Interface for aerial model aggregation in federated systems

Abstract

Various aspects of the present disclosure relate generally to wireless communications. In some aspects, a user equipment (UE) may determine a quantization parameter in a recurrent neural network (RNN) or a gradient for deriving the RNN based at least in part on artificial intelligence (AI) modeling at the UE as part of a federated edge learning system. The UE may generate a message indicating the quantization parameter or gradient determined by the UE. The message may include a medium access control (MAC) protocol data unit or a set of bits obtained from a MAC layer, a packet data convergence protocol layer, or an application layer. The UE may send the message to a base station on a physical uplink shared channel (PUSCH) radio resource that overlaps with a PUSCH radio resource used by other UEs. A number of other aspects are provided.

Description

Technical Field

[0001] Aspects of the present disclosure generally relate to techniques and apparatus for wireless communications and interfaces for air model aggregation in federated systems. Background Art

[0002] Wireless communication systems are widely deployed to provide a variety of telecommunication services such as telephony, video, data, messaging, and broadcasts. Typical wireless communication systems may employ multiple access technologies capable of supporting communication with multiple users by sharing available system resources (e.g., bandwidth, transmit power, etc.). Examples of such multiple access technologies include code division multiple access (CDMA) systems, time division multiple access (TDMA) systems, frequency division multiple access (FDMA) systems, orthogonal frequency division multiple access (OFDMA) systems, single-carrier frequency division multiple access (SC-FDMA) systems, time division synchronous code division multiple access (TD-SCDMA) systems, and long term evolution (LTE). LTE / LTE-Advanced is a set of enhancements to the Universal Mobile Telecommunications System (UMTS) mobile standard promulgated by the Third Generation Partnership Project (3GPP).

[0003] A wireless network may include multiple base stations (BSs) that may support communications for multiple user equipment (UEs). User equipment (UEs) may communicate with a base station (BS) via downlinks and uplinks. A downlink (or forward link) refers to the communication link from the BS to the UE, while an uplink (or reverse link) refers to the communication link from the UE to the BS. As will be described in more detail herein, a BS may be referred to as a Node B, gNB, access point (AP), radio head, transmit receive point (TRP), new radio (NR) BS, 5G Node B, etc.

[0004] The aforementioned multiple access technologies have been adopted in various telecommunications standards to provide a common protocol that enables diverse user devices to communicate at the city, national, regional, and even global levels. New Radio (NR), also known as 5G, is a set of enhancements to the LTE mobile standard released by the Third Generation Partnership Project (3GPP). NR is designed to better support mobile broadband internet access by using orthogonal frequency division multiplexing (OFDM) with a cyclic prefix (CP) (CP-OFDM) on the downlink (DL), CP-OFDM and / or SC-FDM (e.g., also known as discrete Fourier transform spread OFDM (DFT-s-OFDM)) on the uplink (UL), and supporting beamforming, multiple-input, multiple-output (MIMO) antenna technology, and carrier aggregation to improve spectral efficiency, reduce costs, improve services, utilize new spectrum, and better integrate with other open standards. As the demand for mobile broadband access continues to increase, further improvements to LTE, NR, and other radio access technologies remain valuable. Summary of the Invention

[0005] In some aspects, a method of wireless communication performed by a user equipment (UE) includes determining a quantization parameter in a recurrent neural network (RNN) or a gradient for deriving the RNN based at least in part on artificial intelligence (AI) modeling at the UE as part of a federated edge learning system. The method includes generating a message indicating the quantization parameter or gradient determined by the UE, the message including a medium access control (MAC) protocol data unit (PDU) or a set of bits obtained from a MAC layer, a packet data convergence protocol layer, or an application layer; and sending the message to a base station on a physical uplink shared channel (PUSCH) radio resource that overlaps with PUSCH radio resources used by other UEs.

[0006] In some aspects, a method of wireless communication performed by a base station includes determining, based on messages received on overlapping PUSCH resources from the multiple UEs, quantization parameters of a recurrent neural network (RNN) modeled by AI associated with a federated edge learning system or gradients for deriving the RNN at each of the multiple UEs, each message including a MAC PDU or a set of bits indicating the quantization parameters or gradients. The method includes aggregating the quantization parameters or gradients from the multiple UEs to update a global model and sending the updated global model to the multiple UEs.

[0007] In some aspects, a method of wireless communication performed by a UE includes determining that quantization parameters or gradients are to be centrally aggregated as part of a federated edge learning system, and disabling channel coding based at least in part on determining that the quantization parameters or gradients are to be centrally aggregated.

[0008] In some aspects, a UE for wireless communication includes a memory and one or more processors operably coupled to the memory, the memory and the one or more processors configured to determine a quantization parameter in a RNN or a gradient for deriving the RNN based at least in part on AI modeling at the UE as part of a federated edge learning system. The one or more processors are configured to generate a message indicating the quantization parameter or gradient determined by the UE, the message including a MAC PDU or a set of bits obtained from a MAC layer, a packet data convergence protocol layer, or an application layer; and transmit the message to a base station on a PUSCH radio resource that overlaps with PUSCH radio resources used by other UEs.

[0009] In some aspects, a base station for wireless communication includes a memory and one or more processors operably coupled to the memory, the memory and the one or more processors configured to determine, at each of the multiple UEs, a quantization parameter of an AI-modeled RNN associated with a federated edge learning system or a gradient for deriving the RNN based on messages received on overlapping PUSCH resources from the multiple UEs, each message including a MAC PDU or a set of bits indicating the quantization parameter or gradient. The one or more processors are configured to aggregate the quantization parameters or gradients from the multiple UEs to update a global model and send the updated global model to the multiple UEs.

[0010] In some aspects, a UE for wireless communication includes a memory and one or more processors operably coupled to the memory, the memory and the one or more processors configured to determine that quantization parameters or gradients are to be centrally aggregated as part of a federated edge learning system, and to disable channel coding based at least in part on determining that the quantization parameters or gradients are to be centrally aggregated.

[0011] In some aspects, a non-transitory computer-readable medium storing a set of instructions for wireless communication includes one or more instructions that, when executed by one or more processors of a UE, cause the UE to: determine a quantization parameter in a RNN or a gradient for deriving the RNN based at least in part on AI modeling at the UE as part of a federated edge learning system, generate a message indicating the quantization parameter or gradient determined by the UE, the message including a MAC PDU or a set of bits obtained from a MAC layer, a packet data convergence protocol layer, or an application layer, and send the message to a base station on PUSCH radio resources that overlap with PUSCH radio resources used by other UEs.

[0012] In some aspects, a non-transitory computer-readable medium storing a set of instructions for wireless communication includes one or more instructions that, when executed by one or more processors of a base station, cause the base station to: determine, based on messages received on overlapping PUSCH resources from the multiple UEs, a quantization parameter of an AI-modeled RNN associated with a federated edge learning system or a gradient for deriving the RNN at each of the multiple UEs, each message including a MAC PDU or a set of bits indicating the quantization parameter or gradient, aggregate the quantization parameters or gradients from the multiple UEs to update a global model, and send the updated global model to the multiple UEs.

[0013] In some aspects, a non-transitory computer-readable medium storing a set of instructions for wireless communication includes one or more instructions that, when executed by one or more processors of a UE, cause the UE to: determine that quantization parameters or gradients are to be centrally aggregated as part of a federated edge learning system, and disable channel coding based at least in part on determining that the quantization parameters or gradients are to be centrally aggregated.

[0014] In some aspects, an apparatus for wireless communication includes: means for determining a quantization parameter in a RNN or for deriving a gradient of the RNN based at least in part on AI modeling at the apparatus as part of a federated edge learning system; means for generating a message indicating the quantization parameter or gradient determined by the apparatus, the message comprising a MAC PDU or a set of bits obtained from a MAC layer, a packet data convergence protocol layer, or an application layer; and means for sending the message to a base station on PUSCH radio resources that overlap with PUSCH radio resources used by other UEs.

[0015] In some aspects, an apparatus for wireless communication includes: a component for determining a quantization parameter of an AI-modeled RNN associated with a federated edge learning system or a gradient for deriving the RNN at each of a plurality of UEs based on messages received on overlapping PUSCH resources from the plurality of UEs, each message including a MAC PDU or a set of bits indicating the quantization parameter or gradient; a component for aggregating the quantization parameters or gradients from the plurality of UEs to update a global model; and a component for sending the updated global model to the plurality of UEs.

[0016] In some aspects, an apparatus for wireless communication includes components for determining that quantization parameters or gradients are to be centrally aggregated as part of a federated edge learning system, and components for disabling channel coding based at least in part on determining that the quantization parameters or gradients are to be centrally aggregated.

[0017] Aspects generally include methods, apparatus, systems, computer program products, non-transitory computer-readable media, user equipment, base stations, wireless communication devices, and / or processing systems as substantially described herein with reference to and as illustrated in the accompanying figures and description.

[0018] The foregoing has outlined rather broadly the features and technical advantages of the examples according to the present disclosure so that the subsequent detailed description may be better understood. Additional features and advantages will be described hereinafter. The disclosed concepts and specific examples may be readily used as a basis for modifying or designing other structures for achieving the same purpose of the present disclosure. Such equivalent structures do not depart from the scope of the appended claims. The characteristics of the concepts disclosed herein, their organization and method of operation, and related advantages will be better understood from the following description when considered in conjunction with the accompanying drawings. Each of the figures in the drawings is provided for the purpose of illustration and description and not as a definition of limitations of the claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to be able to understand in detail the above-mentioned features of the present disclosure, a more specific description briefly summarized above may be obtained by reference to some of the aspects shown in the accompanying drawings. However, it should be noted that the drawings illustrate only certain typical aspects of the present disclosure and are not therefore to be considered limiting of its scope, as the description may admit of other equally valid aspects. The same reference numerals in different drawings may identify the same or similar elements.

