by the 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 High-Capacity Mobile Broadband (eMBB) access, and / or services for Machine-Type Communications (MTC) access, etc. 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.

[0067] The SMFs 183a and 183b may be connected to the AMFs 182a and 182b in the CN 115 via an N11 interface. The SMFs 183a and 183b may also be connected to the UPFs 184a and 184b in the CN 115 via an N4 interface. The SMFs 183a and 183b may select and control the UPFs 184a and 184b and configure the routing of traffic through the UPFs 184a and 184b. The SMFs 183a and 183b may also perform other functions, such as managing and assigning UE IP addresses, managing PDU sessions, controlling policy enforcement and QoS, and providing downlink data notifications. PDU session types may be IP-based, non-IP-based, Ethernet-based, etc.

[0068] The UPFs 184a, 184b may be connected to one or more of the gNBs 180a, 180b, 180c in the RAN 113 via an N3 interface, which may provide the WTRUs 102a, 102b, 102c with access to packet-switched networks, such as the Internet 110, to facilitate communications between the WTRUs 102a, 102b, 102c and IP-enabled devices. The UPFs 184a, 184b may also 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, and providing mobility anchoring.

[0069] The CN 115 may facilitate communication with other networks. For example, the CN 115 may include or communicate with an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server) that interfaces between the CN 115 and the PSTN 108. The CN 115 may also provide the WTRUs 102a, 102b, 102c with access to other networks 112, which may include other wired and / or wireless networks owned and / or operated by other service providers. In one embodiment, the WTRUs 102a, 102b, 102c may be connected to local data networks (DNs) 185a, 185b through the UPFs 184a, 184b via an N3 interface to the UPFs 184a, 184b and an N6 interface between the UPFs 184a, 184b and the DNs 185a, 185b.

[0070] 1A-1D and the corresponding description thereof, one or more or all of the functions described herein with respect to one or more of the WTRUs 102a-d, base stations 114a-b, eNode-Bs 160a-c, MME 162, SGW 164, PGW 166, gNBs 180a-c, AMFs 182a-b, UPFs 184a-b, SMFs 183a-b, DNs 185a-b, and / or any other devices 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 functionality.

[0071] The emulation device may be designed to implement one or more tests of other devices in a lab environment and / or an operator network environment. For example, one or more emulation devices may perform one or more or all functions while fully or partially implemented and / or deployed as part of a wired and / or wireless communications network to test other devices in the communications network. One or more emulation devices may perform one or more or all functions while temporarily implemented / deployed as part of a wired and / or wireless communications network. The emulation device may be directly coupled to another device for testing and / or may perform testing using over-the-air wireless communications.

[0072] The one or more emulation devices may perform one or more functions, inclusive, without being implemented / deployed as part of a wired and / or wireless communications network. For example, the emulation devices may be utilized in test labs and / or test scenarios in undeleted (e.g., test) wired and / or wireless communications networks to implement testing of one or more components. The one or more emulation devices may be test equipment. Direct RF coupling and / or wireless communication via RF circuitry (which may include, e.g., one or more antennas) may be used by the emulation devices to transmit and / or receive data.

[0073] Described herein are systems, methods, and means related to dynamic radio bearer selection for artificial intelligence / machine learning (AI / ML) operations.

[0074] Described herein are systems, methods, and means related to dynamic radio bearer selection for artificial intelligence / machine learning (AI / ML) operations.

[0075] In an example, a WTRU may include a processor configured to perform one or more actions. For example, the WTRU may perform AI / ML training or data collection for AI / ML training. The WTRU may receive information indicating a first radio bearer configuration indicating a radio bearer of a first radio bearer type associated with the control plane, a second radio bearer configuration indicating a radio bearer of a second radio bearer type associated with the user plane, a condition associated with transmitting data associated with an artificial intelligence / machine learning (AI / ML)-related operation, a first association between the condition and the first radio bearer type, and a second association between the condition and the second radio bearer type. The WTRU may receive an indication to initiate the AI / ML-related operation. The WTRU may determine that data associated with the AI / ML-related operation is available. The WTRU may select a radio bearer type to use to transmit the data from the first radio bearer type and the second radio bearer type based at least on the condition. The WTRU may transmit at least a portion of the data via a radio bearer of the selected radio bearer type.

[0076] The first radio bearer type may be a signaling radio bearer (SRB). The second radio bearer type may be a data radio bearer (DRB). The WTRU may receive an indication of a time to start training the AI ​​model and a deadline for transmitting data. The data may indicate that the AI ​​model has been trained or at least one of parameters associated with the training. When it is time to start training the AI ​​model, the WTRU may perform the AI ​​training. At least a portion of the data may be transmitted according to a deadline threshold.

[0077] The AI / ML-related operations may include training an AI / ML model. The WTRU may receive an indication of a time to start training the AI / ML model and a deadline for transmitting data. The data may indicate at least one of that the AI / ML model has been trained or parameters associated with the training. The WTRU may determine a first estimated transmission time of the data based on the first association and a second estimated transmission time of the data based on the second association. Selecting a radio bearer type to use for transmitting the data from the first radio bearer type and the second radio bearer type based at least on the condition may include selecting the radio bearer type based on whether one or more of the first estimated transmission time or the second estimated transmission time meets a deadline threshold, and performing the AI / ML training at the time to start training the AI / ML model. At least a portion of the data may be transmitted in accordance with the deadline threshold.

[0078] The AI / ML-related operations can include collecting data, and transmitting at least a portion of the data over a radio bearer of the selected radio bearer type can include transmitting the data to a network entity for training an AI / ML model.

[0079] The WTRU may select a radio bearer of the selected radio bearer type from the first radio bearer and the second radio bearer of the selected radio bearer type based on the uplink buffer levels. The WTRU may select the first radio bearer if the combined uplink buffer level of the first radio bearer and the second radio bearer is above a threshold. The WTRU may select the second radio bearer if the combined uplink buffer level of the first radio bearer and the second radio bearer is below a threshold. The WTRU may select the first radio bearer if the uplink buffer level of the first radio bearer is below the uplink buffer level of the second radio bearer. The WTRU may select the second radio bearer if the uplink buffer level of the second radio bearer is below the uplink buffer level of the first radio bearer.

[0080] The WTRU may select a first radio bearer of a selected radio bearer type as a radio bearer of the selected radio bearer type when radio conditions of the serving cell are above a threshold, and may select a second radio bearer of the selected radio bearer type as a radio bearer of the selected radio bearer type when radio conditions of the serving cell are below a threshold.

[0081] The WTRU may select a radio bearer of the selected radio bearer type from a first radio bearer and a second radio bearer of the selected radio bearer type based on the payload of the data. The WTRU may select the first radio bearer if the payload size of the data is above a threshold. The WTRU may select the second radio bearer if the payload size of the data is below a threshold. The WTRU may select the first radio bearer if the payload type of the data is the first payload type. The WTRU may select the second radio bearer if the payload type of the data is the second payload type.

[0082] The WTRU may select a first radio bearer of the selected radio bearer type as a radio bearer of the selected radio bearer type if a data reliability or security criterion is above a threshold, and may select a second radio bearer of the selected radio bearer type as a radio bearer of the selected radio bearer type if the data reliability or security criterion is below a threshold.

[0083] The radio bearer of the selected radio bearer type may be a first radio bearer of the selected radio bearer type. The at least some of the data may be the first portion of the data. The WTRU may select a second radio bearer of the selected radio bearer type. The WTRU may transmit the second portion of the data over the second radio bearer of the selected radio bearer type.

