Power control for channel state feedback processing

Abstract

Various aspects of this disclosure generally relate to wireless communication. In some aspects, the first device can determine that a power threshold of the first device is met. The first device can switch from a first channel state feedback processing type to a second channel state feedback processing type, at least in part, based on the determination that the power threshold of the first device is met.

Description

[0001] Cross-reference to related applications

[0002] This patent application claims priority to Greek patent application No. 20200100492, filed on August 18, 2020, entitled "POWER CONTROL FOR CHANNELSTATE FEEDBACK PROCESSING," which is assigned to the assignee of this application. The disclosure of the earlier application is considered part of this patent application and is incorporated herein by reference.

[0003] introduction

[0004] Various aspects of this disclosure generally relate to wireless communication and techniques and apparatus for processing channel state information.

[0005] Wireless communication systems are widely deployed to provide a variety of telecommunications services such as telephone, video, data, messaging, and broadcasting. Typical wireless communication systems employ multiple access technologies that can support communication with multiple users by sharing available system resources (e.g., bandwidth, transmit power). 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 an enhancement set of the Universal Mobile Telecommunications System (UMTS) mobile standard issued by the 3rd Generation Partnership Project (3GPP).

[0006] A wireless network may include one or more base stations that support communication for one or more user equipment (UEs). UEs may communicate with base stations via downlink and uplink communication. "Downlink" (or "DL") refers to the communication link from the base station to the UE, while "uplink" (or "UL") refers to the communication link from the UE to the base station.

[0007] The above multiple access technologies have been adopted in various telecommunications standards to provide a common protocol enabling different UEs to communicate at the city, country, region, and / or global levels. New Radio (NR) (which may be referred to as 5G) is an enhancement set to the LTE mobile standard issued by 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, and CP-OFDM and / or Single Carrier Frequency Division Multiplexing (SC-FDM) (also known as Discrete Fourier Transform Extended OFDM (DFT-s-OFDM)) on the uplink, as well as supporting beamforming, multiple-input multiple-output (MIMO) antenna technologies and carrier aggregation to improve spectral efficiency, reduce costs, improve service, utilize new spectrum, and better integrate with other open standards. Further improvements to LTE, NR, and other radio access technologies remain useful as the demand for mobile broadband access continues to grow.

[0008] Overview

[0009] In some aspects, a method for performing wireless communication by a first device includes determining that a power threshold of the first device is met. The method includes switching from a first channel state feedback processing type to a second channel state feedback processing type, at least in part based on the determination that the power threshold of the first device is met.

[0010] In some aspects, a first device for wireless communication includes: a memory; and one or more processors coupled to the memory, the one or more processors being configured to: determine that a power threshold of the first device is met. The one or more processors are configured to: switch from a first channel state feedback processing type to a second channel state feedback processing type, at least in part based on the determination that the power threshold of the first device is met.

[0011] In some aspects, a non-transient computer-readable medium storing a set of instructions for wireless communication, the set of instructions comprising one or more instructions that, when executed by one or more processors of a first device, cause the first device to: determine that a power threshold of the first device is met; and, at least in part based on the determination that the power threshold of the first device is met, switch from a first channel state feedback processing type to a second channel state feedback processing type.

[0012] In some aspects, an apparatus for wireless communication includes means for determining that a power threshold of the apparatus is met. The apparatus may include means for switching from a first channel state feedback processing type to a second channel state feedback processing type, at least in part based on the determination that the power threshold of the apparatus is met.

[0013] In some aspects, a method for performing wireless communication by a second device includes: receiving first channel state feedback processed using a first channel state feedback processing type. The method also includes: receiving second channel state feedback processed using a second channel state feedback processing type after a power threshold is met.

[0014] In some aspects, a second device for wireless communication includes: a memory and one or more processors coupled to the memory, the one or more processors being configured to: receive first channel state feedback processed using a first channel state feedback processing type. The one or more processors may be configured to: receive second channel state feedback processed using a second channel state feedback processing type after a power threshold is met.

[0015] In some aspects, a non-transient computer-readable medium storing a set of instructions for wireless communication, the set of instructions comprising one or more instructions that, when executed by one or more processors of a second device, cause the second device to: receive first channel state feedback processed using a first channel state feedback processing type; and, after a power threshold is met, receive second channel state feedback processed using a second channel state feedback processing type.

[0016] In some aspects, an apparatus for wireless communication includes means for receiving first channel state feedback processed using a first channel state feedback processing type. The apparatus also includes means for receiving second channel state feedback processed using a second channel state feedback processing type after a power threshold is met.

[0017] The aspects generally include, as described substantially with reference to the accompanying drawings and description and explained as such, methods, apparatus, systems, computer program products, non-transient computer-readable media, user equipment, base stations, wireless communication equipment and / or processing systems.

[0018] The foregoing has broadly outlined the features and technical advantages of the examples according to this disclosure in an effort to facilitate a better understanding of the following detailed description. Additional features and advantages will be described thereafter. The disclosed concepts and specific examples can be readily used as the basis for modifying or designing other structures for implementing the same purposes as this disclosure. Such equivalent constructions do not depart from the scope of the appended claims. The characteristics of the concepts disclosed herein, in both their organization and manner of operation, and their associated advantages, will be better understood by considering the following description in conjunction with the accompanying drawings. Each drawing is provided for illustrative and descriptive purposes and does not define any limitation on the claims. Brief description of the attached diagram

[0020] To gain a more detailed understanding of the features described above in this disclosure, reference can be made to various aspects of the above brief overview, some of which are illustrated in the accompanying drawings. However, it should be noted that the drawings illustrate only certain typical aspects of this disclosure and should not be considered as limiting its scope, as other equivalent aspects are permissible in this description. Identical reference numerals in different drawings may identify the same or similar elements.

[0021] Figure 1 This is a diagram illustrating an example of a wireless network according to this disclosure.

[0022] Figure 2 This is a diagram illustrating an example of communication between a base station and a user equipment (UE) in a wireless network according to this disclosure.

[0023] Figure 3 This is a diagram illustrating an example of an encoder and decoder using previously stored channel state information according to this disclosure.

[0024] Figure 4 This is a diagram illustrating examples of encoding and decoding devices according to this disclosure.

[0025] Figure 5-8 This is a diagram illustrating an example of using a neural network to encode and decode a dataset for uplink communication according to this disclosure.

[0026] Figure 9 This is a diagram illustrating an example of power control associated with channel state feedback processing according to this disclosure.

[0027] Figure 10 This is a diagram illustrating an example process associated with power control for channel state feedback processing according to this disclosure.

[0028] Figure 11-13 The illustration is based on the explanatory example equipment of this disclosure.

[0029] Figure 14-15 This is a diagram illustrating an example of channel state feedback processing according to this disclosure.

[0030] Figure 16 This is a diagram illustrating an example process associated with power control for channel state feedback processing according to this disclosure.

[0031] Figure 17-19 The illustration is based on the explanatory example equipment of this disclosure.

[0032] Detailed description

[0033] Encoding devices operating within a network can measure reference signals and other information to report to network entities. For example, an encoding device may measure reference signals during beam management to achieve channel state feedback (CSF), measure the received power of reference signals from serving cells and / or neighboring cells, measure the signal strength of networks between radio access technologies (e.g., WiFi), measure sensor signals used to detect the location of one or more objects in the environment, and so on. However, reporting such information to base stations can consume communication and / or network resources.