[0020] Figure 1 is a diagram illustrating an example of a wireless network in accordance with various aspects of the present disclosure.

[0021] Figure 2 is a diagram illustrating an example of a base station communicating with a user equipment (UE) in a wireless network according to various aspects of the present disclosure.

[0022] Figure 3 is a diagram illustrating an example of federated edge learning according to various aspects of the present disclosure.

[0023] Figure 4 is a diagram illustrating an example of an interface for air model aggregation in a federated system according to various aspects of the present disclosure.

[0024] Figure 5 is a diagram illustrating example processes performed, for example, by a UE, in accordance with various aspects of the present disclosure.

[0025] Figure 6 is a diagram illustrating example processes performed, for example, by a base station, according to various aspects of the present disclosure.

[0026] Figure 7 is a diagram illustrating example processes performed, for example, by a UE, in accordance with various aspects of the present disclosure.

[0027] Figure 8 is a block diagram of an example apparatus for wireless communications.

[0028] Figure 9 is a block diagram of an example apparatus for wireless communications.

[0029] Figure 10 is a block diagram of an example apparatus for wireless communications. DETAILED DESCRIPTION

[0030] Various aspects of the present disclosure are described more fully below with reference to the accompanying drawings. However, the present disclosure can be embodied in a number of different forms and should not be construed as being limited to any specific structure or function presented throughout the present disclosure. On the contrary, these aspects are provided so that the present disclosure will be thorough and complete, and will fully convey the scope of the present disclosure to those skilled in the art. Based on the teachings herein, it should be understood by those skilled in the art that the scope of the present disclosure is intended to cover any aspect of the present disclosure disclosed herein, whether it is implemented independently of any other aspect of the present disclosure or implemented in combination with any other aspect of the present disclosure. For example, a device or practice method can be implemented with any number of aspects set forth herein. In addition, the scope of the present disclosure is intended to cover such a device or method that uses other structures, functions, or structures and functions that supplement or replace the various aspects of the present disclosure set forth herein to practice. It should be understood that any aspect of the present disclosure disclosed herein can be implemented by one or more elements of the claims.

[0031] Several aspects of telecommunications systems will now be presented with reference to various devices and techniques. These devices and techniques will be described in the following detailed description and illustrated in the accompanying drawings by various blocks, modules, components, circuits, steps, processes, algorithms, etc. (collectively, "elements"). These elements can be implemented using hardware, software, or a combination thereof. Whether these elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system.

[0032] It should be noted that although terms generally associated with 5G or NR radio access technology (RAT) may be used herein to describe various aspects, aspects of the present disclosure may be applied to other RATs, such as 3G RAT, 4G RAT, and / or RATs beyond 5G (e.g., 6G).

[0033] Figure 1 is a diagram illustrating an example of a wireless network 100 according to various aspects of the present disclosure. The wireless network 100 may be or may include elements of a 5G (NR) network, an LTE network, or the like. The wireless network 100 may include multiple base stations 110 (shown as BS 110a, BS 110b, BS 110c, and BS 110d) and other network entities. A base station (BS) is an entity that communicates with a user equipment (UE) and may also be referred to as an NR BS, a Node B, a gNB, a 5G Node B (NB), an access point, a transmit receive point (TRP), or the like. Each BS may provide communication coverage for a specific geographic area. In 3GPP, the term "cell" may refer to a coverage area of ​​a BS and / or a BS subsystem serving that coverage area, depending on the context in which the term is used.

[0034] A BS may provide communication coverage for a macro cell, a pico cell, a femto cell, and / or another type of cell. A macro cell may cover a relatively large geographic area (e.g., a radius of several kilometers) and may allow unrestricted access to UEs with service subscriptions. A pico cell may cover a relatively small geographic area and may allow unrestricted access to UEs with service subscriptions. A femto cell may cover a relatively small geographic area (e.g., a home) and may allow restricted access to UEs associated with the femto cell (e.g., UEs in a closed subscriber group (CSG)). A BS for a macro cell may be referred to as a macro BS. A BS for a pico cell may be referred to as a pico BS. A BS for a femto cell may be referred to as a femto BS or a home BS. In Figure 1 In the example shown in FIG, BS 110a may be a macro BS for macrocell 102a, BS 110b may be a pico BS for picocell 102b, and BS 110c may be a femto BS for femtocell 102c. A BS may support one or more (e.g., three) cells. The terms "eNB," "base station," "NR BS," "gNB," "TRP," "AP," "Node B," "5G NB," and "cell" may be used interchangeably herein.

[0035] In some aspects, the cells may not necessarily be fixed, and the geographic area of ​​the cells may move depending on the location of the mobile BS. In some aspects, the BSs may be interconnected with each other and / or with one or more other BSs or network nodes (not shown) in the wireless network 100 via various types of backhaul interfaces, such as direct physical connections, virtual networks, and / or similar means using any suitable transport network.

[0036] The wireless network 100 may also include a relay station. A relay station is an entity that receives a transmission of data from an upstream station (e.g., a BS or a UE) and sends a transmission of the data to a downstream station (e.g., a UE or a BS). A relay station may also be a UE that can relay transmissions for other UEs. Figure 1 In the example shown in , relay BS 110d may communicate with macro BS 110a and UE 120d to facilitate communication between BS 110a and UE 120d. A relay BS may also be referred to as a relay station, relay base station, relay, etc.

[0037] The wireless network 100 may be a heterogeneous network including different types of BSs (e.g., macro BSs, pico BSs, femto BSs, relay BSs, etc.). These different types of BSs may have different transmit power levels, different coverage areas, and different impacts on interference in the wireless network 100. For example, a macro BS may have a high transmit power level (e.g., 5 to 40 watts), while a pico BS, a femto BS, and a relay BS may have a lower transmit power level (e.g., 0.1 to 2 watts).

[0038] The network controller 130 may be coupled to a set of BSs and may provide coordination and control for these BSs. The network controller 130 may communicate with the BSs via a backhaul. The BSs may also communicate with each other directly or indirectly, for example, via a wireless or wired backhaul.

[0039] UEs 120 (e.g., 120a, 120b, 120c) may be dispersed throughout the wireless network 100, and each UE may be fixed or mobile. A UE may also be referred to as an access terminal, terminal, mobile station, subscriber unit, station, etc. A UE may be a cellular phone (e.g., a smartphone), a personal digital assistant (PDA), a wireless modem, a wireless communication device, a handheld device, a laptop computer, a cordless phone, a wireless local loop (WLL) station, a tablet computer, a camera, a gaming device, a netbook, a smartbook, an ultrabook, a medical device or equipment, a biometric sensor / device, a wearable device (e.g., a smart watch, smart clothing, smart glasses, a smart wristband, smart jewelry (e.g., a smart ring, a smart bracelet)), an entertainment device (e.g., a music or video device or satellite radio), a vehicle component or sensor, a smart meter / sensor, industrial manufacturing equipment, a global positioning system device, or any other suitable device configured to communicate via a wireless or wired medium.

[0040] Some UEs may be considered machine type communication (MTC) or evolved or enhanced machine type communication (eMTC) UEs. MTC and eMTC UEs include, for example, robots, drones, remote devices, sensors, meters, monitors, location tags, etc., which can communicate with base stations, other devices (e.g., remote devices), or some other entities. A wireless node may provide, for example, a connection to a network (e.g., a wide area network such as the Internet or a cellular network) or to a network via a wired or wireless communication link. Some UEs may be considered Internet of Things (IoT) devices and / or may be implemented as NB-IoT (narrowband Internet of Things) devices. Some UEs may be considered customer premises equipment (CPE). UE 120 may be included within a housing that houses components of UE 120, such as a processor component, a memory component, etc. In some aspects, the processor component and the memory component may be coupled together. For example, a processor component (e.g., one or more processors) and a memory component (e.g., a memory) may be operatively coupled, communicatively coupled, electronically coupled, electrically coupled, etc.

[0041] In general, any number of wireless networks can be deployed in a given geographic area. Each wireless network can support a specific RAT and can operate on one or more frequencies. RATs can also be referred to as radio technologies, air interfaces, etc. Frequencies can also be referred to as carriers, frequency channels, etc. Each frequency can support a single RAT in a given geographic area to avoid interference between wireless networks of different RATs. In some cases, NR or 5G RAT networks can be deployed.

[0042] In some aspects, two or more UEs 120 (e.g., shown as UE 120a and UE 120e) can communicate directly using one or more sidelink channels (e.g., without using base station 110 as an intermediary for communicating with each other). For example, the UEs 120 can communicate using peer-to-peer (P2P) communication, device-to-device (D2D) communication, vehicle-to-everything (V2X) protocols (e.g., which may include vehicle-to-vehicle (V2V) protocols, vehicle-to-infrastructure (V2I) protocols, etc.), mesh networks, etc. In this case, the UEs 120 can perform scheduling operations, resource selection operations, and / or other operations described elsewhere herein as being performed by the base station 110.