[0084] The WTRU may determine a radio bearer for transmitting data associated with the AI / ML training based on the transmission parameters. The WTRU may transmit the data on the determined radio bearer.

[0085] The WTRU may receive configuration information associated with training the AI / ML model. An indication of when to start training the AI / ML model may be received. The WTRU may receive an indication of a deadline for transmitting data. The data may indicate the trained AI / ML model or metadata associated with the training. The data may be transmitted according to the deadline.

[0086] The transmission parameters may include one or more of the following: the time remaining until the deadline, the current radio conditions between the WTRU and the serving cell, the amount of data to be transmitted, the security requirements for the data, or the current uplink buffer level.

[0087] An exemplary artificial intelligence / machine learning (AI / ML) service (e.g., in a 5G system) is provided herein. A wireless transmit / receive unit (WTRU) can interact with a network function (NF) (e.g., an AI / ML function (AIMLF) or a federated learning function (FLF)) in a 5G core (5GC) network. The WTRU can interact with an application server (AS) and / or application function (AF) through a user plane (UP) (e.g., via a user plane function (UPF)) or a control plane (CP) (e.g., via non-access stratum (NAS) signaling). In the case of a UP model, the WTRU can interact (e.g., at least interact) with the AS and / or AF via a data radio bearer (DRB). The DRB can be established between the WTRU and a next-generation radio access network (NG-RAN) over the Uu air interface. In the CP model, the WTRU may use a signaling radio bearer (SRB) to carry NAS or radio resource control (RRC) messages.

[0088] Exemplary AI / ML metadata and operations are provided herein. The AI / ML metadata may include model topology, model weights, training completion time windows, and / or other AI / ML-specific parameters (e.g., loss function, entropy, prediction accuracy, etc.). The AI / ML operations may be categorized into (i) model distribution, (ii) partitioning of models among AI / ML endpoints, and (iii) federated learning.

[0089] An exemplary federated learning (FL) may be provided. In the FL mode, a central AI server may train a global model. For example, the AI ​​server may train the global model by combining the local models trained by each participant (e.g., WTRU) based on a model averaging technique. The WTRU may perform local model training within each training cycle (e.g., based on a model downloaded from a centralized AI server using local data). The WTRU may distribute the training results (e.g., gradients of a deep neural network (DNN)) to the centralized AI server (e.g., over a 5G uplink channel) (e.g., upon completion of local model training). The centralized AI server may aggregate the gradients (e.g., model weights) from the WTRUs. The centralized AI server may update the global model (e.g., using the aggregated gradients). Another training cycle (e.g., the next training cycle) may begin. For example, the AI ​​server may distribute the updated global model to the WTRUs (e.g., over a 5G downlink channel). Figure 2 shows high-level FL interactions between participants (e.g., WTRUs) and a central AI server over a 5G system.

[0090] FL training over wireless communication may differ from FL training in a data center (e.g., participants such as WTRUs may have highly variable conditions in terms of available computational and network resources). WTRUs may not be homogeneous. WTRUs may have different capabilities (e.g., in terms of computational resources, network resources, and / or supported ML frameworks). It may not be efficient for a centralized AI server to include all participants (e.g., WTRUs) in a training session. A member selection mechanism may be used (e.g., before the start of each training cycle). If conditions (e.g., device computational resources and / or wireless channel conditions) do not change, WTRU reselection and training (re)configuration may not be performed for every training cycle. Different WTRUs may be (re)selected over time (e.g., to achieve global training with diverse datasets).

[0091] Features associated with synchronous FL (SFL) are provided herein. SFL may be referred to as a variant of FL. SFL may have a latency budget (e.g., all participants finish uploading their respective training results within a predefined time window, as shown in FIG. 6). For example, all WTRUs participating in a training session may finish uploading their respective training results within a predefined latency budget. For example, in an uncompressed FL for image recognition, the uplink transmission deadline may be approximately between 1 and 3 seconds, as shown in Table 1.

[0092] [Table 1]

[0093] Exemplary multi-agent-multi-device ML operations are provided herein: When there is some level of impediment to data collection and / or transfer (e.g., lack of network and / or computational resources, temporary failures, etc.), multi-agent-multi-device ML operations with large data sizes may be used.

[0094] FIG. 3 illustrates an example functional relationship between multiple agents (denoted A1...An) and multiple collection devices (e.g., WTRUs denoted M1...Mk). The devices can perform ML operations. For example, functional partitioning may be possible between the devices and one or more learning agents. An agent (e.g., each agent) can interact (e.g., collaboratively) with a set of WTRUs and / or other agents. For example, the devices and agents can partition and / or aggregate workflows (e.g., in a manner similar to that used in a data center network).

[0095] In some examples, if a device's expected input data (e.g., raw data or / and trained data) is not delivered to the intended learning agent in time, the input data may not be used by the learning agent. This can result in wasted resources for the parties involved. There may be several reasons why the input data is not delivered in time (e.g., is disrupted). For example, the input data may not be delivered in time due to a lack of network resources (e.g., lack of radio resources due to temporal degradation, higher noise / interference levels, very congested conditions, partial / total failure, etc.).

[0096] FIG. 4 illustrates an exemplary input data jamming scenario (e.g., the WTRU may take one or more actions to proactively mitigate potential jamming). In an example, the deadline (e.g., preferred deadline) for input data transfer may be 1 second (e.g., t=t0+1) for 3 bits of input data (e.g., useful input data). For example, two different types of scheduling may be provided. For example, the first type of scheduling may be referred to as imperfect scheduling. The second type of scheduling may be referred to as good (e.g., perfect) scheduling. A bit of data (each bit of data) to be transmitted may take 1 second.

[0097] The transfer payload type may not be limited to input data of the learning agent. For example, the payload type may include a learning model transfer. The transfer direction may be uplink (e.g., for input data transfer) or downlink (e.g., for model distribution / transfer). In an example of imperfect scheduling, the input data may miss its deadline (e.g., not allocating a high data rate for this uplink data transmission, which would cause the input data to be delivered to its destination at time t0+2). In an example of perfect scheduling, the input data may be delivered to its destination within a predefined deadline (e.g., 1 second). In an example of perfect scheduling, network resources may be allocated to other devices (e.g., other WTRUs) during times t0+1 and / or t0+2. This may achieve efficient use of radio resources.

[0098] Features associated with an RRC protocol, a signaling radio bearer (SRB), and / or NAS signaling are provided herein. The RRC protocol may be a control plane (CP) protocol. The RRC protocol may control a connection between a WTRU and a network (e.g., a network entity such as a base station / gNodeB (gNB)).

[0099] Some example functions of the RRC protocol may include broadcasting of system information (e.g., for cell discovery, cell selection / reselection, common channel configuration, etc.), RRC connection control (e.g., connection setup from idle state, connection resumption from inactive state, paging of idle / inactive UEs, radio bearer configuration, handover, management of carrier aggregation and / or dual connectivity, recovery from radio link failure, etc.), and / or measurement configuration and / or reporting.

[0100] The WTRU may communicate with the core network (CN) using the NAS protocol, which may be carried in a transparent container within an RRC message (e.g., the RRC protocol may view the NAS information as a stream of bits and may not understand the information contained therein).