[0034] Therefore, encoding devices (e.g., UEs, base stations, transmit / receive points (TRPs), network equipment, low Earth orbit (LEO) satellites, medium Earth orbit (MEO) satellites, geostationary orbit (GEO) satellites, highly elliptical orbit (HEO) satellites, etc.) can train one or more neural networks to learn the dependence of measured quality on individual parameters, isolate these measured qualities through the various layers (also referred to as "operations / operations") of the one or more neural networks, and compress these measurements in a manner that limits compression loss. In some aspects, the encoding device can use the properties of the number of bits to compress to construct the process of extracting and compressing each feature (also referred to as dimension) that affects the number of bits. In some aspects, the number of bits can be associated with sampling of one or more reference signals and / or can indicate channel state information. For example, the encoding device can use one or more extraction and compression operations associated with a neural network to encode measurements to produce compressed measurements, wherein the one or more extraction and compression operations are at least partially based on the feature set of these measurements.

[0035] Encoding devices can transmit compressed measurements to network entities such as servers, TRPs, other UEs, base stations, etc. Although the examples described herein refer to a base station as a decoding device, the decoding device can be any network entity. A network entity may be referred to as a "decoding device".

[0036] The decoding device can decode compressed measurements using one or more decompression and reconstruction operations associated with a neural network. These decompression and reconstruction operations can be at least partially based on a feature set of the compressed dataset to produce reconstructed measurements. The decoding device can use the reconstructed measurements as channel state information feedback.

[0037] Encoding devices (such as UEs) can be configured to process channel state feedback using a variety of different processing types. For example, a UE can use a first type of neural network to process channel state information with compressed measurements, a second type of neural network to process channel state information with compressed measurements, and other examples described above. Furthermore, a UE can use non-neural network-based techniques to process channel state information (without compression or with less compression compared to other techniques). These types of processing techniques can achieve enhanced levels of channel state feedback transmission without incurring excessive network overhead. However, in some scenarios, the UE may have limited resources (such as power resources or processing resources) to process channel state feedback.

[0038] Some aspects described in this paper enable the UE to dynamically adjust which type of channel state feedback processing it performs to account for limited resources. For example, when the UE detects that the battery level is below a threshold, it can switch from a first type of neural network to a second type of neural network. In one or more examples, using a second type of neural network may be associated with less power consumption compared to using the first type of neural network, thus allowing the UE to conserve battery resources. Similarly, when the UE detects that other functionalities are using more processing resources than a threshold, it can switch from neural network-based processing of channel state feedback to non-neural network-based processing (which may be associated with reduced utilization of processing resources compared to neural network-based processing).

[0039] The various aspects of this disclosure are described more fully below with reference to the accompanying drawings. However, this disclosure may be implemented in many different forms and should not be construed as being limited to any specific structure or function given throughout this disclosure. Rather, these aspects are provided so that this disclosure will be thorough and complete, and will fully convey the scope of this disclosure to those skilled in the art. Those skilled in the art will appreciate that the scope of this disclosure is intended to cover any aspect of this disclosure disclosed herein, whether implemented independently of or in combination with any other aspect of this disclosure. For example, any number of aspects set forth herein may be used to implement an apparatus or practice. Furthermore, the scope of this disclosure is intended to cover such apparatuses or methods practiced using additional structures, functionalities, or structures and functionalities that complement or supplement the various aspects of this disclosure set forth herein. It should be understood that any aspect of this disclosure disclosed herein may be implemented by one or more elements of the claims.

[0040] Several aspects of a telecommunications system will now be described with reference to various devices and techniques. These devices and techniques will be described in the following detailed description and explained 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 such elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system.

[0041] While the aspects herein may be described using terms commonly associated with 5G or New Radio (NR) Radio Access Technology (RAT), the aspects of this disclosure may be applied to other RATs, such as 3G RAT, 4G RAT, and / or RATs after 5G (e.g., 6G).

[0042] Figure 1 This is a diagram illustrating an example of a wireless network 100 according to this disclosure. The wireless network 100 may be or may include a 5G (e.g., NR) network and / or a 4G (e.g., LTE) network, etc. The wireless network 100 may include one or more base stations 110 (shown as BS 110a, BS 110b, BS 110c, and BS 110d), user equipment (UE) 120 or multiple UEs 120 (shown as UE 120a, UE 120b, UE 120c, UE 120d, and UE 120e), and / or other network entities. Base station 110 is the entity that communicates with UE 120. Base station 110 (sometimes referred to as BS) may include, for example, an NR base station, an LTE base station, a B-node, an eNB (e.g., in 4G), a gNB (e.g., in 5G), an access point, and / or a TRP. Each base station 110 may provide communication coverage for a specific geographic area. In the 3rd Generation Partnership Project (3GPP), the term "cell" can refer to the coverage area of ​​base station 110 and / or the base station subsystem serving that coverage area, depending on the context in which the term is used.

[0043] Base station 110 provides communication coverage to macrocells, picocells, femtocells, and / or another type of cell. Macrocells can cover a relatively large geographic area (e.g., a radius of several kilometers) and allow unrestricted access by UE 120 with a service subscription. Picocells can cover a relatively small geographic area and allow unrestricted access by UE 120 with a service subscription. Femtocells can cover a relatively small geographic area (e.g., a residential area) and allow restricted access by UE 120 associated with that femtocell (e.g., UE 120 in a closed subscriber group (CSG)). Base station 110 for macrocells may be referred to as a macro base station. Base station 110 for picocells may be referred to as a pico base station. Base station 110 for femtocells may be referred to as a femtocell or a home base station. Figure 1 In the example shown, BS 110a can be a macro base station for macro cell 102a, BS 110b can be a pico base station for pico cell 102b, and BS 110c can be a femto base station (BS) for femtocell 102c. A base station may support one or more (e.g., three) cells.

[0044] In some examples, the cell may not necessarily be stationary, and the geographical area of ​​the cell may move depending on the location of the mobile base station 110 (e.g., a mobile base station). In some examples, base stations 110 may interconnect with each other and / or interconnect to one or more other base stations 110 or network nodes (not shown) in the wireless network 100 using any suitable transport network via various types of backhaul interfaces (such as direct physical connections or virtual networks).

[0045] Wireless network 100 may include one or more relay stations. A relay station is an entity capable of receiving data transmissions from an upstream station (e.g., base station 110 or UE 120) and transmitting those data transmissions to a downstream station (e.g., UE 120 or base station 110). A relay station may be a UE 120 capable of relaying transmissions for other UE 120s. Figure 1 In the example shown, BS 110d (e.g., a relay base station) can communicate with BS 110a (e.g., a macro base station) and UE 120d to facilitate communication between BS 110a and UE 120d. The base station 110 for relay communication may be referred to as a relay station, relay base station, relay, etc.

[0046] Wireless network 100 can be a heterogeneous network comprising different types of base stations 110 (such as macro base stations, pico base stations, femto base stations, or relay base stations, etc.). These different types of base stations 110 may have different transmit power levels, different coverage areas, and / or different effects on interference in wireless network 100. For example, macro base stations may have high transmit power levels (e.g., 5 to 40 watts), while pico base stations, femto base stations, and relay base stations may have lower transmit power levels (e.g., 0.1 to 2 watts).

[0047] Network controller 130 can be coupled to or communicate with a group of base stations 110 and can provide coordination and control over these base stations 110. Network controller 130 can communicate with base stations 110 via backhaul communication links. Base stations 110 can communicate with each other directly or indirectly via wireless or wired backhaul communication links.