[0043] Devices of the wireless network 100 can communicate using an electromagnetic spectrum, which can be subdivided into various categories, bands, channels, etc. based on frequency or wavelength. For example, devices of the wireless network 100 can communicate using an operating band having a first frequency range (FR1) (which can span 410 MHz to 7.125 GHz) and / or can communicate using an operating band having a second frequency range (FR2) (which can span 24.25 GHz to 52.6 GHz). Frequencies between FR1 and FR2 are sometimes referred to as mid-band frequencies. Although a portion of FR1 is greater than 6 GHz, FR1 is often referred to as a "sub-6 GHz" band. Similarly, FR2 is often referred to as a "millimeter wave" band, although it is different from the extremely high frequency (EHF) band (30 GHz-300 GHz) identified as a "millimeter wave" band by the International Telecommunication Union (ITU). Thus, unless expressly stated otherwise, it should be understood that the term "sub-6 GHz," etc., if used herein, may broadly refer to frequencies less than 6 GHz, frequencies within FR1, and / or mid-band frequencies (e.g., greater than 7.125 GHz). Similarly, unless expressly stated otherwise, it should be understood that the term "millimeter wave," etc., if used herein, may broadly refer to frequencies within the EHF band, frequencies within FR2, and / or mid-band frequencies (e.g., less than 24.25 GHz). It is contemplated that the frequencies included in FR1 and FR2 may be modified, and the techniques described herein are applicable to those modified frequency ranges.

[0044] As mentioned above, providing Figure 1 As an example. Other examples may differ from the Figure 1 Examples described.

[0045] Figure 2 is a diagram illustrating an example 200 of base station 110 communicating with UE 120 in wireless network 100 in accordance with various aspects of the present disclosure. Base station 110 may be equipped with T antennas 234a through 234t, and UE 120 may be equipped with R antennas 252a through 252r, where, in general, T ≥ 1 and R ≥ 1.

[0046] At the base station 110, the transmit processor 220 may receive data for one or more UEs from the data source 212, select one or more modulation and coding schemes (MCS) for each UE based at least in part on a channel quality indicator (CQI) received from the UE, process (e.g., encode and modulate) the data for each UE based at least in part on the MCS selected for the UE, and provide data symbols for all UEs. The transmit processor 220 may also process system information (e.g., for semi-static resource partitioning information (SRPI) and control information (e.g., CQI requests, grants, upper layer signaling, etc.) and provide overhead symbols and control symbols. The transmit processor 220 may also generate reference symbols for reference signals (e.g., cell-specific reference signals (CRS), demodulation reference signals (DMRS), etc.) and synchronization signals (e.g., primary synchronization signals (PSS) and secondary synchronization signals (SSS)). A transmit (TX) multiple-input, multiple-output (MIMO) processor 230 may perform spatial processing (e.g., precoding) on ​​data symbols, control symbols, overhead symbols, and / or reference symbols, as applicable, and may provide T output symbol streams to T modulators (MODs) 232a through 232t. Each modulator 232 may process a respective output symbol stream (e.g., for OFDM, etc.) to obtain an output sample stream. Each modulator 232 may further process (e.g., convert to analog, amplify, filter, and frequency upconvert) the output sample stream to obtain a downlink signal. The T downlink signals from modulators 232a through 232t may be transmitted via T antennas 234a through 234t, respectively.

[0047] At UE 120, antennas 252a through 252r can receive downlink signals from base station 110 and / or other base stations and can provide received signals to demodulators (DEMODs) 254a through 254r, respectively. Each demodulator 254 can condition (e.g., filter, amplify, downconvert, and digitize) the received signal to obtain input samples. Each demodulator 254 can further process the input samples (e.g., for OFDM, etc.) to obtain received symbols. A MIMO detector 256 can obtain received symbols from all R demodulators 254a through 254r, perform MIMO detection on the received symbols where applicable, and provide detected symbols. A receive processor 258 can process (e.g., demodulate and decode) the detected symbols, provide decoded data for UE 120 to a data sink 260, and provide decoded control information and system information to a controller / processor 280. The term "controller / processor" can refer to one or more controllers, one or more processors, or a combination thereof. The channel processor may determine reference signal received power (RSRP), received signal strength indicator (RSSI), reference signal received quality (RSRQ), channel quality indicator (CQI), etc. In some aspects, one or more components of the UE 120 may be included in the housing 284.

[0048] The network controller 130 may include a communication unit 294, a controller / processor 290, and a memory 292. The network controller 130 may include, for example, one or more devices in a core network. The network controller 130 may communicate with the base station 110 via the communication unit 294.

[0049] On the uplink, at the UE 120, a transmit processor 264 may receive and process data from a data source 262 and control information (e.g., for reports including RSRP, RSSI, RSRQ, CQI, etc.) from the controller / processor 280. The transmit processor 264 may also generate reference symbols for one or more reference signals. The symbols from the transmit processor 264 may be precoded by a TX MIMO processor 266, if applicable, further processed by modulators 254a through 254r (e.g., for DFT-s-OFDM, CP-OFDM, etc.), and transmitted to the base station 110. In some aspects, the UE 120 includes a transceiver. The transceiver may include any combination of antenna(s) 252, a modulator and / or demodulator 254, a MIMO detector 256, a receive processor 258, a transmit processor 264, and / or a TX MIMO processor 266. The transceiver may be used by a processor (eg, controller / processor 280) and memory 282 to perform operations described herein (eg, as described with reference to Figures 3 to 10 any aspects of any method described).

[0050] At base station 110, uplink signals from UE 120 and other UEs may be received by antenna 234, processed by demodulator 232, detected by MIMO detector 236, if applicable, and further processed by receive processor 238 to obtain decoded data and control information sent by UE 120. Receive processor 238 may provide the decoded data to a data sink 239 and the decoded control information to controller / processor 240. Base station 110 may include a communication unit 244 and communicate with network controller 130 via communication unit 244. Base station 110 may include a scheduler 246 to schedule UE 120 for downlink and / or uplink communications. In some aspects, base station 110 includes a transceiver. The transceiver may include any combination of antenna(s) 234, modulator and / or demodulator 232, MIMO detector 236, receive processor 238, transmit processor 220, and / or TX MIMO processor 230. The transceiver may be used by a processor (eg, controller / processor 240) and memory 242 to perform operations described herein (eg, as described with reference to Figures 3 to 10 any aspects of any method described).

[0051] The controller / processor 240 of the base station 110, the controller / processor 280 of the UE 120, and / or Figure 2 Any other component of FIG2 may perform one or more techniques associated with interfaces for over-the-air (OTA) model aggregation in a joint system, as described in more detail elsewhere herein. For example, the controller / processor 240 of the base station 110, the controller / processor 280 of the UE 120, and / or any other component in FIG2 may perform or direct, for example, Figure 5 The process of 500 Figure 6 The process of 600 Figure 7 700 and / or other processes described herein. Memories 242 and 282 may store data and program codes for base station 110 and UE 120, respectively. In some aspects, memory 242 and / or memory 282 may include a non-transitory computer-readable medium storing one or more instructions (e.g., code, program code, etc.) for wireless communications. For example, the one or more instructions, when executed by one or more processors of base station 110 and / or UE 120 (e.g., directly, or after compilation, conversion, interpretation, etc.), may cause the one or more processors, UE 120, and / or base station 110 to perform or direct, for example, Figure 5 The process of 500 Figure 6 The process of 600 Figure 7In some aspects, executing instructions includes running instructions, converting instructions, compiling instructions, interpreting instructions, etc.

[0052] In some aspects, the UE 120 includes: means for determining a quantization parameter in a recurrent neural network (RNN) or for deriving a gradient of the RNN based at least in part on artificial intelligence (AI) modeling at the UE as part of a federated edge learning system; means for generating a message indicating the quantization parameter or gradient determined by the UE, the message comprising a medium access control (MAC) protocol data unit (PDU) or a set of bits obtained from a MAC layer, a packet data convergence protocol layer, or an application layer; and / or means for transmitting the message to a base station on a physical uplink shared channel (PUSCH) radio resource that overlaps with a PUSCH radio resource used by other UEs. Means for the UE 120 to perform the operations described herein may include, for example, an antenna 252, a demodulator 254, a MIMO detector 256, a receive processor 258, a transmit processor 264, a TX MIMO processor 266, a modulator 254, a controller / processor 280, and / or a memory 282.

[0053] In some aspects, the UE 120 includes means for receiving a configuration for generating the message, the configuration comprising one or more of: a number of consecutive bits to be modulated into an analog symbol, a modulation and coding scheme (MCS), or a number of analog modulated bits to be carried by the radio resources of the PUSCH.

[0054] In some aspects, the UE 120 includes means for determining a modulation scheme based at least in part on one or more new MCS values ​​indicated in the configuration.

[0055] In some aspects, the UE 120 includes means for receiving a configuration for generating the message, the configuration based at least in part on one or more of: downlink control information (DCI), a MAC control element (MAC CE), or a radio resource control (RRC) message.

[0056] In some aspects, the UE 120 includes means for receiving a configuration for generating the message, the configuration based at least in part on a configured granted PUSCH (CG-PUSCH) specified for AI modeling.

[0057] In some aspects, the UE 120 includes means for disabling channel coding based at least in part on one or more of: a DCI, a MAC control element, or an RRC message.

[0058] In some aspects, the UE 120 includes means for disabling channel coding based at least in part on receiving an indication of one or more new MCS values.

[0059] In some aspects, the UE 120 includes means for disabling channel coding based at least in part on one or more of: determining that CG-PUSCH is configured for radio resources that overlap on PUSCH, or determining that no MCS is configured or indicated for PUSCH.