[0101] NAS and RRC messages may be transported between the WTRU and the network via SRBs. In some examples (e.g., New Radio (NR) communications), there are five types of available SRBs. For example, SRB0 may be used for RRC messages such as an RRC setup request, an RRC resume request, and an RRC re-establishment request (e.g., when a security context is not established in the WTRU and integrity protection and ciphering are not available or required). Other SRBs (e.g., all other SRBs) may be integrity protected and / or ciphered. For example, SRB1 may be used for RRC messages (e.g., which may include piggybacked NAS messages) and / or NAS messages (e.g., before the establishment of SRB2). SRB1 may be the main SRB (e.g., because it is used to transport higher priority RRC messages).

[0102] SRB2 may have a lower priority than SRB1. SRB2 may be configured by the network after security activation. SRB2 may be used to transmit NAS messages and / or WTRU information responses in response to requests from the network (e.g., to transmit non-priority mobility history, logged measurements, etc.). SRB3 may be used for direct CP communication with the secondary node (e.g., when the WTRU is in dual connected mode) (e.g., to transmit measurement reports for measurements configured by the secondary node). SRB4 may be used to transmit application layer measurements related to Quality of Experience (QoE) monitoring (e.g., buffering for streaming services). SRB4 may support message segmentation (e.g., because QoE measurement reports can be relatively large). For example, a QoE measurement report may be segmented into (e.g., up to) 16 RRC packets. In the uplink, WTRU capability information (e.g., separate from the QoE report) can be relatively large. The WTRU capability information may be segmented into several RRC packets. The WTRU capability information may be transmitted over SRB1.

[0103] SRB1 may have the highest priority (e.g., priority 1) of all radio bearers (e.g., because SRB1 may be used for messages such as RRC control messages). SRB3 may have a similar priority to SRB1. SRB3 priority may be relevant (e.g., only relevant) in the case of dual connectivity. SRB3 priority may affect the scheduling of the secondary link (e.g., only the secondary link).

[0104] SRB2 may be assigned the second highest priority (e.g., priority 2). SRB4 and / or DRBs may have the third highest priority. For example, SRB4 and / or DRBs may be assigned (e.g., assigned to each) a lower priority such as priority level 16. The priority level may determine the priority of data from the DRBs and / or SRBs (e.g., at the MAC level of the WTRU). The WTRU may attempt to utilize uplink grants received from the network. For example, data from higher priority SRBs and / or DRBs may be prioritized over data from lower priority SRBs and / or DRBs (e.g., if the WTRU is not granted enough resources to transmit all SRBs and / or DRBs).

[0105] During an FL training cycle, a participant (e.g., a WTRU) may train a local neural network (NN) model (e.g., in the WTRU's environment or based on a dataset). The training process may take a certain amount of time to complete (e.g., as shown in FIG. 6). The training process may be delayed by several factors. These factors may include the WTRU's resource availability (e.g., computational resources such as a graphics processing unit / central processing unit (GPU / CPU), battery, etc.). The FL training session may include a task completion deadline. For example, the WTRU may deliver its local training to the AF / AS within a specific time window (e.g., as shown in FIG. 6). In some instances (e.g., if the local training results are delivered after the deadline), the local training results may not be included in the next version of the global training model, or the local training results may be discarded. The group performance of the AI / ML service may be defined by the worst performer (e.g., the worst-performing WTRU). For example (e.g., in SFL), if an individual component performs significantly worse than others, the availability of associative information and functionality may be reduced (e.g., because completing an iteration with the whole group may be ideal). This is sometimes referred to as the flocking problem.

[0106] There may be several reasons why a WTRU participating in an FL training session may miss its task completion deadline or suffer from the swarming problem. Such reasons may include, for example, a lack of proper scheduling of uplink transmissions of data related to the training. The lack of proper scheduling may be due to one or more of blocking / delay due to data with higher priority than the AI / ML flow, poor radio conditions (e.g., between the WTRU and the serving base station / cell), and / or overload at the serving base station / cell (e.g., several WTRUs connected to the same cell or / and WTRUs served by the cell have active applications / services with high traffic demands), etc.

[0107] Another reason why WTRUs participating in an FL training session may miss task completion deadlines or suffer from the swarming problem may be a lack of sufficient computational resources (e.g., CPU / GPU, etc.). Lack of resources may cause delays (e.g., significant delays) in completing the training of the NN model. This delay may be compensated for by allocating more resources to the network (e.g., uplink and / or CN).

[0108] It may be desirable for the WTRU to ensure that (meta)data required for AI / ML operations (e.g., training) is transmitted on time to avoid missing task completion deadlines and / or prevent swarming scenarios. The network may not know the situation the WTRU or the network will be in until the AI / ML-related data is available. The network may not be able to configure a (e.g., a single) DRB / SRB to transmit AI / ML-related data without over-provisioning and further adversely affecting other traffic. For example, if a WTRU is configured to transmit AI / ML-related data using the highest priority DRB and the AI / ML data is ready well ahead of the deadline, transmitting the data with high priority data may block other traffic that has stricter latency requirements at the time.

[0109] Another aspect (e.g., in addition to data priority) is where the termination point of the AI / ML-related data is. For example, the FL controller may reside in the gNB, UPF, Access and Mobility Management Function (AMF), or other network node. In some cases, it may be appropriate to transmit data via the control plane (e.g., RRC messages, NAS messages embedded within RRC messages). In other cases (e.g., other cases), it may be more appropriate to transmit data via the user plane (e.g., using DRB).

[0110] Radio bearers can be categorized into two groups: data radio bearers (DRBs) (e.g., for user plane data) and signaling radio bearers (SRBs) (e.g., for control plane data). For AI / ML, message sizes (e.g., training (meta)data, training datasets, etc.) can vary greatly, from very small messages (e.g., a binary 1-bit indicating whether the WTRU is AI / ML capable) to very large messages (e.g., neural network weights, radio conditions / WTRU configuration parameters on which the neural network is trained, e.g., channel coherence time, channel coherence bandwidth, signal-to-noise ratio (SNR), signal-to-interference-and-noise ratio (SINR), bandwidth fraction (BWP), WTRU antenna configuration, etc.). As a result, mechanisms such as dedicating SRB1 to RRC signaling messages, SRB2 to NAS messages, and DRBs to data plane packet transmissions may not be suitable for AI / ML traffic.

[0111] The WTRU may determine an appropriate mechanism (e.g., CP or UP) and / or a particular SRB or DRB to be used for transmitting the AI / ML-related data that ensures that the AI / ML-related data is received by the network before a particular deadline (e.g., the latest time that data is integrated into FL training, as shown in FIG. 6) without impairing the performance of the involved WTRUs (e.g., including the transmitting WTRU) and other traffic from other WTRUs.

[0112] The WTRU may be connected to a public land mobile network (PLMN) via an access network (e.g., gNB). The WTRU may have gone through a registration process. The WTRU may have a PDU session established between the WTRU and the network (AMF) for an application client running on the WTRU. The 5GC may support publishing of data and analytics to the WTRU and application server (AS) via the user plane (UP) and control plane (CP). This support may be activated for the WTRU during a PDU session establishment or modification procedure. The AS / AF may activate such support by interacting (e.g., interacting directly) with the 5GC. The AS may publish information to the WTRU via the 5GC through the CP and / or UP. The NG-RAN may support publishing of data and analytics to the AS / AF via the 5GC. The AS / AF may subscribe to or request data and / or analytics from the 5GC and the NG-RAN. The 5GC may employ dedicated network functions for handling AI / ML workflows, such as FL.