[0048] Each UE 120 may be distributed throughout the wireless network 100, and each UE 120 may be stationary or mobile. UE 120 may include, for example, access terminals, terminals, mobile stations, and / or subscriber units. UE 120 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 device, a camera, a gaming device, a netbook, a smartbook, an ultrabook, a medical device, a biometric device, a wearable device (e.g., a smartwatch, smart clothing, smart glasses, a smart wristband, smart jewelry (e.g., a smart ring or smart bracelet)), an entertainment device (e.g., a music device, a video device, and / or a satellite radio), an in-vehicle component or sensor, a smart meter / sensor, industrial manufacturing equipment, a GPS device, or any other suitable device configured to communicate via wireless or wired media.

[0049] Some UEs 120 may be considered Machine-Type Communication (MTC) UEs, or evolved or enhanced Machine-Type Communication (eMTC) UEs. MTC UEs and / or eMTC UEs may include, for example, robots, drones, remote devices, sensors, meters, monitors, location tags, etc., which can communicate with a base station, another device (e.g., a remote device), or some other entity. Some UEs 120 may be considered Internet of Things (IoT) devices, and / or may be implemented as NB-IoT (Narrowband IoT) devices. Some UEs 120 may be considered client equipment. UE 120 may be included within a housing that houses the components of UE 120, such as processor components and / or memory components. In some examples, the processor components and memory components may be coupled together. For example, the processor components (e.g., one or more processors) and memory components (e.g., memory) may be operatively coupled, communicatively coupled, electronically coupled, and / or electrically coupled.

[0050] Generally, any number of wireless networks 100 can be deployed in a given geographical area. Each wireless network 100 can support a specific RAT and can operate on one or more frequencies. A RAT may be referred to as a radio technology, air interface, etc. A frequency may be referred to as a carrier, frequency channel, etc. Each frequency can support a single RAT in a given geographical area to avoid interference between wireless networks using different RATs. In some cases, NR or 5G RAT networks can be deployed.

[0051] In some examples, two or more UEs 120 (e.g., shown as UE 120a and UE 120e) may communicate directly using one or more sidelink channels (e.g., without using base station 110 as an intermediary). For example, UEs 120 may 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, or vehicle-to-pedestrian (V2P) protocols), and / or mesh networks. In such examples, UEs 120 may perform scheduling operations, resource selection operations, and / or other operations described elsewhere herein as performed by base station 110.

[0052] The electromagnetic spectrum is typically subdivided into various classes, bands, channels, etc., by frequency / wavelength. In 5G NR, two initial operating bands have been designated as frequency ranges FR1 (410MHz–7.125GHz) and FR2 (24.25GHz–52.6GHz). It should be understood that although a portion of FR1 is greater than 6GHz, FR1 is generally (interchangeably) referred to as the “sub-6GHz” band in various documents and articles. Similar naming issues sometimes arise with FR2; although different from the Very High Frequency (EHF) band (30GHz–300GHz) designated as the “millimeter wave” band by the International Telecommunication Union (ITU), FR2 is generally (interchangeably) referred to as the “millimeter wave” band in various documents and articles.

[0053] The frequencies between FR1 and FR2 are generally referred to as intermediate frequency (IF) bands. Recent 5G NR studies have designated the operating bands of these IF bands as the frequency range designation FR3 (7.125 GHz – 24.25 GHz). Bands falling within FR3 can inherit FR1 and / or FR2 characteristics, thus effectively extending the features of FR1 and / or FR2 into the IF band. Additionally, higher frequency bands are currently being explored to extend 5G NR operation above 52.6 GHz. For example, three higher operating frequency bands have been designated as the frequency range designations FR4a or FR4-1 (52.6 GHz – 71 GHz), FR4 (52.6 GHz – 114.25 GHz), and FR5 (114.25 GHz – 300 GHz). Each of these higher frequency bands falls within the EHF band.

[0054] Considering the examples above, unless otherwise stated, it should be understood that, as used herein, the terms "sub-6GHz," etc., can broadly refer to frequencies less than 6GHz, within FR1, or that may include intermediate frequency band frequencies. Furthermore, unless otherwise stated, it should be understood that, as used herein, the terms "millimeter wave," etc., can broadly refer to frequencies that may include intermediate frequency band frequencies, within FR2, FR4, FR4-a, or FR4-1 and / or FR5, or within the EHF band. It is conceivable that the frequencies included in these operating bands (e.g., FR1, FR2, FR3, FR4-a, FR4-1, and / or FR5) can be modified, and the techniques described herein are applicable to those modified frequency ranges.

[0055] In some aspects, the first device (e.g., UE 120) may include a communication manager 140. As described in more detail elsewhere herein, the communication manager 140 may determine that a power threshold of the first device is met; and, at least in part based on the determination that the power threshold of the first device is met, switch from a first channel state feedback processing type to a second channel state feedback processing type. Additionally or alternatively, the communication manager 140 may perform one or more other operations described herein.

[0056] In some aspects, the second device (e.g., base station 110) may include a communication manager 150. As described in more detail elsewhere herein, the communication manager 150 may receive first channel state feedback processed using a first channel state feedback processing type; and, after a power threshold is met, receive second channel state feedback processed using a second channel state feedback processing type. Additionally or alternatively, the communication manager 150 may perform one or more other operations described herein.

[0057] As indicated above, Figure 1 This is provided as an example. Other examples may differ from the one provided. Figure 1 The example described.

[0058] Figure 2 This is a diagram illustrating an example 200 of communication between a base station 110 and a UE 120 in a wireless network 100 according to this disclosure. The base station 110 may be equipped with a set of antennas 234a to 234t, such as T antennas (T≥1). The UE 120 may be equipped with a set of antennas 252a to 252r, such as R antennas (R≥1).

[0059] At base station 110, transmit processor 220 can receive data from data source 212 intended for UE 120 (or a group of UEs 120). Transmit processor 220 can select one or more modulation and coding schemes (MCS) for UE 120 based at least in part on one or more channel quality indicators (CQIs) received from UE 120. Base station 110 can process (e.g., encode and modulate) the data for UE 120 based at least in part on the MCS(s) selected for UE 120 and can provide data symbols to UE 120. Transmit processor 220 can process system information (e.g., semi-static resource partitioning information (SRPI)) and control information (e.g., CQI requests, grants, and / or higher-layer signaling) and provide overhead symbols and control symbols. Transmit processor 220 can generate reference symbols for reference signals (e.g., a cell-specific reference signal (CRS) or demodulation reference signal (DMRS)) and synchronization signals (e.g., a primary synchronization signal (PSS) or secondary synchronization signal (SSS)). Transmit (TX) multiple-input multiple-output (MIMO) processor 230 can perform spatial processing (e.g., precoding) on ​​data symbols, control symbols, overhead symbols, and / or reference symbols where applicable, and can provide a set of output symbol streams (e.g., T output symbol streams) to a corresponding set of modems 232 (e.g., T modulators) (shown as modems 232a to 232t). For example, each output symbol stream can be provided to a modulator component (shown as MOD) of modem 232. Each modem 232 can use a corresponding modulator component to process the corresponding output symbol stream (e.g., for OFDM) to obtain an output sample stream. Each modem 232 may further use a corresponding modulator component to process (e.g., convert to analog, amplify, filter, and / or upconvert) the output sample stream to obtain a downlink signal. Modems 232a to 232t may transmit a set of downlink signals (e.g., T downlink signals) via a corresponding set of antennas 234 (e.g., T antennas) (shown as antennas 234a to 234t).