[0060] In some aspects, the UE 120 includes means for encoding quantization parameters or gradients prior to modulation based at least in part on a neural network after disabling channel coding.

[0061] In some aspects, the base station 110 includes: means for determining, at each of the plurality of UEs, a quantization parameter for an AI-modeled RNN associated with the federated edge learning system or a gradient for deriving the RNN based on messages received on overlapping PUSCH resources from the plurality of UEs, each message including a MAC PDU or a set of bits indicating the quantization parameter or gradient; means for aggregating the quantization parameters or gradients from the plurality of UEs to update a global model; and / or means for sending the updated global model to the plurality of UEs. Means for the base station 110 to perform the operations described herein may include, for example, a transmit processor 220, a TX MIMO processor 230, a modulator 232, an antenna 234, a demodulator 232, a MIMO detector 236, a receive processor 238, a controller / processor 240, a memory 242, and / or a scheduler 246.

[0062] In some aspects, the base station 110 includes means for sending a configuration for generating each message, the configuration including one or more of: a number of consecutive bits to be modulated into an analog symbol, an MCS, or a number of analog modulated bits to be carried by the radio resources of the PUSCH.

[0063] In some aspects, the base station 110 includes means for transmitting a configuration for generating the message, the configuration based at least in part on the CG-PUSCH specified for AI modeling.

[0064] In some aspects, the UE 120 includes means for determining that quantization parameters or gradients are to be centrally aggregated as part of a federated edge learning system, and / or means for disabling channel coding based at least in part on determining that quantization parameters or gradients are to be centrally aggregated. Means for the UE 120 to perform the operations described herein may include, for example, antennas 252, demodulators 254, MIMO detectors 256, receive processors 258, transmit processors 264, TX MIMO processors 266, modulators 254, controllers / processors 280, and / or memory 282.

[0065] Although Figure 2 The blocks in FIG. 2 are shown as distinct components, but the functionality described above with reference to the blocks may be implemented in a single hardware, software, or combined component or in various combinations of components. For example, the functionality described with respect to the transmit processor 264, the receive processor 258, and / or the TX MIMO processor 266 may be performed by or under the control of the controller / processor 280.

[0066] As mentioned above, providing Figure 2 As an example. Other examples can be related to Figure 2 The examples described are different.

[0067] Figure 3 is a diagram illustrating an example 300 of federated edge learning in accordance with various aspects of the present disclosure. Figure 3 A federated edge learning system is shown with an edge device (eg, UE 120 ) and an edge server (eg, base station 110 ) at a cell edge that can communicate with each other.

[0068] Many services seek to improve accuracy and performance through machine learning and AI models. This learning has typically occurred at the center of a cloud computing system. However, due to the large amounts of data that may be involved, this learning has been moved from the cloud center to the edge of the network, where edge devices have fast access to real-time data. Each edge device can train a local AI model (e.g., a recurrent neural network (RNN)) and provide parameters related to the local AI model to a centralized edge server for training a global AI model. There may not be enough radio resources to wirelessly send large amounts of data from each edge device to the edge server for AI model training, and therefore federated edge learning can be used to train local models at the edge devices.

[0069] like Figure 3As shown, the edge device can send the parameters of the local model or the gradients used to derive the local model to the edge server to update the global model. The global model can be updated by aggregating (e.g., averaging) the parameters or gradients. The edge server can then broadcast the global model to the edge device to improve service and performance at the local and / or global levels. Because the original data may not be required, sending parameters or gradients can provide better data privacy. In addition, the edge server can avoid consuming a large amount of radio resources and experiencing the delay that occurs with the transmission of such raw data. However, transmitting parameters or gradients may still consume a large amount of radio resources because a 50-layer neural network may have, for example, approximately 26 million parameters.

[0070] In some aspects, edge devices can use broadband analog aggregation (BAA) in a federated edge learning system. BAA exploits simultaneous transmissions over multiple access channels using waveform overlay, where radio resources fully overlap for multiple edge devices. BAA builds on the concept of air computing (AirComp), which involves analog transmissions over multiple access channels without decoding and with channel pre-equalization for each OFDM tone. Pre-equalization can include using truncated channel inversion or channel-based power modulation. With pre-equalization, parameters can be received at the edge server (e.g., gNB) from different edge devices with the same amplitude to simplify averaging at the edge server.

[0071] As pointed out above, Figure 3 are provided as examples. Other examples may differ from those regarding Figure 3 Examples described.

[0072] When preparing for transmission, the UE may forward the MAC PDU as a binary sequence from the UE's MAC layer to the physical (PHY) layer. The UE may form each MAC PDU into a transport block for channel coding, rate matching, modulation, and mapping to resource elements. The UE may determine the transport block size based on the MCS (e.g., quadrature amplitude modulation (QAM)), random access procedure, and / or rate matching mode. However, the conventional PHY-MAC interface does not support over-the-air computing. If the edge device (e.g., UE) quantizes the parameters or gradients of the local AI model into a binary sequence, the base station associated with the edge server will not be able to interpret the binary sequence as parameters or gradients of the AI ​​model at the MAC or PHY layer. As a result, the edge server and edge devices of the joint edge learning system may be subject to MAC / PHY limitations on data transfer for OTA model aggregation. As a result, the AI ​​model may not be updated quickly and the performance of the edge device may be degraded.

[0073] According to various aspects described herein, a base station may configure an edge device (e.g., UE) to use a MAC layer and / or a PHY layer to better support federated learning AI model aggregation. For example, a UE may send a MAC PDU on a physical uplink shared channel (PUSCH) as a quantization parameter or gradient for AI model aggregation as part of federated edge learning. The UE may use PHY layer slices for model aggregation. In some aspects, the UE may form a specific bit set to indicate the quantization parameter or gradient for federated learning AI model aggregation. The UE may obtain the bit set directly from the MAC layer, the packet data convergence protocol layer, or the application layer. The base station may receive a MAC PDU or a specific bit set and interpret it as a quantization parameter or gradient, and use the parameter or gradient to update the global model. As a result, the edge server and edge device of the federated edge learning system may update the AI ​​model faster, and the performance of the edge device may be improved.

[0074] Figure 4 4 is a diagram illustrating an example of an interface 400 for OTA model aggregation in a federated system according to various aspects of the present disclosure. Figure 4 As shown, example 400 includes BS 410 (e.g., Figure 1 and Figure 2 BS 110) and UE 420 (eg, Figure 1 and Figure 2 120). BS 410 may also communicate with other UEs 430, 440. In some aspects, BS 410 and UEs 420, 430, 440 may be included in a wireless network, such as wireless network 100. BS 410 and UEs 420, 430, 440 may communicate over a wireless access link, which may include an uplink and a downlink. BS 410 may be associated with an edge server of a federated edge learning system, and UEs 420, 430, 440 may be edge devices of the federated edge learning system that provide AI model parameter or gradient updates to the edge server to update the global model.

[0075] The UE 420 may perform AI modeling or some type of machine learning to train and / or use a local model for data processed by the UE 420. For example, the UE 420 may be part of an autonomous driving application for a vehicle, and data from the UE 420 may be used to update applications or services for all vehicles using the autonomous driving application. As shown by reference numeral 450, the UE 420 may determine quantization parameters in an RNN of the local model or gradients for deriving the RNN based at least in part on the local AI modeling as part of the federated edge learning system.

[0076] UE 420 may quantize a parameter or gradient for transmission on a multiple access channel. As shown by reference numeral 455, UE 420 may generate a message to indicate the quantization parameter or gradient. The message may be a MAC PDU, wherein the MAC PDU has not been previously configured to indicate the quantization parameter or gradient to the base station. Alternatively, a MAC PDU is not used. Instead, a specific bit set (e.g., a binary sequence) may be used to indicate the quantization parameter or gradient. UE 420 may obtain the bit set at the PHY layer from the MAC layer, the Packet Data Convergence Protocol (PDCP) layer, or the application layer.

[0077] As part of the over-the-air computation transmission of this message, or even for BAA, bits representing the quantization parameter or gradient may be modulated onto analog symbols. In some aspects, the BS 410 may send a configuration for generating this message to the UE 420, which may determine how the message is sent, including how to map the binary sequence of bits or MAC PDU into the analog constellation of the MCS.

[0078] The configuration may indicate the number of consecutive bits to be modulated into analog symbols and / or the number of analog modulated bits to be carried by the radio resources of the PUSCH. The UE 420 may determine the number of analog modulated bits based on an explicit indication in the configuration or implicitly based on the number of consecutive bits to be modulated into analog symbols and / or the random access procedure of the PUSCH. The UE 420 may determine the configuration based at least in part on a DCI, a MAC CE, or an RRC message. The configuration may also be based at least in part on one or more CG-PUSCH configurations. Certain CG-PUSCHs may correspond to transmissions based on model aggregation.