[0113] While the examples described herein may relate to AI / ML metadata (e.g., trained models) or AI / ML-related datasets, the features described herein may be applicable to other uplink data (e.g., uplink traffic) that may have different needs and / or varied and / or bursty nature. An example of such data / traffic may be extended reality (XR) traffic (e.g., traffic related to augmented reality (AR), virtual reality (VR), mixed reality (MR), etc.), where the network may not be able to configure appropriate bearers, LCIDs, and / or the like (e.g., that may be used to transmit data) without over-provisioning (e.g., configuring bearers and / or logical channel identifiers (LCIDs) with the highest priority, highest data rates, lowest packet delay budgets, etc.).

[0114] As used herein, the term "file" may be used interchangeably with the term "payload." A file (e.g., payload) may include, for example, data in an uplink buffer of a WTRU. A "file size" (e.g., payload size) may refer to the amount of data in an uplink buffer of a WTRU. A "file type" (e.g., payload type) may refer to the type of data in an uplink buffer of a WTRU. As used herein, the term "application function" or "AF" may be used interchangeably with the term "application server" or "AS."

[0115] As used herein, the term "AI / ML server" may refer to an entity and / or function within a network responsible for managing AI / ML lifecycle management (LCM). For example, an AI / ML server may perform LCM functions such as controlling and / or configuring federated learning (FL) operations.

[0116] The WTRU may receive information (e.g., configuration) from the network regarding conditions associated with transmitting data associated with AI / ML-related operations (e.g., model training or data collection). For example, this information may be related to training an AI / ML model (e.g., as shown in FIG. 7). The WTRU may receive an indication from the network of when to start training (e.g., as shown in FIG. 7). The WTRU may receive an indication to collect data associated with training the AI / ML model. The WTRU may receive an indication from the network regarding a deadline (e.g., a deadline threshold) for transmitting data associated with the AI / ML training (e.g., as shown in FIG. 7). This data may indicate that an AI model has been trained or parameters associated with the training (e.g., the trained AI / ML model or metadata associated with the training). The WTRU may initiate execution of the AI / ML model training (e.g., at the time of starting training, as shown in FIGS. 6 and 7). The data may be transmitted according to the deadline. The data may be used by a network entity to train the AI / ML model.

[0117] The WTRU may determine a radio bearer type and / or a radio bearer of the selected radio bearer type (e.g., a particular SRB or DRB of the selected radio bearer type) to use to transmit data based on one or more transmission parameters. The WTRU may make the decision when training of the AI / ML model is completed or is about to be completed. The transmission parameters may include one or more of the time remaining until a deadline (e.g., a deadline for transmitting data), the current radio conditions between the WTRU and the serving cell, the amount of data to be transmitted, the security requirements of the data, and / or the current uplink buffer level. The WTRU may transmit the data over the selected radio bearer. The data may be transmitted according to the deadline.

[0118] The WTRU may determine a radio bearer to use to transmit AI / ML-related data (e.g., as shown in FIG. 7). For example, the WTRU may receive information indicating a first radio bearer type and a second radio bearer type (e.g., a first radio bearer configuration and a second radio bearer configuration). The first radio bearer type may be associated with the control plane, and the second radio bearer type may be associated with the user plane. The information may indicate that the WTRU will transmit data. The information may indicate a condition associated with the data, a first association between the condition and the first radio bearer type, and / or a second association between the condition and the second radio bearer type.

[0119] The WTRU may determine an estimated transmission time of the data based on a condition (e.g., satisfaction of a condition) and at least one of a first radio bearer type or a second radio bearer type. For example, the first radio bearer type may be an SRB, and the second radio bearer type may be a DRB. The WTRU may determine a radio bearer type to use based on a condition (e.g., an AI / ML task completion deadline, as shown in FIG. 7). The WTRU may select a radio bearer type from the first radio bearer type and the second radio bearer type based on at least a condition (e.g., a condition that the estimated transmission time satisfies a deadline threshold). The WTRU may determine a radio bearer to use for transmitting AI / ML training results (e.g., as shown in FIG. 7). The WTRU may transmit at least a portion of the data via a radio bearer of the selected radio bearer type.

[0120] The WTRU may determine which radio bearer to use based on the remaining time (eg, until a deadline) to transmit training data. For example, the WTRU may be configured to do one or more of: use a first signaling radio bearer (SRB) (e.g., SRB1) if the remaining time is below a first threshold (e.g., threshold 1); use a second SRB (e.g., SRB2) if the remaining time is between the first threshold and a second threshold (e.g., threshold 2); use a third SRB (e.g., SRB4) if the remaining time is between the second threshold and a third threshold (e.g., threshold 3); use a first data radio bearer (DRB) (e.g., DRBx) if the remaining time is between the third threshold and a fourth threshold (e.g., threshold 4); use a second DRB (e.g., DRBy) if the remaining time is between a fourth threshold and a fifth threshold (e.g., threshold 5); and / or use a third DRB (e.g., DRBz) if the remaining time is above a sixth threshold (e.g., threshold 6), etc.

[0121] The WTRU can use an SRB to deliver data to a network entity (e.g., a gNB) with high priority. It may be desirable to deliver the data over a control plane (e.g., a 5G control plane) in a manner that prevents congestion (e.g., in the 5GC control plane). In an example, the network entity may subscribe to obtain network analytics. For example, the network analytics may include network analytics regarding the level of congestion in the 5GC control plane. The network entity can determine how to send data from the WTRU to the AI / ML server (e.g., via the CP or via the UPF to the UP).

[0122] The WTRU may determine the radio bearer to use for transmitting the AI / ML related data based on the uplink buffer status. One or more of the following may apply:

[0123] The WTRU may determine which radio bearers to use to transmit AI / ML training results by considering the uplink buffer status (e.g., total uplink buffer level, uplink buffer level of a particular DRB or SRB, etc.). The WTRU may be configured to use one or more SRBs if the total uplink buffer level is above a threshold. The WTRU may be configured to use one or more DRBs if the total uplink buffer level is below a threshold.

[0124] For example, the WTRU may select the first radio bearer if the combined uplink buffer level of the first radio bearer and the second radio bearer is above a threshold, and the WTRU may select the second radio bearer if the combined uplink buffer level of the first radio bearer and the second radio bearer is below a threshold.

[0125] The WTRU may be configured with several uplink buffer thresholds. For example, the uplink buffer thresholds may be associated with different SRBs used to transmit AI / ML-related data. For example, the WTRU may be configured to do one or more of: use a first SRB (e.g., SRB1) if the total uplink buffer level is above a first threshold (e.g., threshold 1); use a second SRB (e.g., SRB2) if the total uplink buffer level is between a second threshold (e.g., threshold 2) and the first threshold; use a third SRB (e.g., SRB4) if the total uplink buffer level is between a third threshold (e.g., threshold 3) and the second threshold; and / or use a fourth SRB (e.g., SRBx) if the total uplink buffer level is between a fourth threshold (e.g., threshold y) and a fifth threshold (e.g., threshold z), etc.

[0126] The WTRU may be configured with several uplink buffer thresholds, for example, the uplink buffer thresholds may be associated with different DRBs used to transmit AI / ML-related data.