[0060] At UE 120, an array of antennas 252 (shown as antennas 252a to 252r) can receive downlink signals from base station 110 and / or other base stations 110 and can provide a set of received signals (e.g., R received signals) to an array of modems 254 (e.g., R modems) (shown as modems 254a to 254r). For example, each received signal can be provided to a demodulator component (shown as DEMOD) of modem 254. Each modem 254 can use a corresponding demodulator component to condition (e.g., filter, amplify, downconvert, and / or digitize) the received signal to obtain an input sample. Each modem 254 can use the demodulator component to further process the input sample (e.g., for OFDM) to obtain received symbols. MIMO detector 256 can obtain the received symbols from modem 254, perform MIMO detection on these received symbols where applicable, and can provide detected symbols. The receiver processor 258 can process (e.g., demodulate and decode) these detected symbols, provide decoded data for UE 120 to data sink 260, and provide decoded control and system information to 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 can determine Reference Signal Received Power (RSRP) parameters, Received Signal Strength Indicator (RSSI) parameters, Reference Signal Received Quality (RSRQ) parameters, and / or CQI parameters, etc. In some examples, one or more components of UE 120 may be included in a housing.

[0061] Network controller 130 may include communication unit 294, controller / processor 290, and memory 292. Network controller 130 may include one or more devices, such as those in the core network. Network controller 130 may communicate with base station 110 via communication unit 294.

[0062] One or more antennas (e.g., antennas 234a to 234t and / or antennas 252a to 252r) may include one or more antenna panels, one or more antenna groups, one or more antenna element assemblies, and / or one or more antenna arrays, etc., or may be included therein. Antenna panels, antenna groups, antenna element assemblies, and / or antenna arrays may include one or more antenna elements (within a single housing or multiple housings), coplanar antenna element assemblies, non-coplanar antenna element assemblies, and / or coupled to one or more transmit and / or receive components (such as...) Figure 2 One or more antenna elements (one or more components).

[0063] On the uplink, at UE 120, transmit processor 264 can receive and process data from data source 262 and control information from controller / processor 280 (e.g., reports including RSRP, RSSI, RSRQ, and / or CQI). Transmit processor 264 can generate reference symbols for one or more reference signals. Symbols from transmit processor 264 may be pre-encoded by TX MIMO processor 266 where applicable, further processed by modem 254 (e.g., for DFT-s-OFDM or CP-OFDM), and transmitted to base station 110. In some examples, modem 254 of UE 120 may include modulator and demodulator. In some examples, UE 120 includes a transceiver. The transceiver may include any combination of antennas 252, modems 254, MIMO detector 256, receive processor 258, transmit processor 264, and / or TX MIMO processor 266. The transceiver can be used by a processor (e.g., controller / processor 280) and memory 282 to perform aspects of any of the methods described herein.

[0064] At base station 110, uplink signals from UE 120 and / or other UEs may be received by antenna 234, processed by modem 232 (e.g., demodulator component of modem 232, shown as DEMOD), detected by MIMO detector 236 where applicable, and further processed by receiver processor 238 to obtain decoded data and control information transmitted by UE 120. Receiver processor 238 may provide the decoded data to data sink 239 and the decoded control information to controller / processor 240. Base station 110 may include communication unit 244 and may communicate with network controller 130 via communication unit 244. Base station 110 may include scheduler 246 to schedule one or more UEs 120 for downlink and / or uplink communication. In some examples, modem 232 of base station 110 may include modulator and demodulator. In some examples, base station 110 includes transceiver. The transceiver may include any combination of antennas 234, modems 232, MIMO detectors 236, receiver processors 238, transmitter processors 220, and / or TX MIMO processors 230. The transceiver may be used by a processor (e.g., controller / processor 240) and memory 242 to perform aspects of any of the methods described herein.

[0065] The controller / processor 240 of base station 110, the controller / processor 280 of UE 120, and / or Figure 2Any other component may perform one or more techniques associated with power control used for channel state feedback processing, as described in more detail elsewhere herein. For example, the controller / processor 240 of base station 110, the controller / processor 280 of UE 120, and / or Figure 2 Any other component may execute or direct, for example Figure 10 Process 1000 Figure 14 Process 1400 Figure 15 Process 1500 Figure 16 The operation of process 1600 and / or other processes as described herein. Memory 242 and memory 282 may store data and program code for base station 110 and UE 120, respectively. In some examples, memory 242 and / or memory 282 may include a non-transitory computer-readable medium storing one or more instructions (e.g., code and / or program code) for wireless communication. For example, when executed by one or more processors of base station 110 and / or UE 120 (e.g., directly executed, or executed after compilation, transformation, and / or interpretation), the one or more processors, UE 120, and / or base station 110 may cause the one or more processors, UE 120, and / or base station 110 to perform or direct, for example... Figure 10 Process 1000 Figure 14 Process 1400 Figure 15 Process 1500 Figure 16 The operation of process 1600, and / or other processes described herein. In some examples, the execution instructions may include run instructions, transform instructions, compile instructions, and / or interpret instructions, etc.

[0066] In some aspects, UE 120a may include: means for determining that a power threshold of the UE is met; means for switching from a first channel state feedback processing type to a second channel state feedback processing type based at least in part on the determination that the power threshold of the UE is met; and so on. Additionally or alternatively, UE 120a may include means for performing one or more other operations described herein. In some aspects, such means may include a communication manager 140. Additionally or alternatively, such means may include a combination of... Figure 2 One or more other components of the described UE 120a, such as controller / processor 280, transmit processor 264, TX MIMO processor 266, MOD 254, antenna 252, DEMOD 254, MIMO detector 256, receive processor 258, etc.

[0067] In some aspects, base station 110 may include: means for receiving first channel state feedback processed using a first channel state feedback processing type; and means for receiving second channel state feedback processed using a second channel state feedback processing type after a power threshold is met; and so on. Additionally or alternatively, base station 110 may include means for performing one or more other operations described herein. In some aspects, such means may include a communication manager 150. Additionally or alternatively, such means may include... Figure 2 One or more other components of the described base station 110, such as controller / processor 240, transmit processor 220, TX MIMO processor 230, MOD 232, antenna 234, DEMOD 232, MIMO detector 236, receive processor 238, etc.

[0068] although Figure 2 The boxes in the diagram are interpreted as different components, but the functions described above with respect to these boxes can be implemented by a single hardware component, software component, or combination of components. For example, the functions described with respect to transmit processor 264, receive processor 258, and / or TX MIMO processor 266 can be performed by controller / processor 280 or under the control of controller / processor 280.

[0069] As indicated above, Figure 2 This is provided as an example. Other examples may differ from the one provided. Figure 2 The example described.

[0070] Figure 3 An example of an encoding device 300 and a decoding device 350 using previously stored channel state information (CSI) according to this disclosure is explained. Figure 3 An encoding device 300 (e.g., UE 120) with a CSI instance encoder 310, a CSI sequence encoder 320 and a memory 330 is shown. Figure 3 A decoding device 350 (e.g., base station 110) with a CSI sequence decoder 360, a memory 370, and a CSI instance decoder 380 is also shown.

[0071] Encoding device 300 and decoding device 350 can utilize the correlation of CSI instances over time (temporal aspect) or the sequence of CSI instances to perform a series of channel estimations. Encoding device 300 and decoding device 350 can save and use previously stored CSIs, encoding and decoding only those CSIs that differ from previous instances. This provides less CSI feedback overhead and improves performance. Encoding device 300 can also be able to encode more accurate CSIs, and neural networks can be trained with more accurate CSIs.