[0079] In some aspects, the configuration may also indicate an MCS. The MCS may be a modulation scheme (e.g., pulse amplitude modulation (PAM), QAM, phase shift keying (PSK)) with a refined bit-to-constellation mapping to make averaging easier for BS 410. For example, the bit-to-constellation mapping may be specified using a more linear range so that coefficients from UE 420, UE 430, UE 440, and any other UEs may be successfully averaged. The MCS may include a bit-to-constellation mapping between a quantized complex or real value and its position in the constellation plane. For example, for 4QAM or quadrature PSK (QPSK), the value "11" may be mapped to position "1+1j" on the constellation plane. Similarly, "10" may be mapped to "1-1j," "01" may be mapped to "-1+1j," and "00" may be mapped to "-1-1j." For an example with 4-amplitude shift keying (4ASK), "11" may be mapped to 3, "10" may be mapped to 1, "01" may be mapped to -1, and "00" may be mapped to -3. The bit-to-constellation mapping may be arranged for AI model aggregation at BS 410 or at an edge server otherwise associated with BS 410. For example, the edge server or BS 410 may average a "1" from UE 420 and a "-3" from UE 430 to obtain -1 as a parameter for the updated global model. Of course, the averaging may be performed on a larger scale for a larger amount of data from UE 420, UE 430, and UE 440. In some aspects, certain bit-to-constellation mappings may be associated with and / or triggered by preparations for sending the above-mentioned MAC PDUs or sets of bits as part of a federated edge learning system.

[0080] In some aspects, the MCS may be a new MCS, or an MCS not found in a legacy MCS or an MCS typically defined at the UE for transmission. The configuration may also introduce new bit-to-constellation rules. For example, a quantized bit (or group of bits) may be mapped to a complex or real value representing a value associated with the group of quantized bits in the constellation plane. In another example, for QAM, the configuration may indicate the use of a real axis for quantized bits representing a first set of real values ​​and an imaginary axis for quantized bits representing a second set of real values. In some aspects, the MCS may be selected from a predefined or preconfigured MCS.

[0081] As indicated by reference numeral 460, UE 420 may transmit the message on a PUSCH radio resource that overlaps with other PUSCH radio resources from UE 430 and UE 440. UE 420 may transmit the message such that it is transmitted concurrently with other messages as part of a BAA or simulated aggregated OTA transmission that exploits the waveform superposition properties of multiple access channels. This may involve an over-the-air computing implementation in which the message is transmitted as a simulated communication without channel coding.

[0082] In some aspects, if an analog constellation is to be used, the UE 420 may disable channel coding. The UE 420 may disable channel coding based at least in part on an explicit indication, such as an indication in a DCI, MAC CE, or RRC message. The UE 420 may disable channel coding based at least in part on receiving an indication of one or more new MCSs or an MCS that is not regularly configured for transmission. Alternatively or additionally, the UE 420 may disable channel coding based at least in part on an implicit indication. For example, the UE 420 may disable channel coding based at least in part on determining that the CG-PUSCH is configured for radio resources overlapping on the PUSCH or that the CG-PUSCH is configured to operate in an analog modulation mode. If no MCS is configured or indicated for the PUSCH, the UE 420 may disable channel coding.

[0083] If channel coding is disabled, some type of source coding may still be present for compression and error control. For example, the UE 402 may use a neural network to encode quantization parameters or gradients prior to modulation. For example, the input to the modulator may be the output of the neural network. The BS 410 may configure or instruct the neural network and dynamically activate such source coding via DCI, MAC CE, or RRC messages.

[0084] As shown by reference numeral 465, BS 410 may aggregate quantization parameters and / or gradients from UE 420, UE 430, and UE 440, as well as other UEs. This may include averaging the parameters and / or gradients to update a global model. The global model may represent an improvement in service to the UE without processing the original data from the UE. As shown by reference numeral 470, BS 410 may send (e.g., unicast, broadcast) the updated global model to UE 420 and other UEs. This may include an indication of what to update in the local model based at least in part on the updated global model. As a result, the UE may operate with improved performance, which may save time, power, processing resources, and signaling resources at the UE.

[0085] As pointed out above, Figure 4 are provided as examples. Other examples may differ from those regarding Figure 4 Examples described.

[0086] Figure 5 5 is a diagram illustrating an example process 500 performed, for example, by a UE, according to various aspects of the present disclosure. The example process 500 is a diagram illustrating an example process 500 performed, for example, by a UE, Figure 1 and Figure 2 UE 120 depicted in Figure 3 The edge devices depicted in Figure 4 An example of a UE 420 depicted in FIG. 4 performing operations associated with an interface for OTA model aggregation in a federated system.

[0087] like Figure 5 As shown, in some aspects, process 500 may include determining quantization parameters in the RNN or gradients for deriving the RNN based at least in part on AI modeling at the UE as part of the federated edge learning system (block 510). For example, as described above, the UE (e.g., using Figure 8 The determining component 808 depicted in can determine quantization parameters in the RNN or gradients for deriving the RNN based at least in part on AI modeling at the UE as part of the federated edge learning system.

[0088] like Figure 5 As further shown, in some aspects, process 500 may include generating a message indicating a quantization parameter or gradient determined by the UE, the message comprising a MAC PDU or a set of bits obtained from the MAC layer, PDCP layer, or application layer (block 520). For example, as described above, the UE (e.g., using Figure 8 The generating component 810 depicted in FIG may generate a message indicating a quantization parameter or gradient determined by the UE, the message comprising a MAC PDU or a set of bits obtained from a MAC, PDCP layer, or an application layer.

[0089] like Figure 5 As further shown, in some aspects, process 500 may include sending the message to the base station on PUSCH radio resources that overlap with PUSCH radio resources used by other UEs (block 530). For example, as described above, a UE (e.g., using Figure 8 The transmitting component 804 depicted in FIG may transmit the message to the base station on PUSCH radio resources that overlap with PUSCH radio resources used by other UEs.

[0090] Process 500 may include additional aspects, such as any single aspect or any combination of aspects as described below and / or in combination with one or more other processes described elsewhere herein.

[0091] In a first aspect, process 500 includes receiving a configuration for generating the message, the configuration including one or more of: a number of consecutive bits to be modulated into an analog symbol, an MCS, or a number of analog modulated bits to be carried by radio resources of a PUSCH.

[0092] In a second aspect, alone or in combination with the first aspect, the configuration for generating the message includes an MCS having a bit-to-constellation mapping between quantized complex or real values ​​and positions of the quantized complex or real values ​​in a constellation plane. The bit-to-constellation mapping is arranged for AI model aggregation at the base station.

[0093] In a third aspect, alone or in combination with one or more of the first and second aspects, the arrangement for generating the message comprises an arrangement for mapping a quantized bit group to a complex or real valued MCS representing a value associated with the quantized bit group in a constellation plane.

[0094] In a fourth aspect, alone or in combination with one or more of the first to third aspects, the configuration for generating the message specifies, for QAM, the use of a real axis for quantized bits representing a first set of real values ​​and an imaginary axis for quantized bits representing a second set of real values.

[0095] In a fifth aspect, alone or in combination with one or more of the first to fourth aspects, process 500 includes determining a modulation scheme based at least in part on one or more new MCS values ​​indicated in the configuration.

[0096] In a sixth aspect, alone or in combination with one or more of the first to fifth aspects, the configuration for generating the message includes an MCS value selected from a plurality of predefined MCS values.

[0097] In a seventh aspect, alone or in combination with one or more of the first to sixth aspects, process 500 includes receiving a configuration for generating the message, the configuration being based at least in part on one or more of a DCI, a MACCE, or an RRC message.

[0098] In an eighth aspect, alone or in combination with one or more of the first to seventh aspects, the process 500 includes receiving a configuration for generating the message, the configuration being based at least in part on a CG-PUSCH specified for AI modeling.

[0099] In a ninth aspect, alone or in combination with one or more of the first to eighth aspects, process 500 includes disabling channel coding based at least in part on one or more of a DCI, a MAC CE, or an RRC message.

[0100] In a tenth aspect, alone or in combination with one or more of the first to ninth aspects, process 500 includes disabling channel coding based at least in part on receiving an indication of one or more new MCS values.

[0101] In the eleventh aspect, alone or in combination with one or more of the first to tenth aspects, process 500 includes disabling channel coding based at least in part on determining that the CG-PUSCH is configured for radio resources overlapping on the PUSCH, or determining that one or more of the MCSs are not configured or indicated for the PUSCH.

[0102] In a twelfth aspect, alone or in combination with one or more of the first to eleventh aspects, process 500 includes encoding a quantization parameter or gradient based at least in part on a neural network before modulation after disabling channel coding.

[0103] although Figure 5 Example blocks of process 500 are shown, but in some aspects, process 500 may include Figure 5 Additional blocks, fewer blocks, different blocks, or a different arrangement of blocks than those shown in . Additionally or alternatively, two or more of the blocks in process 500 may be executed in parallel.

[0104] Figure 6 is a diagram illustrating an example process 600, for example, performed by a base station, according to various aspects of the present disclosure. The example process 600 is a diagram illustrating an example process 600 performed by a base station (for example, Figures 1 to 2 The base station 110 depicted in Figure 3 The edge server depicted in Figure 4 An example of a base station 410 depicted in FIG performing operations associated with an interface for OTA model aggregation in a federated system.

[0105] like Figure 6 As shown, in some aspects, process 600 may include determining, at each of the plurality of UEs, a quantization parameter of an AI-modeled RNN associated with a federated edge learning system or a gradient for deriving the RNN based on messages received on overlapping PUSCH resources from the plurality of UEs, each message including a MAC PDU or set of bits indicating the quantization parameter or gradient (block 610). For example, as described above, a base station (e.g., using Figure 9 The determining component 908 depicted in the figure can determine a quantization parameter of an AI-modeled RNN associated with a federated edge learning system or a gradient for deriving the RNN at each of the multiple UEs based on messages received on overlapping PUSCH resources from the multiple UEs, each message including a MAC PDU or a bit set indicating the quantization parameter or gradient.