[0127] The WTRU may select the first radio bearer if the uplink buffer level of the first radio bearer is below the uplink buffer level of the second radio bearer. The WTRU may select the second radio bearer if the uplink buffer level of the second radio bearer is below the uplink buffer level of the first radio bearer. For example, the WTRU may be configured to do one or more of: use a first DRB (e.g., DRB1) if the total uplink buffer level is below a first threshold (e.g., threshold 1); use a second DRB (e.g., DRB2) if the total uplink buffer level is between the first threshold and a second threshold (e.g., threshold 2); and / or use a third DRB (e.g., DRBx) if the total uplink buffer level is between a third threshold (e.g., threshold y) and a fourth threshold (e.g., threshold z), etc.

[0128] The WTRU may be configured to use a particular SRB or DRB for transmitting AI / ML-related data. For example, the WTRU may be configured to use a particular SRB or DRB for transmitting AI / ML-related data if (e.g., only if) the amount of pending uplink data for that bearer is below a particular (e.g., configured) threshold. If the amount of uplink buffered data on that bearer is above the threshold, the WTRU may choose another SRB or DRB for transmitting the data. For example, this decision may be based on the SRB and / or DRB with the least amount of uplink buffered data, the SRB and / or DRB with the highest priority, or a combination thereof.

[0129] The WTRU may be configured to use a particular SRB or DRB for transmitting AI / ML-related data depending on the number of active bearers. For example, if the number of active bearers is above a certain value, the WTRU may be configured to use an SRB (e.g., only an SRB).

[0130] The WTRU may determine the radio bearer to use for transmitting the AI / ML-related data based on the radio conditions. The WTRU may consider the radio conditions (e.g., SINR, Reference Signal Received Power (RSRP), etc.) for the current serving cell. For example, the WTRU may use the radio conditions for the current serving cell to determine the radio bearer to use for transmitting the AI / ML-related data.

[0131] For example, the WTRU may select a first radio bearer (e.g., of the selected radio bearer type) as the radio bearer (e.g., of the selected radio bearer type) when the radio conditions of the serving cell are above a threshold. The WTRU may select a second radio bearer (e.g., of the selected radio bearer type) as the radio bearer when the radio conditions of the serving cell are below a threshold. For example, when the signal level is above a certain threshold, the WTRU may use a low-priority DRB to transmit AI / ML-related data. For example, when the signal level is below a certain threshold, the WTRU may use a high-priority DRB or SRB to transmit data. When the radio conditions are good (e.g., when the signal level is above a threshold), the priority of the selected bearer may not be as important because the WTRU can transmit more data per given allowed uplink radio resource (e.g., by using the highest modulation and coding scheme).

[0132] The thresholds associated with the radio conditions that the WTRU uses to determine which radio bearer to use to transmit AI / ML data may be specified in terms of retransmissions (e.g., at the Medium Access Control (MAC) and / or Radio Link Control (RLC) level).

[0133] The WTRU may select / decide which radio bearer to use based on the payload size.

[0134] A set of different thresholds for file size may be defined / configured in the WTRU (e.g., by the gNB or the network). Such thresholds may be configured by the WTRU vendor and / or verified by the gNB or the network. A set of thresholds may be defined to classify file sizes (e.g., uplink data in a WTRU buffer) into "small," "medium," and "large" types. In one example, a "small" file size may refer to an uplink payload less than 32 bits. A "medium" file size may refer to an uplink payload between 32 and 512 bits. A "large" file size may refer to an uplink payload larger than 512 bits.

[0135] The WTRU may be configured with rules such that small file sizes may be configured with SRB, medium file sizes may be configured with, for example, SRB4 or any other existing or new SRB or DRB, and large file sizes may be configured with, for example, SRB4 or any other existing or new SRB or DRB.

[0136] A WTRU may be configured with rules / thresholds corresponding to two (e.g., only two) size categories (e.g., "small" data size and "large" data size). A WTRU may be configured with a set of rules / thresholds corresponding to more than three size categories (e.g., "very small file size," "small file size," "medium file size," "large file size," "very large file size," etc.).

[0137] To assist the WTRU in determining the most appropriate radio bearer to use for transmitting uplink data, different sets of thresholds for file size may be defined / configured in the WTRU (e.g., by the gNB / NW). The WTRU may be configured with rules to determine the most appropriate radio bearer to use. For example, the WTRU may determine the radio bearer to use based on the type of data being transmitted in the UL, the radio bearer status, the AI / ML server destination, radio bearer congestion, etc. For example, the WTRU may select a first radio bearer if the payload size of the data is above a threshold. The WTRU may select a second radio bearer if the payload size of the data is below a threshold.

[0138] The WTRU may decide which radio bearer to use to transmit the AI / ML related data based on the reliability requirements of the payload.

[0139] A radio bearer (e.g., any radio bearer) that meets conditions associated with the remaining time for transmitting AI / ML data, buffer level, size of the data to be transmitted, and / or radio conditions may be used. DRBs may have different reliability associated with them. For example, some bearers may be configured to use acknowledged mode RLC with retransmissions at the RLC level (RLC-AM), thereby improving reliability. Some radio bearers (e.g., other radio bearers) may be configured to use transparent mode (e.g., RLC-TM) or unacknowledged mode (e.g., RLC-UM), which do not provide retransmissions.

[0140] The selection of the radio bearer to be used may be based on the reliability requirements of the AI / ML data. For example, the WTRU may select a first radio bearer (e.g., of the selected radio bearer type) as the radio bearer (e.g., of the selected radio bearer type) if the reliability or security criterion of the data is above a threshold. The WTRU may select a second radio bearer (e.g., of the selected radio bearer type) as the radio bearer (e.g., of the selected radio bearer type) if the reliability or security criterion of the data is below a threshold. For example, the AI / ML data may require high reliability. The WTRU may choose a radio bearer (e.g., radio bearer only) configured / associated with an acknowledged mode (e.g., RLC-AM). In some examples, the AI / ML data may not require high reliability. In this case, any radio bearer may be a candidate for transmitting the AI / ML data.

[0141] The WTRU may select / determine a radio bearer to use based on the type of payload. For example, the WTRU may select a first radio bearer if the payload type of the data is a first payload type. The WTRU may select a second radio bearer if the payload type of the data is a second payload type.

[0142] Different sets of thresholds for file types may be defined / configured (e.g., by the gNB / network) in the WTRU to allow some types of data to be transmitted (e.g., only transmitted) over some types of radio bearers. For example, the WTRU may be configured to use one radio bearer (e.g., SRB) for one type of AI / ML traffic (e.g., training metadata) and another radio bearer (e.g., another SRB or DRB) for another type of AI / ML traffic (e.g., all possible training results, training datasets, training configurations, etc.).

[0143] The WTRU may select / decide which radio bearer to use based on security / integrity.

[0144] A radio bearer (e.g., any radio bearer) that meets conditions associated with the remaining time to transmit AI / ML data, buffer level, size of the data to be transmitted, and / or radio conditions may be used. DRBs may be configured with or without integrity protection. SRBs may be integrity protected (e.g., always). Some DRBs may not be suitable for certain AI / ML-related data (e.g., if the integrity of the AI / ML data is important).

[0145] The selection of the radio bearer to be used may be based on an integrity criterion for the AI / ML data. For example, the AI / ML data may be integrity protected (e.g., may need to be integrity protected). In this case, the WTRU may choose an SRB or DRB (e.g., only an SRB or DRB) configured for integrity protection. In some examples, AI / ML data integrity may not be important. In this case, any radio bearer may be a candidate for transmitting the AI / ML data.