[0072] like Figure 3 As shown, the CSI instance encoder 310 can encode a CSI instance into an intermediate encoded CSI for each DL channel estimate in the DL channel estimation sequence. The CSI instance encoder 310 (e.g., a feedforward network) can use neural network encoder weights θ. The intermediate encoded CSI can be represented as... The CSI sequence encoder 320 (e.g., a Long Short-Term Memory (LSTM) network) can determine a previously encoded CSI instance h(t-1) from memory 330 and compare this intermediate encoded CSI m(t) with the previously encoded CSI instance h(t-1) to determine the change n(t) in the encoded CSI. This change n(t) may be the new part in the channel estimation and may not have been predicted by the decoding device 350. The encoded CSI at this point can be obtained from... The CSI sequence encoder 320 may provide this change n(t) on the Physical Uplink Shared Channel (PUSCH) or the Physical Uplink Control Channel (PUCCH), and the encoding device 300 may transmit the change (e.g., information indicating the change) n(t) as an encoded CSI on the UL channel leading to the decoding device 350. Because the change is smaller than the entire CSI instance, the encoding device 300 may transmit a smaller payload for the encoded CSI on the UL channel while including more detailed information about the change in the encoded CSI. The CSI sequence encoder 320 may generate the encoded CSI h(t) based at least in part on the intermediate encoded CSI m(t) and at least a portion of the previous encoded CSI instance h(t-1). The CSI sequence encoder 320 may store the encoded CSI h(t) in memory 330.

[0073] CSI sequence decoder 360 can receive encoded CSI on PUSCH or PUCCH. CSI sequence decoder 360 can determine that only the change n(t) of the CSI is received as encoded CSI. CSI sequence decoder 360 can determine intermediate decoded CSI m(t) based at least in part on the encoded CSI and at least a portion of a previous intermediate decoded CSI instance h(t-1) from memory 370, and that change. CSI instance decoder 380 can decode the intermediate decoded CSI m(t) into decoded CSI. CSI sequence decoder 360 and CSI instance decoder 380 can use neural network decoder weights φ. The intermediate decoded CSI can be obtained from... The CSI sequence decoder 360 can generate the decoded CSI h(t) based at least in part on at least a portion of the intermediate decoded CSI m(t) and the previously decoded CSI instance h(t-1). The decoding device 350 can reconstruct the DL channel estimate from the decoded CSI h(t), and the reconstructed channel estimate can be expressed as... The CSI sequence decoder 360 can save the decoded CSI h(t) to memory 370.

[0074] Because the change n(t) is smaller than the entire CSI instance, the encoding device 300 can transmit a smaller payload on the UL channel. For example, if the DL channel changes only slightly from previous feedback due to low Doppler or minimal movement of the encoding device 300, the output of the CSI sequence encoder can be quite compact. In this way, the encoding device 300 can utilize the channel to estimate the correlation over time. Because the output is smaller, the encoding device 300 can include more detailed information about the change in the encoded CSI. The encoding device 300 can transmit an indication (e.g., a flag) to the decoding device 350 regarding the temporal encoding (CSI change) of the encoded CSI. Alternatively, the encoding device 300 can transmit an indication that the encoded CSI is encoded independently of any previous encoded CSI feedback. The decoding device 350 can decode the encoded CSI without using previous decoded CSI instances. Devices (which may include the encoding device 300 or the decoding device 350) can use the CSI sequence encoder and CSI sequence decoder to train a neural network model.

[0075] CSI can be a function of channel estimation (also known as channel response) H and interference N. There can be multiple ways to convey H and N. For example, coding device 300 can encode CSI as N. -1 / 2 H. Encoding device 300 can encode H and N separately. Encoding device 300 can partially encode H and N separately, and then jointly encode the two partially encoded outputs. Encoding H and N separately can be advantageous. Interference and channel variations can occur at different time scales. In low-Doppler scenarios, the channel can be stable, but interference may still change rapidly due to traffic or scheduler algorithms. In high-Doppler scenarios, the channel can change faster than the UE's scheduler clustering. In some aspects, the device (which may include encoding device 300 or decoding device 350) can use the separately encoded H and N to train a neural network model.

[0076] Reconstructed DL Channel This accurately reflects the DL channel H, and this can be referred to as explicit feedback. In some cases, Only the information required for decoding device 350 to derive the rank and precoding can be captured. CQI can be fed back separately. In time-coded scenarios, CSI feedback can be expressed as m(t) or n(t). Similar to type-II CSI feedback, m(t) can be structured as a rank index (RI), beam index, and a concatenation of coefficients representing amplitude or phase. In some cases, m(t) can be a quantized version of a real-valued vector. The beam can be predefined (not obtained through training), or it can be part of the training (e.g., part of θ and φ and conveyed to encoding device 300 or decoding device 350).

[0077] Decoding device 350 and encoding device 300 can maintain multiple encoder and decoder networks, each targeting a different payload size (to achieve a trade-off between varying accuracy and UL overhead). For each CSI feedback, depending on reconstruction quality and uplink budget (e.g., PUSCH payload size), encoding device 300 can select, or decoding device 350 can instruct encoding device 300 to select, one of the encoders used to construct the encoded CSI. Encoding device 300 can transmit the encoder index and CSI based at least in part on the encoder selected by encoding device 300. Similarly, decoding device 350 and encoding device 300 can maintain multiple encoder and decoder networks to accommodate different antenna geometries and channel conditions. Note that although some operations are described in relation to decoding device 350 and encoding device 300, these operations can also be performed by another device as part of the pre-configuration of encoder and decoder weights and / or structures.

[0078] As indicated above, Figure 3 This can be provided as an example. Other examples may differ from those provided. Figure 3 The example described.

[0079] Figure 4 This is an illustration of example 400 associated with an encoding device and a decoding device according to this disclosure. The encoding device (e.g., UE 120, encoding device 300, etc.) may be configured to perform one or more operations on data to compress the data. The decoding device (e.g., base station 110, decoding device 350, etc.) may be configured to decode the compressed data to determine information.

[0080] As used in this paper, a "layer" in a neural network is used to represent an operation on the input data. For example, convolutional layers and fully connected layers represent operations that correlate the data input into the layer. A convolution AxB operation refers to the operation of transforming several input features A into several output features B. The "kernel size" refers to the number of adjacent coefficients combined in one dimension.

[0081] As used herein, “weight” is used to refer to one or more coefficients used in an operation in a layer that combines the individual rows and / or columns of input data. For example, a fully connected layer operation may have an output y that is determined at least in part based on the sum of the product of the input matrix x and the weights A (which may be matrices) and the bias B (which may be matrices). The term “weight” may be used in this document to generally refer to both weights and biases.

[0082] As shown in Example 400, the encoding device can perform convolution operations on samples. For example, the encoding device can receive a set of bits structured as a 2x64x32 dataset, indicating IQ sampling for tap features (e.g., associated with multipath timing offsets) and spatial features (e.g., associated with different antennas of the encoding device). The convolution operation can be a 2x2 operation with kernel sizes of 3 and 3 on the data structure. The output of the convolution operation can be fed into a batch normalization (BN) layer, followed by LeakyReLu activation, to give an output dataset with a size of 2x64x32. The encoding device can perform a flattening operation to flatten the bits into a 4096-bit vector. The encoding device can apply a fully connected operation with a size of 4096xM to the 4096-bit vector to output an M-bit payload. The encoding device can then transmit the M-bit payload to a decoding device.