[0106] like Figure 6 As further shown, in some aspects, process 600 may include aggregating quantization parameters or gradients from multiple UEs to update the global model (block 620). For example, as described above, a base station (e.g., using Figure 9 The aggregation component 910 depicted in FIG may aggregate quantization parameters or gradients from multiple UEs to update a global model.

[0107] like Figure 6 As further shown, in some aspects, process 600 may include sending the updated global model to the plurality of UEs (block 630). For example, as described above, a base station (e.g., using Figure 9 The sending component 904 described in can send the updated global model to multiple UEs.

[0108] Process 600 may include additional aspects, such as any single aspect or any combination of aspects as described below and / or in combination with one or more other processes described elsewhere herein.

[0109] In a first aspect, the set of bits from the plurality of UEs is obtained at each of the plurality of UEs from a MAC layer, a PDCP layer, or an application layer.

[0110] In a second aspect, alone or in combination with the first aspect, aggregating the quantization parameters or gradients from multiple UEs includes averaging the quantization parameters or gradients from the multiple UEs.

[0111] In a third aspect, alone or in combination with one or more of the first and second aspects, the set of bits is in a format for averaging quantization parameters or gradients from multiple UEs.

[0112] In a fourth aspect, alone or in combination with one or more of the first to third aspects, process 600 includes sending a configuration for generating each message, the configuration including the number of consecutive bits to be modulated into an analog symbol, the MCS, or the number of analog modulated bits to be carried by the radio resources of the PUSCH.

[0113] In a fifth aspect, alone or in combination with one or more of the first to fourth aspects, the configuration for generating the message includes an MCS having a bit-to-constellation mapping between quantized complex or real values ​​and positions of the quantized complex or real values ​​in a constellation plane.

[0114] In a sixth aspect, alone or in combination with one or more of the first to fifth aspects, the configuration for generating the message includes a configuration for mapping a quantized bit group to a complex or real-valued MCS representing a value associated with the quantized bit group in a constellation plane.

[0115] In a seventh aspect, alone or in combination with one or more of aspects 1 to 6, the configuration for generating the message specifies, for QAM, the use of a real axis for quantized bits representing a first set of real values ​​and an imaginary axis for quantized bits representing a second set of real values.

[0116] In an eighth aspect, alone or in combination with one or more of the first to seventh aspects, process 600 includes sending a configuration for generating the message, the configuration being based at least in part on a CG-PUSCH specified for AI modeling.

[0117] although Figure 6 Example blocks of process 600 are shown, but in some aspects, process 600 may include Figure 6 Additional blocks, fewer blocks, different blocks, or a different arrangement of blocks than those shown in . Additionally or alternatively, two or more blocks of process 600 may be performed in parallel.

[0118] Figure 7 7 is a diagram illustrating an example process 700 performed, for example, by a UE, according to various aspects of the present disclosure. The example process 700 is a diagram illustrating an example process 700 performed, for example, by a UE, Figures 1 to 2 UE 120 depicted in Figure 3 The edge devices depicted in Figure 4 An example of a UE 420 depicted in FIG. 4 performing operations associated with an interface for OTA model aggregation in a federated system.

[0119] like Figure 7 As shown, in some aspects, process 700 may include determining that quantization parameters or gradients are to be centrally aggregated as part of a federated edge learning system (block 710). For example, as described above, a UE (e.g., using Figure 10 The determining component 1008 depicted in can determine that as part of the federated edge learning system, quantization parameters or gradients are to be centrally aggregated.

[0120] like Figure 7 As further shown, in some aspects, process 700 may include disabling channel coding based at least in part on determining that the quantization parameter or gradient is to be aggregated (block 720). For example, as described above, the UE (e.g., using Figure 10 The disabling component 1010 depicted in FIG can disable channel coding based at least in part on determining that quantization parameters or gradients are to be centrally aggregated.

[0121] Process 700 may include additional aspects, such as any single aspect or any combination of aspects as described below and / or in combination with one or more other processes described elsewhere herein.

[0122] In a first aspect, determining that quantization parameters or gradients are to be collectively aggregated includes receiving an indication of one or more new MCS values.

[0123] In a second aspect, alone or in combination with the first aspect, determining that quantization parameters or gradients are to be aggregated includes receiving a CG-PUSCH configured for radio resources overlapping on a PUSCH.

[0124] In a third aspect, alone or in combination with the first or second aspects, process 700 includes encoding quantization parameters or gradients for one or more of compression or error control after disabling channel coding.

[0125] although Figure 7 Example blocks of process 700 are shown, but in some aspects, process 700 may include Figure 7 Additional blocks, fewer blocks, different blocks, or a different arrangement of blocks than those shown in . Additionally or alternatively, two or more blocks of process 700 may be performed in parallel.

[0126] Figure 8 800 is a block diagram of an example apparatus 800 for wireless communication. Apparatus 800 may be an edge device (e.g., a UE), or an edge device or a UE may include apparatus 800. In some aspects, apparatus 800 includes a receiving component 802 and a transmitting component 804, which may communicate with each other (e.g., via one or more buses and / or one or more other components). As shown, apparatus 800 may communicate with another apparatus 806 (such as a UE, a base station, or another wireless communication device) using receiving component 802 and transmitting component 804. As further shown, apparatus 800 may include one or more of a determining component 808, a generating component 810, and / or a disabling component 812, among other examples.

[0127] In some aspects, the apparatus 800 may be configured to perform the Figures 3 to 7 Additionally or alternatively, the apparatus 800 may be configured to perform one or more of the processes described herein, such as, Figure 5 Process 500. In some aspects, Figure 8 The apparatus 800 and / or one or more components shown in FIG. 8 may include the above-mentioned apparatus 800 and / or one or more components ... Figure 2 Additionally or alternatively, one or more components of the UE described. Figure 8 One or more components shown in the above may be implemented in combination with Figure 2Additionally or alternatively, one or more components in the set of components may be at least partially implemented as software stored in a memory. For example, a component (or portion of a component) may be implemented as instructions or code stored in a non-transitory computer-readable medium and executable by a controller or processor to perform the function or operation of the component.

[0128] The receiving component 802 may receive communications, such as reference signals, control information, data communications, or a combination thereof, from the apparatus 806. The receiving component 802 may provide the received communications to one or more other components of the apparatus 800. In some aspects, the receiving component 802 may perform signal processing (such as filtering, amplification, demodulation, analog-to-digital conversion, demultiplexing, deinterleaving, demapping, equalization, interference cancellation, or decoding) on ​​the received communications and may provide the processed signals to one or more other components of the apparatus 806. In some aspects, the receiving component 802 may include the processing described above in conjunction with Figure 2 One or more antennas, demodulators, MIMO detectors, receive processors, controllers / processors, memories, or combinations thereof of the described UE.

[0129] The transmitting component 804 may transmit communications, such as reference signals, control information, data communications, or a combination thereof, to the apparatus 806. In some aspects, one or more other components of the apparatus 806 may generate communications and may provide the generated communications to the transmitting component 804 for transmission to the apparatus 806. In some aspects, the transmitting component 804 may perform signal processing (such as filtering, amplification, modulation, digital-to-analog conversion, multiplexing, interleaving, mapping, or encoding) on ​​the generated communications and may transmit the processed signals to the apparatus 806. In some aspects, the transmitting component 804 may include the above-described components in conjunction with Figure 2 One or more antennas, modulators, transmit MIMO processors, transmit processors, controllers / processors, memories, or combinations thereof of the described UE. In some aspects, the transmitting component 804 can be co-located with the receiving component 802 in a transceiver.

[0130] The determining component 808 can determine a quantization parameter in the RNN or a gradient for deriving the RNN based at least in part on AI modeling at the UE as part of the federated edge learning system. In some aspects, the determining component 808 can include the above-mentioned combination of Figure 2 A controller / processor, memory, or a combination thereof of a described UE.

[0131] The generating component 810 may generate a message indicating a quantization parameter or gradient determined by the UE, the message comprising a MAC PDU or a set of bits obtained from the MAC layer, the PDCP layer, or the application layer. In some aspects, the generating component 810 may include the above in combination with Figure 2 One or more antennas, demodulators, MIMO detectors, receive processors, modulators, transmit MIMO processors, transmit processors, controllers / processors, memories, or combinations thereof of the described UE. The transmitting component 804 can transmit the message to the base station on PUSCH radio resources that overlap with PUSCH radio resources used by other UEs.

[0132] Receiving component 802 can receive a configuration for generating the message, the configuration comprising one or more of: a number of consecutive bits to be modulated into an analog symbol, an MCS, or a number of analog modulated bits to be carried by radio resources of a PUSCH.

[0133] The determining component 808 can determine a modulation scheme based at least in part on one or more new MCS values ​​indicated in the configuration. In some aspects, the determining component 808 can include the above-mentioned combination of Figure 2 One or more antennas, demodulators, MIMO detectors, receive processors, modulators, transmit MIMO processors, transmit processors, controllers / processors, memories, or combinations thereof of a described UE.

[0134] Receiving component 802 can receive a configuration for generating the message based at least in part on one or more of: a DCI, a MAC CE, or an RRC message.

[0135] Receiving component 802 can receive a configuration for generating the message based at least in part on a CG-PUSCH specified for AI modeling.