[0146] The WTRU may select / determine multiple radio bearers for transmitting control messages / data. The WTRU may use multiple radio bearers for transmitting control messages and / or AI / ML data. The WTRU may use multiple SRBs for transmitting control messages related to AI / ML traffic. For example, the WTRU may use SRB4 to report certain application layer measurement report information (e.g., related to AI / ML model training metadata). The WTRU may use another SRB (e.g., a new SRB) to report training results.

[0147] The WTRU may divide the AI / ML traffic among multiple SRBs based on the importance / priority of the data. For example, the WTRU may select a radio bearer (e.g., of a selected radio bearer type) to use to transmit at least a portion of the data (e.g., a first portion of the data). The WTRU may select a second radio bearer (e.g., of the selected radio bearer type). The WTRU may transmit the second portion of the data via the second radio bearer (e.g., of the selected radio bearer type). For example, higher priority / more important data may be transmitted in the uplink via SRB1. Lower priority / less important data may be transmitted in the uplink via SRB2.

[0148] The WTRU may use multiple DRBs with different priorities. For example, if an application client (AC) running on the WTRU finishes its model training earlier than expected, the WTRU may transmit the training results over a low-priority DRB. The WTRU may transmit its training hyperparameters on a high-priority radio bearer.

[0149] The WTRU can select / decide which radio bearer to use based on a combination of one or more of the above-mentioned parameters. The WTRU may be configured to determine which radio bearer to use based on a combination of one or more parameters. For example, if the uplink data in the WTRU buffer is "small" (e.g., below a preconfigured threshold) and the data is transmitted with strict latency requirements (e.g., within a preconfigured time window), the WTRU may decide to use an SRB. In an example, if the uplink data in the WTRU buffer is "large" (e.g., above a preconfigured threshold) and the latency limit for transmitting the data is greater than a threshold, the WTRU may decide to use a DRB.

[0150] In some examples (e.g., examples where SRBs are used to transmit user plane data), the WTRU may (e.g., should) add markings to the SRBs to indicate their use for user plane data. In some examples (e.g., examples where SRBs are used to transmit user plane data), there may be a common understanding between the WTRU and the gNB that user plane data (e.g., any user plane data) that meets certain requirements (e.g., small size and strict latency requirements) can be transmitted using SRBs (and thus, e.g., an explicit indication from the WTRU may not be required). The WTRU may send another message to the gNB to indicate that an SRB transmitted in the next time window carries user plane data.

[0151] The conditions (e.g., radio conditions and buffer levels, etc.) for determining the bearer to use for transmitting AI / ML data may be current conditions. The WTRU may be capable of predicting the buffer level and / or radio conditions (e.g., using an already trained AI / ML model or a prediction provided by the network). The thresholds associated with the buffer level or radio conditions may take into account the current and / or predicted conditions. For example, the buffer threshold level may be a predicted buffer threshold level within a predetermined time period, and the WTRU may be configured with a threshold related to the current buffer level and a threshold related to the predicted threshold level (e.g., other thresholds), and / or similar considerations may be given to thresholds related to radio signal levels.

[0152] The WTRU may be configured with an SRB dedicated to mapping of AI / ML QoS flows. The WTRU may be configured with SRBs applicable to mapping of AI / ML QoS flows. The WTRU may be configured with relative priorities between different SRBs applicable to AI / ML QoS flows. The WTRU may be configured to determine a first set of currently configured and active (e.g., not suspended) SRBs. The WTRU may be configured to map the AI / ML QoS flows to the SRB with the highest priority within the first set of SRBs.

[0153] The WTRU may be configured with a DRB dedicated to mapping of AI / ML QoS flows. The WTRU may be configured with DRBs applicable to mapping of AI / ML QoS flows. The WTRU may be configured with relative priorities among different DRBs applicable to AI / ML QoS flows. The WTRU may be configured to determine a second set of currently configured and active (e.g., not suspended) DRBs. The WTRU may be configured to map the AI / ML QoS flows to the DRB with the highest priority within the second set of DRBs.

[0154] The WTRU may be configured with a relative priority between a first set of radio bearers (e.g., SRBs) and a second set of radio bearers (e.g., DRBs). The WTRU may be configured to determine the priority of the first and second sets of radio bearers depending on the size of the PDU, the type of QoS flow (e.g., transmission of an AI / ML model, transmission of a data set, etc.), the type of wireless function associated with the AI / ML model (e.g., channel state information (CSI) feedback, beam management, positioning, mobility, etc.), and / or buffer status associated with the AI / ML QoS flow / radio bearer, etc.

[0155] The WTRU may determine the radio bearer mapping for the AI / ML QoS flow based on a condition (e.g., an implicit condition). For example, the WTRU may receive a model for training on a radio bearer type (e.g., SRB or DRB) from the network. The WTRU may train the model (e.g., locally) based on measurements. Once training is complete, the WTRU may forward the trained model on the same radio bearer type on which the model was received. A similar implicit mapping may be applied based on an association between a downlink radio bearer for which a configuration is received from the network and an uplink radio bearer on which the AI / ML flow is to be transmitted by the WTRU. Such an association may be pre-configured or pre-defined.

[0156] The WTRU can use the control plane (e.g., NAS signaling over SRB2) to upload its training results to an AI / ML function hosted in the 5GC. This AI / ML function may be an instance of the NWDAF (Network Data Analysis Function) of the 5GC. The NWDAF can provide data and analysis services to network functions (e.g., other network functions in the 5GC) and / or other entities in the 3GPP system (e.g., the WTRU and / or the RAN). An example NWDAF can generate its results using ML techniques.

[0157] The WTRU may send the training results to the AI / ML server hosted at the gNB via an uplink RRC message (e.g., a new uplink RRC message for transmitting user plane data) using SRB0, SRB1, or another (e.g., new) SRB. The WTRU may send the AI / ML data to the AI / ML server hosted at the gNB using a NAS message in SRB1.

[0158] The WTRU may be configured to initially send training results to the gNB using an SRB, and then from the gNB via the 5GC UPF to an AI / ML server (e.g., hosted in the cloud). The AI / ML server may be hosted outside / inside the 3GPP network. The WTRU may be configured to send and receive data to and from the network using a DRB (e.g., using only a DRB).

[0159] The WTRU may map QoS flows to high / low priority bearers (e.g., depending on the priority of the AI / ML data). For example, if SRBs are intended to be used, SRB1 may have a higher priority than SRB2. For example, if DRBs are intended to be used, one DRB may have a higher priority than another DRB. Several factors (e.g., other factors) besides the location of the AI / ML server may be considered by the WTRU when deciding which SRB or DRB to use for a particular QoS flow.

[0160] 5 is an example illustrating a WTRU selecting / deciding whether to use the control plane or the user plane and on which radio bearer to transmit data. The WTRU's decision may enable an AI / ML AC (e.g., running in the WTRU) to transmit data with a particular (e.g., required) transmission priority.

[0161] In 1, the WTRU can decide how to transmit data of an AC to the network. The WTRU can decide whether the data of the AC should be transmitted over a CP or an UP. The WTRU can decide whether the data of the AC should be transmitted over an SRB or a DRB. The WTRU can be configured with a policy to assist in this decision-making. The policy can take into account several parameters. For example, the parameters can include data size, data priority, radio conditions of the SRB / DRB, current QoS flow rules, destination of the AI / ML server (e.g., AS), and / or user mobility.