[0083] The decoding device can apply a fully connected operation of size Mx4096 to an M-bit payload to output a 4096-bit vector. The decoding device can then reshape the 4096-bit vector to a size of 2x64x32. The decoding device can apply one or more RefineNet operations to the reshaped bit vector. For example, RefineNet operations may include applying a 2x8 convolution operation (e.g., with kernel sizes of 3 and 3), the output of which is fed into a BN layer followed by LeakyReLU activation, producing an output dataset of size 8x64x32; applying an 8x16 convolution operation (e.g., with kernel sizes of 3 and 3), the output of which is fed into a BN layer followed by LeakyReLU activation, producing an output dataset of size 16x64x32; and / or applying a 16x2 convolution operation (e.g., with kernel sizes of 3 and 3), the output of which is fed into a BN layer followed by LeakyReLU activation, producing an output dataset of size 2x64x32. The decoding device can also apply 2x2 convolution operations with kernel sizes of 3 and 3 to generate decoded and / or reconstructed outputs.

[0084] As indicated above, Figure 4 This is provided merely as an example. Other examples may differ from those provided. Figure 4 The example described.

[0085] As described herein, encoding devices operating in a network can measure reference signals, etc., to report to decoding devices. For example, a UE can measure reference signals during beam management to report CSF, measure the received power of reference signals from serving cells and / or neighboring cells, measure the signal strength of networks between radio access technologies (e.g., WiFi), measure sensor signals used to detect the location of one or more objects in the environment, and so on. However, reporting such information to network entities can consume communication and / or network resources.

[0086] Encoding devices (e.g., UEs) can train one or more neural networks to learn the dependence of these measured qualities on individual parameters, isolate these measured qualities through the individual layers (also referred to as "operations / operations") of the one or more neural networks, and compress these measurements in a manner that limits compression loss. The encoding device can use the properties of the number of bits being compressed to construct the process of extracting and compressing each feature (also referred to as dimension) that affects the number of bits. The number of bits may be associated with sampling of one or more reference signals and / or may indicate channel state information.

[0087] Based at least in part on using neural networks to encode and decode datasets for uplink communication, the encoding device can transmit CSF with a reduced payload. This saves network resources that might otherwise be used to transmit complete datasets, such as those sampled by the encoding device.

[0088] Figure 5 This is an illustration of example 500 associated with using a neural network to encode and decode a dataset for uplink communication according to this disclosure. An encoding device (e.g., UE 120, encoding device 300, etc.) may be configured to perform one or more operations on samples (e.g., data) received via one or more antennas of the encoding device to compress those samples. A decoding device (e.g., base station 110, decoding device 350, etc.) may be configured to decode the compressed samples to determine information such as CSF.

[0089] The encoding device can identify the features to be compressed. The encoding device can perform a first type of operation in a first dimension associated with the features to be compressed. The encoding device can perform a second type of operation in other dimensions (e.g., in all other dimensions). For example, the encoding device can perform a fully connected operation in the first dimension and perform convolutions (e.g., pointwise convolutions) in all other dimensions.

[0090] The reference numerals in the accompanying drawings may identify operations that include multiple neural network layers and / or operations. The neural networks of encoding and decoding devices may be formed by cascading one or more of the referenced operations.

[0091] As shown by reference numeral 505, the encoding device can perform spatial feature extraction on the data. As shown by reference numeral 510, the encoding device can perform tap-domain feature extraction on the data. The encoding device can perform tap-domain feature extraction before performing spatial feature extraction. The extraction operation may include multiple operations. For example, the multiple operations may include one or more convolutional operations that may be activated or deactivated, one or more fully connected operations, etc. The extraction operation may include Residual Neural Network (ResNet) operations.

[0092] As shown by reference numeral 515, the encoding device can compress one or more features that have been extracted. The compression operation may include one or more operations, such as one or more convolution operations, one or more fully connected operations, etc. After compression, the bit count of the output may be less than the bit count of the input.

[0093] As shown by reference numeral 520 in the accompanying drawing, the encoding device can perform a quantization operation. The encoding device can perform the quantization operation at the output of the flattening compression operation and / or after performing a fully connected operation following the flattening output.

[0094] As shown by reference numeral 525, the decoding device can perform feature decompression. As shown by reference numeral 530, the decoding device can perform tap field feature reconstruction. As shown by reference numeral 535, the decoding device can perform spatial feature reconstruction. The decoding device can perform spatial feature reconstruction before performing tap field feature reconstruction. After the reconstruction operation, the decoding device can output a reconstructed version of the input from the encoding device.

[0095] The decoding device can perform operations in the reverse order of those performed by the encoding device. For example, if the encoding device follows operations (a, b, c, d), the decoding device can follow the reverse operations (D, C, B, A). The decoding device can perform operations that are completely symmetrical to those of the encoding device. This reduces the number of bits required for neural network configuration at the user interface (UE). The decoding device can perform additional operations besides those of the encoding device (e.g., convolution operations, fully connected operations, ResNet operations, etc.). The decoding device can also perform operations that are asymmetric to those of the encoding device.

[0096] Based at least in part on the use of neural networks by the encoding device to encode datasets for uplink communication, the encoding device (e.g., UE) can transmit CSF with a reduced payload. This saves network resources that might otherwise be used to transmit complete datasets, such as those sampled by the encoding device.

[0097] As indicated above, Figure 5 This is provided merely as an example. Other examples may differ from those provided. Figure 5 The example described.

[0098] Figure 6This is a diagram illustrating an example 600 associated with using a neural network to encode and decode a dataset for uplink communication according to this disclosure. An encoding device (e.g., UE 120, encoding device 300, etc.) may be configured to perform one or more operations on samples (e.g., data) received via one or more antennas of the encoding device to compress those samples. A decoding device (e.g., base station 110, decoding device 350, etc.) may be configured to decode the compressed samples to determine information such as CSF.

[0099] As shown in Example 600, the encoding device may receive samples from an antenna. For example, the encoding device may receive a dataset of size 64x64 based at least in part on the number of antennas, the number of samples per antenna, and tap features.

[0100] Encoding devices can perform spatial feature extraction, short-time (tap) feature extraction, and so on. This can be achieved using a 1D convolution operation that is fully connected in the spatial dimension (to extract spatial features) and a simple convolution with a small kernel size (e.g., 3) in the tap dimension (to extract short-tap features). The output of such a 64xW 1D convolution operation can be a Wx64 matrix.

[0101] The encoding device can perform one or more ResNet operations. These one or more ResNet operations can further refine spatial and / or temporal features. A ResNet operation can include multiple operations associated with a feature. For example, a ResNet operation can include multiple (e.g., three) 1D convolutional operations, skip connections (e.g., avoiding the application of 1D convolutional operations between the ResNet input and output), a summation operation of the path through multiple 1D convolutional operations and the path through skipped connections, etc. Multiple 1D convolutional operations can include: a Wx256 convolutional operation with a kernel size of 3, whose output is fed into a BN layer and then activated with LeakyReLU, producing an output dataset of size 256x64; a 256x512 convolutional operation with a kernel size of 3, whose output is fed into a BN layer and then activated with LeakyReLU, producing an output dataset of size 512x64; and a 512xW convolutional operation with a kernel size of 3, whose output has a BN dataset of size Wx64. The output of one or more ResNet operations can be a Wx64 matrix.

[0102] The encoding device can perform WxV convolution operations on the outputs of one or more ResNet operations. WxV convolution operations can include pointwise (e.g., tapwise) convolution operations. A WxV convolution operation can compress spatial features into a reduced dimension for each tap. A WxV convolution operation has W features as input and V features as output. The output from a WxV convolution operation can be a Vx64 matrix.

[0103] The encoding device can perform a flattening operation to flatten a Vx64 matrix into a 64V element vector. The encoding device can perform a 64VxM fully connected operation to further compress the spatial-temporal feature dataset into a low-dimensional vector of size M for over-the-air transmission to the decoding device. The encoding device can perform quantization before transmitting the low-dimensional vector of size M to map the transmitted samples into discrete values ​​for the low-dimensional vector of size M.