[0136] The disabling component 812 may disable channel coding based at least in part on one or more of: DCI, MAC CE, or RRC message. In some aspects, the disabling component 812 may include the above in combination with Figure 2One or more antennas, demodulators, MIMO detectors, receive processors, modulators, transmit MIMO processors, transmit processors, controllers / processors, memories, or combinations thereof of a UE described herein. The disabling component 812 may disable channel coding based at least in part on receiving an indication of one or more new MCS values. The disabling component 812 may disable channel coding based at least in part on one or more of: determining that the CG-PUSCH is configured for radio resources that overlap on the PUSCH, or determining that no MCS is configured or indicated for the PUSCH. The generating component 810 may, after disabling channel coding, encode a quantization parameter or gradient prior to modulation based at least in part on a neural network.

[0137] Figure 8 The number and arrangement of components shown in are provided as examples. In practice, there may be Figure 8 Additional components, fewer components, different components, or differently arranged components than those shown. Figure 8 Two or more components shown in may be implemented in a single component, or Figure 8 The single components shown in can be implemented as multiple, distributed components. Additionally or alternatively, Figure 8 The assembly of (one or more) components shown in the FIGURES may perform the operations described by Figure 8 One or more functions performed by another collection of components shown in .

[0138] Figure 9 900 is a block diagram of an example apparatus 900 for wireless communication. Apparatus 900 may be a base station, or a base station may include apparatus 900. In some aspects, apparatus 900 includes a receiving component 902 and a transmitting component 904, which may communicate with each other (e.g., via one or more buses and / or one or more other components). As shown, apparatus 900 may communicate with another apparatus 906 (such as a UE, a base station, or another wireless communication device) using receiving component 902 and transmitting component 904. As further shown, apparatus 900 may include one or more of a determining component 908 and / or an aggregating component 910, among other examples.

[0139] In some aspects, the apparatus 900 may be configured to perform the Figures 3 to 7 Additionally or alternatively, the apparatus 900 may be configured to perform one or more processes described herein, such as, Figure 6 Process 600. In some aspects, Figure 9 The apparatus 900 and / or one or more components shown in FIG. 1 may include the above-mentioned apparatus 900 and / or one or more components ... Figure 2 Additionally or alternatively, Figure 9 One or more components shown in the above may be implemented in combination with Figure 2 Additionally or alternatively, one or more components in the set of components may be at least partially implemented as software stored in a memory. For example, a component (or portion of a component) may be implemented as instructions or code stored in a non-transitory computer-readable medium and executable by a controller or processor to perform the function or operation of the component.

[0140] The receiving component 902 may receive communications, such as reference signals, control information, data communications, or a combination thereof, from the apparatus 906. The receiving component 902 may provide the received communications to one or more other components of the apparatus 900. In some aspects, the receiving component 902 may perform signal processing (such as filtering, amplification, demodulation, analog-to-digital conversion, demultiplexing, deinterleaving, demapping, equalization, interference cancellation, or decoding) on ​​the received communications and may provide the processed signals to one or more other components of the apparatus 906. In some aspects, the receiving component 902 may include the processing described above in conjunction with Figure 2 One or more antennas, demodulators, MIMO detectors, receive processors, controllers / processors, memories, or combinations thereof of the described base stations.

[0141] Transmit component 904 may transmit communications, such as reference signals, control information, data communications, or a combination thereof, to apparatus 906. In some aspects, one or more other components of apparatus 906 may generate communications and may provide the generated communications to transmit component 904 for transmission to apparatus 906. In some aspects, transmit component 904 may perform signal processing (such as filtering, amplification, modulation, digital-to-analog conversion, multiplexing, interleaving, mapping, or encoding) on ​​the generated communications and may transmit the processed signals to apparatus 906. In some aspects, transmit component 904 may include the above-described components in conjunction with Figure 2 One or more antennas, modulators, transmit MIMO processors, transmit processors, controllers / processors, memories, or combinations thereof of the described base stations. In some aspects, the transmit component 904 can be co-located with the receive component 902 in a transceiver.

[0142] The determining component 908 can determine a quantization parameter of an AI-modeled RNN associated with the federated edge learning system or a gradient for deriving the RNN at each of the plurality of UEs based on messages received on overlapping PUSCH resources from the plurality of UEs, each message including a MAC PDU or a bit set indicating the quantization parameter or gradient. In some aspects, the determining component 908 can include the above in combination with Figure 2 A controller / processor, memory, or a combination thereof of a base station is described.

[0143] Aggregation component 910 can aggregate quantization parameters or gradients from multiple UEs to update the global model. In some aspects, aggregation component 910 can include the above-mentioned Figure 2 The controller / processor, memory, or combination thereof of the described base station can be configured to transmit the updated global model to multiple UEs.

[0144] Transmitting component 904 can transmit a configuration for generating each message, the configuration comprising one or more of: a number of consecutive bits to be modulated into an analog symbol, an MCS, or a number of analog modulated bits to be carried by radio resources of a PUSCH.

[0145] Transmitting component 904 can transmit a configuration for generating the message based at least in part on the CG-PUSCH specified for AI modeling.

[0146] Figure 9 The number and arrangement of components shown in are provided as examples. In practice, there may be Figure 9 Additional components, fewer components, different components, or differently arranged components than those shown. Figure 9 Two or more components shown in may be implemented in a single component, or Figure 9 The single components shown in can be implemented as multiple, distributed components. Additionally or alternatively, Figure 9 The assembly of (one or more) components shown in the FIGURES may perform the operations described by Figure 9 One or more functions performed by another collection of components shown in .

[0147] Figure 10 1 is a block diagram of an example apparatus 1000 for wireless communication. Apparatus 1000 may be a UE, or a UE may include apparatus 1000. In some aspects, apparatus 1000 includes a receiving component 1002 and a transmitting component 1004, which may communicate with each other (e.g., via one or more buses and / or one or more other components). As shown, apparatus 1000 may communicate with another apparatus 1006 (such as a UE, a base station, or another wireless communication device) using receiving component 1002 and transmitting component 1004. As further shown, apparatus 1000 may include one or more of a determining component 1008 and / or a disabling component 1010, as well as other examples.

[0148] In some aspects, the apparatus 1000 may be configured to perform the Figures 3 to 7 Additionally or alternatively, the apparatus 1000 may be configured to perform one or more processes described herein, such as, Figure 7Process 700. In some aspects, Figure 10 The apparatus 1000 and / or one or more components shown in FIG. 1 may include the above-mentioned apparatus 1000 and / or one or more components ... Figure 2 Additionally or alternatively, one or more components of the UE described. Figure 10 One or more components shown in the above may be implemented in combination with Figure 2 Additionally or alternatively, one or more components in the set of components may be at least partially implemented as software stored in a memory. For example, a component (or portion of a component) may be implemented as instructions or code stored in a non-transitory computer-readable medium and executable by a controller or processor to perform the function or operation of the component.

[0149] The receiving component 1002 may receive communications, such as reference signals, control information, data communications, or a combination thereof, from the apparatus 1006. The receiving component 1002 may provide the received communications to one or more other components of the apparatus 1000. In some aspects, the receiving component 1002 may perform signal processing (such as filtering, amplification, demodulation, analog-to-digital conversion, demultiplexing, deinterleaving, demapping, equalization, interference cancellation, or decoding) on ​​the received communications and may provide the processed signals to one or more other components of the apparatus 1006. In some aspects, the receiving component 1002 may include the processing described above in conjunction with Figure 2 One or more antennas, demodulators, MIMO detectors, receive processors, controllers / processors, memories, or combinations thereof of the described UE.

[0150] The transmitting component 1004 may transmit communications, such as reference signals, control information, data communications, or a combination thereof, to the apparatus 1006. In some aspects, one or more other components of the apparatus 1006 may generate communications and may provide the generated communications to the transmitting component 1004 for transmission to the apparatus 1006. In some aspects, the transmitting component 1004 may perform signal processing (such as filtering, amplification, modulation, digital-to-analog conversion, multiplexing, interleaving, mapping, or encoding) on ​​the generated communications and may transmit the processed signals to the apparatus 1006. In some aspects, the transmitting component 1004 may include the above-described components in combination with the above-described components. Figure 2 One or more antennas, modulators, transmit MIMO processors, transmit processors, controllers / processors, memories, or combinations thereof of the described UE. In some aspects, the transmitting component 1004 can be co-located with the receiving component 1002 in a transceiver.

[0151] The determining component 1008 can determine that the quantization parameters or gradients are to be centrally aggregated as part of the federated edge learning system. In some aspects, the determining component 1008 can include the above-mentioned combination of Figure 2A controller / processor, memory, or a combination thereof of a described UE.

[0152] The disabling component 1010 may disable channel coding based at least in part on determining that the quantization parameter or gradient is to be aggregated. In some aspects, the disabling component 1010 may include the above-mentioned combination of Figure 2 One or more antennas, demodulators, MIMO detectors, receive processors, modulators, transmit MIMO processors, transmit processors, controllers / processors, memories, or combinations thereof of a described UE.

[0153] Figure 10 The number and arrangement of components shown in are provided as examples. In practice, there may be Figure 10 Additional components, fewer components, different components, or differently arranged components than those shown. Figure 10 Two or more components shown in may be implemented in a single component, or Figure 10 The single components shown in can be implemented as multiple, distributed components. Additionally or alternatively, Figure 10 The assembly of (one or more) components shown in the FIGURES may perform the operations described by Figure 10 One or more functions performed by another collection of components shown in .

[0154] The foregoing disclosure provides illustration and description, but is not intended to be exhaustive or to limit the various aspects to the precise forms disclosed. Modifications and variations may be made in light of the above disclosure or may be acquired from practice of the various aspects.