[0162] In 2, the WTRU may transmit the AC's data (e.g., AI / ML training results) to the gNB (e.g., via an uplink RRC message). The WTRU may transmit the data over a specific SRB (e.g., depending on the priority of the uplink data transmission). The WTRU may indicate to the gNB whether this message contains the WTRU's user plane data (e.g., data that the gNB forwards to its destination). The destination of the data may be within the gNB / RAN or elsewhere. If the AS is hosted in a cloud data center outside the 5G network, the gNB may forward the WTRU's data to the AS via the UPF via N3 or via the Network Exposure Function (NEF) via the AMF / SMF.

[0163] In 3, the gNB may forward the WTRU's data to the AS (e.g., via the UPF). Data transmission between the gNB and the UPF may be via the N3 tunnel. The WTRU's data may be delivered from the UPF to the AS via N6.

[0164] 6 shows an example timeline of data transmission. One or more WTRUs may be configured to perform AI / ML-related actions (e.g., AI / ML training). The WTRUs may send a report (e.g., trained model weights) within a predetermined time (e.g., before a deadline).

[0165] In the example of FIG. 6, a first WTRU (e.g., WTRU1) may complete training before the deadline. In this case, the first WTRU may transmit results in time (e.g., even if the first WTRU is configured to use a low-priority RB, e.g., a DRB). A second WTRU (e.g., WTRU2) may complete training closer to the deadline. In this case, the second WTRU may transmit results in time if (e.g., only if) the second WTRU was configured to use a high-priority RB (e.g., a high-priority DRB or SRB). The network and / or WTRU may not know when an action (e.g., training) will be completed (e.g., because it may depend on variable WTRU and / or network conditions).

[0166] 7 is an example call flow illustrating a WTRU selecting / determining a radio bearer for transmitting data. As shown, a network node may send configuration information to the WTRU. The configuration information may include specifications (e.g., requirements) for the data (e.g., AI / ML-related data). The configuration information may include RBs (e.g., DRBs and / or SRBs) that the WTRU may use to transmit the data. The configuration information may include one or more conditions (e.g., UL buffer level, radio conditions, etc.). The WTRU may use these conditions to determine which RBs to use to transmit the data.

[0167] The network node may send an indication of one or more triggers that indicate the WTRU should initiate an AI / ML-related action (e.g., training). The network node may send information regarding a deadline for sending the results of the action, and / or quality of service (QoS) specifications (e.g., requirements), such as security and reliability specifications.

[0168] The WTRU may initiate execution of an AI / ML-related action (e.g., in response to a trigger). The WTRU may complete an action that generates a result / data. The WTRU may determine the RBs to use to transmit data according to the specifications (e.g., requirements) of the data. For example, the WTRU may determine the RBs to use to transmit data based on the size of the data and / or security and / or reliability specifications of the data, etc. The WTRU may determine the RBs to use to transmit data depending on WTRU conditions (e.g., current uplink buffer level, etc.), network conditions (e.g., radio conditions, etc.), and / or configuration information received from a network node, etc. The WTRU may transmit data to the network node using the selected / elected RBs.

[0169] Although the above-described features and elements are described in particular combinations, each feature or element can be used alone without other features and elements of the preferred embodiments, or in various combinations with or without other features and elements.

[0170] While the implementations described herein may consider 3GPP-specific protocols, it will be understood that the implementations described herein are not limited to this scenario and may be applicable to other wireless systems. For example, while the solutions described herein consider LTE, LTE-A, New Radio (NR), or 5G-specific protocols, it will be understood that the solutions described herein are not limited to this scenario and may be applicable to other wireless systems. For example, while the systems are described with reference to 3GPP, 5G, and / or NR network layers, contemplated embodiments extend beyond implementations using specific network layer technologies. Similarly, potential implementations span all types of service layer architectures, systems, and embodiments. The techniques described herein may be applied independently and / or used in combination with other resource configuration techniques.

[0171] The processes described herein may be implemented in a computer program, software, and / or firmware embodied in a computer-readable medium for execution by a computer and / or processor. Examples of computer-readable media include, but are not limited to, electronic signals (transmitted via wired and / or wireless connections) and / or computer-readable storage media. Examples of computer-readable storage media include, but are not limited to, read-only memory (ROM), random-access memory (RAM), registers, cache memory, semiconductor memory devices, magnetic media such as, but not limited to, internal hard disks and removable disks, magneto-optical media, and / or optical media such as compact disc (CD)-ROM disks and / or digital versatile discs (DVDs). The software and associated processor may be used to implement a radio frequency transceiver for use in a WTRU, a terminal, a base station, an RNC, or any host computer.

[0172] It will be understood that the entities performing the processes described herein may be logical entities that may be implemented in the form of software (e.g., computer-executable instructions) stored in the memory of and executed on the processor of a mobile device, network node, or computer system. That is, the processes may be implemented in the form of software (e.g., computer-executable instructions) stored in the memory of a mobile device and / or network node, such as a node or computer system, which computer-executable instructions, when executed by the processor of the node, perform the described process. It will also be understood that any transmit and receive processes shown in the figures may be performed by the node's communications circuitry under control of the node's processor and the computer-executable instructions (e.g., software) it executes.

[0173] The various techniques described herein may be implemented in connection with hardware or software, or, where appropriate, with a combination of both. Accordingly, implementations and apparatuses of the subject matter described herein, or certain aspects or portions thereof, may take the form of program code (e.g., instructions) embodied in tangible media, including any other machine-readable storage medium; when the program code is loaded into and executed by a machine, such as a computer, the machine becomes an apparatus for implementing the subject matter described herein. When program code is stored on a medium, it may be stored on one or more media that collectively perform the operation; i.e., one or more media may contain code that together perform the operation; however, if there is more than a single medium, there is no requirement that any particular portion of the code be stored on any particular medium. In the case of program code execution on a programmable device, the computing device generally includes a processor, a storage medium (including volatile and non-volatile memory and / or storage elements) readable by the processor, at least one input device, and at least one output device. One or more programs may implement or utilize the processes described in connection with the subject matter described herein, for example, through the use of an API or reusable controls. Such programs are preferably implemented in a high-level procedural or object-oriented programming language to communicate with a computer system. However, the programs can be implemented in assembly or machine language, if desired. In either case, the language may be a compiled or interpreted language, and combined with hardware implementations.

[0174] While exemplary embodiments may illustrate utilizing aspects of the subject matter described herein in the context of one or more standalone computing systems, the subject matter described herein is not so limited and, rather, may be implemented in connection with any computing environment, such as a network or distributed computing environment. Furthermore, aspects of the subject matter described herein may be implemented within or across multiple processing chips or devices, and storage may be similarly affected across multiple devices. Such devices may include personal computers, network servers, handheld devices, supercomputers, or computers integrated into other systems, such as automobiles or airplanes.

[0175] In describing preferred embodiments of the subject matter of the present disclosure, as illustrated in the figures, specific terminology is utilized for clarity, however, it is understood that the claimed subject matter is not intended to be limited to the specific terminology so selected, and that each specific element includes all technical equivalents that operate in a similar manner to accomplish a similar purpose.

Claims

1. 1. A wireless transmit / receive unit (WTRU), comprising: a first radio bearer configuration indicating radio bearers of a first radio bearer type associated with the control plane; a second radio bearer configuration indicating radio bearers of a second radio bearer type associated with the user plane; and Conditions associated with transmitting data associated with artificial intelligence / machine learning (AI / ML) related operations; and a first association between the condition and the first radio bearer type, and a second association between the condition and the second radio bearer type; receiving information indicating receiving an indication to initiate the AI / ML-related operation; determining that the data associated with the AI / ML-related operation is available; selecting a radio bearer type to use for transmitting the data from the first radio bearer type and the second radio bearer type based on at least the condition; transmitting at least a portion of the data via a radio bearer of the selected radio bearer type; 12. A WTRU comprising: a processor configured to:

2. The WTRU of claim 1 , wherein the first radio bearer type comprises a signaling radio bearer (SRB) and the second radio bearer type comprises a data radio bearer (DRB).