[0104] The decoding device can perform an Mx64V fully connected operation to decompress a low-dimensional vector of size M into a spatial-temporal feature dataset. The decoding device can perform a reshaping operation to reshape the 64V element vector into a 2D Vx64 matrix. The decoding device can perform a VxW (with a kernel of 1) convolution operation on the output from the reshaping operation. The VxW convolution operation can include pointwise (e.g., tapwise) convolution operations. The VxW convolution operation decompresses spatial features from a reduced dimension for each tap. The VxW convolution operation has V feature inputs and W feature outputs. The output from the VxW convolution operation can be a Wx64 matrix.

[0105] The decoding device can perform one or more ResNet operations. These ResNet operations can further decompress spatial and / or temporal features. ResNet operations may include multiple (e.g., three) 1D convolutional operations, skipped connections (e.g., to avoid applying 1D convolutional operations), summation of paths through multiple convolutional operations and paths through skipped connections, etc. The output from one or more ResNet operations may be a Wx64 matrix.

[0106] The decoding device can perform spatial and temporal feature reconstruction. This can be achieved using a 1D convolution operation that is fully connected in the spatial dimension (to reconstruct spatial features) and a simple convolution with a small kernel size (e.g., 3) in the tap dimension (to reconstruct short tap features). The output from a 64xW convolution operation can be a 64x64 matrix.

[0107] The values ​​of M, W, and / or V can be configurable to adjust the feature weights, payload size, etc.

[0108] As indicated above, Figure 6 This is provided merely as an example. Other examples may differ from those provided. Figure 6 The example described.

[0109] Figure 7This is an illustration of Example 700, which aligns with the present disclosure and relates to using a neural network to encode and decode a dataset for uplink communication. An encoding device (e.g., UE 120, encoding device 300, etc.) may be configured to perform one or more operations on samples (e.g., data) received via one or more antennas of the encoding device to compress those samples. A decoding device (e.g., base station 110, decoding device 350, etc.) may be configured to decode the compressed samples to determine information such as CSF. As shown in Example 700, features may be compressed and decompressed sequentially. For example, the encoding device may extract and compress features associated with the input to generate a payload, and subsequently, the decoding device may extract and compress features associated with the payload to reconstruct the input. The encoding and decoding operations may be symmetric (as shown) or asymmetric.

[0110] As shown in Example 700, the encoding device can receive samples from the antenna. For example, the encoding device can receive a dataset of size 256x64 based at least in part on the number of antennas, the number of samples per antenna, and tap features. The encoding device can reshape the data into a (64x64x4) dataset.

[0111] The encoding device can perform 2D 64x128 convolutional operations (with kernel sizes of 3 and 1). In some aspects, the 64x128 convolutional operation can perform spatial feature extraction associated with the antenna dimension of the decoding device, short-term (tap) feature extraction associated with the antenna dimension of the decoding device (e.g., a base station), etc. This can be achieved by using a simple convolutional operation that is fully connected in the antenna dimension of the decoding device, has a small kernel size (e.g., 3) in the tap dimension, and a small kernel size (e.g., 1) in the antenna dimension of the encoding device. The output from the 64xW convolutional operation can be a matrix of size (128x64x4).

[0112] The encoding device may perform one or more ResNet operations. These ResNet operations may further refine the spatial features associated with the decoding device and / or the temporal features associated with the decoding device. In some aspects, a ResNet operation may include multiple operations associated with the features. For example, a ResNet operation may include multiple (e.g., three) 2D convolution operations, skip connections (e.g., between the input and output of the ResNet to avoid applying 2D convolution operations), a summation operation of paths through multiple 2D convolution operations and paths through skip connections, etc. Multiple 2D convolutional operations can include: a Wx2W convolutional operation with kernel sizes of 3 and 1, whose output is fed into a BN layer and then activated with LeakyReLU, producing an output dataset of size 2Wx64xV; a 2Wx4W convolutional operation with kernel sizes of 3 and 1, whose output is fed into a BN layer and then activated with LeakyReLU, producing an output dataset of size 4Wx64xV; and a 4WxW convolutional operation with kernel sizes of 3 and 1, whose output has a BN dataset of size (128x64x4). The output from one or more ResNet operations can be a matrix of size (128x64x4).

[0113] The encoding device can perform 2D 128xV convolution operations (with kernel sizes of 1 and 1) on the outputs from one or more ResNet operations. The 128xV convolution operations can include pointwise (e.g., tapwise) convolution operations. The WxV convolution operation can compress the spatial features associated with the decoding device into a reduced dimension for each tap. The output from the 128xV convolution operation can be a matrix of size (4x64xV).

[0114] The encoding device can perform 2D 4x8 convolutional operations (with kernel sizes of 3 and 1). The 4x8 convolutional operation can perform spatial feature extraction associated with the encoding device's antenna dimension, short-time (tap) feature extraction associated with the encoding device's antenna dimension, etc. The output from the 4x8 convolutional operation can be a matrix of size (8x64xV).

[0115] The encoding device can perform one or more ResNet operations. These ResNet operations can further refine the spatial features and / or temporal features associated with the encoding device. A ResNet operation may include multiple operations associated with the features. For example, a ResNet operation may include multiple (e.g., three) 2D convolution operations, skip connections (e.g., to avoid applying 2D convolution operations), a summation operation of paths through multiple 2D convolution operations and paths through skip connections, etc. The output from one or more ResNet operations may be a matrix of size (8x64xV).

[0116] The encoding device can perform 2D 8xU convolution operations (with kernel sizes of 1 and 1) on the outputs from one or more ResNet operations. The 8xU convolution operation can include pointwise (e.g., tapwise) convolution operations. The 8xU convolution operation can compress the spatial features associated with the decoding device into a reduced dimension for each tap. The output from a 128xV convolution operation can be a matrix of size (U x 64 x V).

[0117] The encoding device can perform a flattening operation to flatten a matrix of size (U x 64 x V) into a 64UV element vector. The encoding device can perform a 64UV x M fully connected operation to further compress the 2D space-time feature dataset into a low-dimensional vector of size M for over-the-air transmission to the decoding device. The encoding device can perform quantization before transmitting the low-dimensional vector of size M to map the transmitted samples into discrete values ​​for the low-dimensional vector of size M.

[0118] The decoding device can perform an Mx64UV fully connected operation to decompress a low-dimensional vector of size M into a spatial-temporal feature dataset. The decoding device can perform a reshaping operation to reshape the 64UV element vector into a matrix of size (Ux64xV). The decoding device can perform a 2D Ux8 convolution operation (with a 1, 1 kernel) on the output from the reshaping operation. The Ux8 convolution operation can include pointwise (e.g., tapwise) convolution operations. The Ux8 convolution operation can decompress spatial features from a reduced dimension for each tap. The output from the Ux8 convolution operation can be a dataset of size (8x64xV).

[0119] The decoding device can perform one or more ResNet operations. These ResNet operations can further decompress spatial and / or temporal features associated with the encoding device. In some aspects, the ResNet operation may include multiple (e.g., three) 2D convolutional operations, skipped connections (e.g., to avoid applying 2D convolutional operations), summation operations of paths through multiple 2D convolutional operations and paths through skipped connections, etc. The output from one or more ResNet operations may be a dataset of size (8x64xV).

[0120] The decoding device can perform 2D 8x4 convolutional operations (with kernel sizes of 3 and 1). The 8x4 convolutional operations can perform spatial feature reconstruction in the antenna dimension of the encoding device, as well as short-term feature reconstruction. The output from the 8x4 convolutional operation can be a dataset of size (Vx64x4).