[0155] As used herein, the term "component" is intended to be broadly interpreted as hardware, firmware, and / or a combination of hardware and software. As used herein, a processor is implemented in hardware, firmware, and / or a combination of hardware and software. It will be apparent that the systems and / or methods described herein can be implemented in different forms of hardware, firmware, and / or a combination of hardware and software. The actual specialized control hardware and software code used to implement these systems and / or methods are not limitations of various aspects. Therefore, the operation and behavior of the systems and / or methods are not described herein with reference to specific software code - it is to be understood that software and hardware can be designed to implement the systems and / or methods based, at least in part, on the description herein.

[0156] As used herein, satisfying a threshold may refer to a value that is greater than a threshold, greater than or equal to a threshold, less than a threshold, less than or equal to a threshold, equal to a threshold, not equal to a threshold, etc., depending on the context.

[0157] Although specific feature combinations are recorded in the claims and / or disclosed in the specification, these combinations are not intended to limit the disclosure of the various aspects. In fact, many of these features can be combined in ways that are not recorded in the claims and / or disclosed in the specification. Although each dependent claim listed below can directly reference only one claim, the disclosure of the various aspects includes the combination of each dependent claim with any other claim in the claim set. A phrase referring to "at least one of" a list of items refers to any combination of those items, including single members. As an example, "at least one of a, b, or c" is intended to cover a, b, c, ab, ac, bc, and abc, as well as any combination with multiple identical elements (e.g., aa, aaa, aab, aac, abb, acc, bb, bbb, bbc, cc, and ccc, or any other order of a, b, and c).

[0158] Elements, actions or instructions used herein should not be interpreted as being critical or necessary unless clearly described. Moreover, as used herein, the articles "one" and "an" are intended to include one or more projects and can be used interchangeably with "one or more". In addition, as used herein, the article "said" is intended to include one or more projects cited in conjunction with the article "said", and can be used interchangeably with "said one or more". In addition, as used herein, the terms "set" and "group" are intended to include one or more projects (for example, related projects, unrelated projects, the combination of related projects and unrelated projects, etc.), and can be used interchangeably with "one or more". In the case where only one project is expected, phrases "only one" or similar languages ​​are used. Moreover, as used herein, the terms "have", "possess", "have" etc. are intended to be open terms. In addition, the phrase "based on" is intended to represent "at least partially based on", unless otherwise clearly stated. Furthermore, as used herein, the term "or" when used in serial form is intended to be inclusive and can be used interchangeably with "and / or" unless expressly stated otherwise (e.g., if used in combination with "either" or "only one of").

Claims

1. A method for wireless communication performed by a user equipment (UE), comprising: Determining quantization parameters in a recurrent neural network (RNN) or for deriving gradients of the RNN based at least in part on artificial intelligence (AI) modeling at the UE as part of a federated edge learning system; generating a message indicating the quantization parameter or gradient determined by the UE, the message comprising a medium access control MAC protocol data unit (PDU) or a set of bits obtained from a MAC layer, a packet data convergence protocol layer, or an application layer; and The message is sent to the network node on a Physical Uplink Shared Channel (PUSCH) radio resource that overlaps with PUSCH radio resources used by other UEs.

2. The method according to claim 1, further comprising: A configuration for generating the message is received, the configuration comprising one or more of: a number of consecutive bits to be modulated into an analog symbol, a modulation and coding scheme MCS, or a number of analog modulated bits to be carried by radio resources of a PUSCH.

3. The method according to claim 2, wherein: The configuration for generating the message includes an MCS having a bit-to-constellation mapping between quantized complex or real values ​​and positions of the quantized complex or real values ​​in a constellation plane, wherein the bit-to-constellation mapping is arranged for AI model aggregation at the network node.

4. The method according to claim 2, wherein: The configuration for generating the message includes an MCS for mapping a group of quantized bits to a complex or real value representing a value associated with the group of quantized bits in a constellation plane.

5. The method according to claim 2, wherein: For quadrature amplitude modulation, the configuration for generating the message specifies using a real axis for representing quantized bits of a first real-valued set and using an imaginary axis for representing quantized bits of a second real-valued set.

6. The method according to claim 2, further comprising: A modulation scheme is determined based at least in part on one or more new MCS values ​​indicated in the configuration.

7. The method according to claim 2, wherein: The configuration for generating the message includes an MCS value selected from a plurality of predefined MCS values.

8. The method according to claim 1, further comprising: A configuration for generating the message is received, the configuration based at least in part on one or more of: downlink control information, a MAC control element, or a radio resource control message.

9. The method according to claim 1, further comprising: A configuration for generating the message is received, the configuration being based at least in part on a configured granted PUSCH (CG-PUSCH) specified for the AI ​​modeling.

10. The method according to claim 1, further comprising: Channel coding is disabled based at least in part on one or more of: downlink control information, a MAC control element, or a radio resource control message.

11. The method according to claim 1 , further comprising: Channel coding is disabled based at least in part on receiving an indication of one or more new MCS values.

12. The method according to claim 1, further comprising: Channel coding is disabled based at least in part on one or more of: determining that a configured granted PUSCH, ie, CG-PUSCH, is configured for radio resources overlapping on the PUSCH, or determining that no MCS is configured or indicated for the PUSCH.

13. The method according to claim 1, further comprising: The quantization parameter or gradient is encoded based at least in part on a neural network before modulation after disabling channel coding.

14. A method of wireless communication performed by a network node, comprising: Determine, based on messages received on overlapping physical uplink shared channel (PUSCH) resources from a plurality of user equipments (UEs), a quantization parameter of a recurrent neural network (RNN) modeled by an artificial intelligence (AI) system associated with a federated edge learning system at each of the plurality of UEs or a gradient for deriving the RNN, each message including a medium access control (MAC) protocol data unit (PDU) or a bit set indicating the quantization parameter or gradient; aggregating the quantization parameters or gradients from the plurality of UEs to update a global model; as well as The updated global model is sent to the plurality of UEs.

15. The method according to claim 14, wherein The set of bits from the plurality of UEs is obtained from a MAC layer, a Packet Data Convergence Protocol layer, or an application layer at each of the plurality of UEs.

16. The method according to claim 14, wherein Aggregating the quantization parameters or gradients from the plurality of UEs includes averaging the quantization parameters or gradients from the plurality of UEs.

17. The method according to claim 16, wherein The set of bits is in a format for averaging the quantization parameters or gradients from the plurality of UEs.

18. The method according to claim 14, further comprising: A configuration for generating each message is sent, the configuration including one or more of the following: the number of consecutive bits to be modulated into analog symbols, the modulation and coding scheme MCS, or the number of analog modulated bits to be carried by the radio resources of the PUSCH.

19. The method according to claim 18, wherein The configuration for generating the message comprises an MCS having a bit-to-constellation mapping between quantized complex or real values ​​and positions of the quantized complex or real values ​​in a constellation plane.

20. The method according to claim 18, wherein The configuration for generating the message includes an MCS for mapping a group of quantized bits to a complex or real value representing a value associated with the group of quantized bits in a constellation plane.

21. The method according to claim 18, wherein For quadrature amplitude modulation, the configuration for generating the message specifies using a real axis for representing quantized bits of a first real-valued set and using an imaginary axis for representing quantized bits of a second real-valued set.

22. The method of claim 14, further comprising: A configuration for generating the message is sent, the configuration being based at least in part on a configured granted PUSCH (CG-PUSCH) specified for the AI ​​modeling.

23. A user equipment (UE) for wireless communication, comprising: Memory; as well as one or more processors operatively coupled to the memory, the memory and the one or more processors being configured to: Determining quantization parameters in a recurrent neural network (RNN) or for deriving gradients of the RNN based at least in part on artificial intelligence (AI) modeling at the UE as part of a federated edge learning system; generating a message indicating the quantization parameter or gradient determined by the UE, the message comprising a medium access control MAC protocol data unit (PDU) or a set of bits obtained from a MAC layer, a packet data convergence protocol layer, or an application layer; and The message is sent to the network node on a Physical Uplink Shared Channel (PUSCH) radio resource that overlaps with PUSCH radio resources used by other UEs.

24. The UE according to claim 23, wherein: The one or more processors are also configured to receive a configuration for generating the message, the configuration comprising one or more of: the number of consecutive bits to be modulated into analog symbols, the modulation and coding scheme MCS, or the number of analog modulated bits to be carried by the radio resources of the PUSCH.

25. The UE according to claim 23, wherein The one or more processors are further configured to disable channel coding based at least in part on one or more of: downlink control information, a MAC control element, a radio resource control message, or an indication of one or more new MCS values.

26. The UE according to claim 23, wherein: The one or more processors are further configured to disable channel coding based at least in part on one or more of: determining that a configured granted PUSCH, i.e., CG-PUSCH, is configured for radio resources overlapping on the PUSCH, or determining that no MCS is configured or indicated for the PUSCH.

27. A network node for wireless communication, comprising: Memory; as well as One or more processors are operatively coupled to the memory, the memory and the one or more processors being configured to implement the method according to any one of claims 14-22.

28. A non-transitory computer-readable medium storing an instruction set for wireless communication, comprising one or more instructions that, when executed by one or more processors of a user equipment (UE), cause the UE to perform the method according to any one of claims 1-13.

29. A non-transitory computer-readable medium storing an instruction set for wireless communication, comprising one or more instructions that, when executed by one or more processors of a network node, cause the network node to perform the method according to any one of claims 14-22.

Images