3. The AI / ML-related operations include training an AI / ML model, and the processor: receiving an indication of a time to start training the AI / ML model and a deadline for transmitting the data, the data indicating at least one of that the AI / ML model has been trained and parameters associated with the training; determining a first estimated transmission time of the data based on the first association and a second estimated transmission time of the data based on the second association; further configured as follows: the processor configured to select the radio bearer type to use for transmitting the data from the first radio bearer type and the second radio bearer type based on at least the condition includes a processor configured to select the radio bearer type based on whether one or more of the first estimated transmission time or the second estimated transmission time meets a deadline threshold; The WTRU of claim 1 , wherein at the time to start training the AI / ML model, AI / ML training is performed, and at least a portion of the data is transmitted according to the deadline threshold.

4. 2. The WTRU of claim 1, wherein the AI / ML-related operations include collecting data, and wherein the processor configured to transmit at least a portion of the data over a radio bearer of the selected radio bearer type includes a processor configured to transmit the data to a network entity for training an AI / ML model.

5. The processor is further configured to select the radio bearer of the selected radio bearer type from a first radio bearer and a second radio bearer of the selected radio bearer type based on an uplink buffer level, and the processor configured to select the radio bearer of the selected radio bearer type based on the uplink buffer level: selecting the first radio bearer if a combined uplink buffer level of the first radio bearer and the second radio bearer is above a threshold; If the total uplink buffer level of the first radio bearer and the second radio bearer is below the threshold, select the second radio bearer. a processor configured to: selecting the first radio bearer if an uplink buffer level of the first radio bearer is lower than an uplink buffer level of the second radio bearer; Selecting the second radio bearer if the uplink buffer level of the second radio bearer is lower than the uplink buffer level of the first radio bearer. A processor configured to The WTRU of claim 1 , comprising:

6. The processor: selecting a first radio bearer of the selected radio bearer type as a radio bearer of the selected radio bearer type if the radio condition of the serving cell is above a threshold; If the radio condition of the serving cell is below the threshold, select a second radio bearer of the selected radio bearer type as the radio bearer of the selected radio bearer type. The WTRU of claim 1 , further configured to:

7. The processor is further configured to select the radio bearer of the selected radio bearer type from a first radio bearer and a second radio bearer of the selected radio bearer type based on a payload of the data, and the processor configured to select the radio bearer of the selected radio bearer type based on a payload of the data: If the payload size of the data exceeds a threshold, selecting the first radio bearer; If the payload size of the data is below the threshold, select the second radio bearer. a processor configured to: selecting the first radio bearer if the payload type of the data is a first payload type; If the type of the payload of the data is a second payload type, select the second radio bearer. A processor configured to The WTRU of claim 1 , comprising:

8. The processor: selecting a first radio bearer of the selected radio bearer type as the radio bearer of the selected radio bearer type if the data reliability or security criterion is above a threshold; selecting a second radio bearer of the selected radio bearer type as the radio bearer of the selected radio bearer type if the reliability or security metric of the data is below the threshold. The WTRU of claim 1 further configured to:

9. the radio bearer of the selected radio bearer type is a first radio bearer of the selected radio bearer type, and the at least a portion of the data is a first portion of the data, and the processor: selecting a second radio bearer of the selected radio bearer type; transmitting a second portion of the data over the second radio bearer of the selected radio bearer type; The WTRU of claim 1 further configured to:

10. 1. A method implemented by a wireless transmit / receive unit (WTRU), comprising: a first radio bearer configuration indicating a first radio bearer of a first radio bearer type associated with the control plane; a second radio bearer configuration indicating a second radio bearer of a second radio bearer type associated with the user plane; and Conditions associated with transmitting data associated with artificial intelligence / machine learning (AI / ML) related operations; and a first association between the condition and the first radio bearer type, and a second association between the condition and the second radio bearer type; receiving information indicative of receiving an indication to initiate the AI / ML-related operation; determining that the data associated with the AI / ML-related operation is available; selecting a radio bearer type to use for transmitting the data from the first radio bearer type and the second radio bearer type based on at least the condition associated with transmitting the data; transmitting at least a portion of the data over a radio bearer of the selected radio bearer type; and A method comprising:

11. 11. The method of claim 10, wherein the first radio bearer type comprises a signaling radio bearer (SRB) and the second radio bearer type comprises a data radio bearer (DRB).

12. receiving an indication of a time to start training an AI model and a deadline for transmitting the data, the data indicating at least one of that the AI ​​model has been trained or parameters associated with the training; At the time to start training the AI, performing AI training, wherein at least a portion of the data is transmitted according to a deadline threshold. The method of claim 10 further comprising:

13. 11. The method of claim 10, wherein the AI / ML-related operations include collecting data, and wherein transmitting at least a portion of the data over a radio bearer of the selected radio bearer type includes transmitting the data to a network entity for training an AI / ML model.

14. The method further includes selecting the radio bearer of the selected radio bearer type from a first radio bearer and a second radio bearer of the selected radio bearer type based on an uplink buffer level, wherein selecting the radio bearer of the selected radio bearer type based on the uplink buffer level includes: selecting the first radio bearer if a combined uplink buffer level of the first radio bearer and the second radio bearer is above a threshold; selecting the second radio bearer if the total uplink buffer level of the first radio bearer and the second radio bearer is below the threshold; Contains, or selecting the first radio bearer if an uplink buffer level of the first radio bearer is lower than an uplink buffer level of the second radio bearer; selecting the second radio bearer if the uplink buffer level of the second radio bearer is lower than the uplink buffer level of the first radio bearer; The method of claim 10, comprising:

15. The method comprises: selecting a first radio bearer of the selected radio bearer type as a radio bearer of the selected radio bearer type if radio conditions of a serving cell are above a threshold; selecting a second radio bearer of the selected radio bearer type as the radio bearer of the selected radio bearer type if the radio condition of the serving cell is below the threshold; The method of claim 10 further comprising:

16. The method further includes selecting the radio bearer of the selected radio bearer type from a first radio bearer and a second radio bearer of the selected radio bearer type based on a payload of the data, wherein selecting the radio bearer of the selected radio bearer type based on a payload of the data includes: selecting the first radio bearer if a payload size of the data exceeds a threshold; selecting the second radio bearer if the payload size of the data is below the threshold; Contains, or selecting the first radio bearer if the payload type of the data is a first payload type; selecting the second radio bearer if the type of the payload of the data is a second payload type; The method of claim 10, comprising:

17. The method comprises: selecting a first radio bearer of the selected radio bearer type as the radio bearer of the selected radio bearer type if the data reliability or security metric is above a threshold; selecting a second radio bearer of the selected radio bearer type as the radio bearer of the selected radio bearer type if the reliability or security metric of the data is below the threshold; The method of claim 10 further comprising:

18. the radio bearer of the selected radio bearer type is a first radio bearer of the selected radio bearer type, and the at least a portion of the data is a first portion of the data, and the method further comprises: selecting a second radio bearer of the selected radio bearer type; transmitting a second portion of the data over the second radio bearer of the selected radio bearer type; and The method of claim 10 further comprising:

Images