[0121] The decoding device can perform a 2D Vx128 (with a kernel of 1) convolution operation on the output of a 2D 8x4 convolution operation to reconstruct the tap features and spatial features associated with the decoding device. The Vx128 convolution operation can include pointwise (e.g., tapwise) convolution operations. The Vx128 convolution operation can decompress the spatial features associated with the decoding device antenna from a reduced dimension for each tap. The output from the Ux8 convolution operation can be a matrix of size (128x64x4).

[0122] The decoding device can perform one or more ResNet operations. These ResNet operations can further decompress spatial and / or temporal features associated with the decoding device. ResNet operations may include multiple (e.g., three) 2D convolutional operations, skipped connections (e.g., to avoid applying 2D convolutional operations), summation operations of paths through multiple 2D convolutional operations and paths through skipped connections, etc. The output from one or more ResNet operations can be a matrix of size (128x64x4).

[0123] The decoding device can perform 2D 128x64 convolutional operations (with kernel sizes of 3 and 1). In some respects, the 128x64 convolutional operation can perform spatial feature reconstruction, short-temporal feature reconstruction, etc., associated with the antenna dimension of the decoding device. The output from the 128x64 convolutional operation can be a dataset of size (64x64x4).

[0124] In some respects, the values ​​of M, V, and / or U can be configurable to adjust the feature weights, payload size, etc. For example, the value of M can be 32, 64, 128, 256, or 512, the value of V can be 16, and / or the value of U can be 1.

[0125] As indicated above, Figure 7 This is provided merely as an example. Other examples may differ from those provided. Figure 7 The example described.

[0126] Figure 8 This is a diagram illustrating an example 800 associated with using a neural network to encode and decode a dataset for uplink communication according to this disclosure. An encoding device (e.g., UE 120, encoding device 300, etc.) may be configured to perform one or more operations on samples (e.g., data) received via one or more antennas of the encoding device to compress those samples. A decoding device (e.g., base station 110, decoding device 350, etc.) may be configured to decode the compressed samples to determine information such as CSF. The operation of the encoding and decoding devices may be asymmetric. In other words, the decoding device may have a greater number of layers than the decoding device.

[0127] As shown in Example 800, the encoding device may receive samples from an antenna. For example, the encoding device may receive a dataset of size 64x64 based at least in part on the number of antennas, the number of samples per antenna, and tap features.

[0128] The encoding device can perform 64xW convolution operations (with a kernel size of 1). In some respects, the 64xW convolution operation can be fully connected in the antenna, convolution in the tap, etc. The output from the 64xW convolution operation can be a Wx64 matrix. The encoding device can perform one or more WxW convolution operations (with a kernel size of 1 or 3). The output from one or more WxW convolution operations can be a Wx64 matrix. The encoding device can perform convolution operations (with a kernel size of 1). One or more WxW convolution operations can perform spatial feature extraction, short-time (tap) feature extraction, etc. The WxW convolution operation can be a series of 1D convolution operations.

[0129] The encoding device can perform a flattening operation to flatten a Wx64 matrix into a 64W element vector. The encoding device can perform a 4096xM fully connected operation to further compress the spatial-temporal feature dataset into a low-dimensional vector of size M for over-the-air transmission to the decoding device. The encoding device can perform quantization before transmitting the low-dimensional vector of size M to map the transmitted samples into discrete values ​​for the low-dimensional vector of size M.

[0130] The decoding device can perform a 4096xM fully connected operation to decompress a low-dimensional vector of size M into a spatial-temporal feature dataset. The decoding device can also perform a reshaping operation to reshape a 6W-element vector into a Wx64 matrix.

[0131] The decoding device can perform one or more ResNet operations. These one or more ResNet operations can decompress spatial and / or temporal features. In some aspects, the ResNet operations may include multiple (e.g., three) 1D convolutional operations, skipped connections (e.g., avoiding the application of 1D convolutional operations between the ResNet input and output), summation operations of paths through multiple 1D convolutional operations and paths through skipped connections, etc. The multiple 1D convolutional operations may include: a Wx256 convolutional operation with a kernel size of 3, whose output is fed into a BN layer and then activated with LeakyReLU, producing an output dataset of size 256x64; a 256x512 convolutional operation with a kernel size of 3, whose output is fed into a BN layer and then activated with LeakyReLU, producing an output dataset of size 512x64; and a 512xW convolutional operation with a kernel size of 3, whose output has a BN dataset of size Wx64. The output from one or more ResNet operations may be a Wx64 matrix.

[0132] Decoding devices can perform one or more WxW convolution operations (with kernel sizes of 1 or 3). The output from one or more WxW convolution operations can be a Wx64 matrix. Encoding devices can perform convolution operations (with a kernel size of 1). WxW convolution operations can perform spatial feature reconstruction, short-time (tap) feature reconstruction, etc. WxW convolution operations can be a series of 1D convolution operations.

[0133] The encoding device can perform Wx64 convolution operations (with a kernel size of 1). A Wx64 convolution operation can be a 1D convolution operation. The output from a 64xW convolution operation can be a 64x64 matrix.

[0134] In some respects, the values ​​of M and / or W can be configurable to adjust the feature weights, payload size, etc.

[0135] As indicated above, Figure 8 This is provided merely as an example. Other examples may differ from those provided. Figure 8 The example described.

[0136] As described above, the UE (coding device) may have limited resources to process channel state information to generate a channel state feedback report. For example, the UE's battery level may be below a threshold. As another example, the UE may have less available processing resources than a threshold, such as when processing resources are assigned to other tasks. The UE can be configured with multiple different processing types to process channel state information. For example, the UE may have multiple different neural network models to process channel state information to reduce overhead during the transmission of the channel state feedback report. As another example, the UE may have non-neural network-based techniques for processing channel state information to generate the channel state feedback report.

[0137] Some aspects described herein enable the UE to switch between different processing types for channel state feedback processing. For example, the UE can switch from a first processing type to a second processing type, at least in part, based on the fact that a power threshold (such as a threshold related to battery level, a threshold related to the availability of processing resources, etc.) is met. In such cases, for example, the UE can detect a battery level below a threshold and can switch from using a first neural network processing technique that utilizes a relatively high level of processing resources and associated battery resources to using a second neural network processing technique that utilizes a relatively low level of processing resources.

[0138] Figure 9 This is a diagram illustrating example 900 related to power control for channel state feedback processing according to this disclosure. (See diagram for example.) Figure 9As shown, Example 900 includes communication between base station 110 (which may include decoding equipment and may correspond to the second device described herein) and UE 120a (which may include encoding equipment and may correspond to the first device described herein). In some aspects, base station 110 and UE 120a may be included in a wireless network (such as wireless network 100). Base station 110 and UE 120a may communicate on a radio access link, which may include an uplink and a downlink.

[0139] As in Figure 9 As further shown by reference numeral 910 in the accompanying drawing, UE 120a can use a first channel state feedback processing type to process channel state feedback and can report the processed channel state feedback. For example, UE 120a can use the first neural network architecture described above to process channel state information and can report the processed channel state information. In some aspects, UE 120a can receive configuration information associated with configuring the channel state feedback processing type. For example, UE 120a can receive signaling identifying the first channel state feedback processing type, such as Radio Resource Control (RRC) signaling, Media Access Control (MAC) Control Element (CE) signaling, Downlink Control Information (DCI) signaling, etc. Additionally or alternatively, UE 120a can receive signaling identifying a second channel state feedback processing type, and UE 120a will switch to using the second channel state feedback processing type when the handover conditions are met. Additionally or alternatively, UE 120a can receive information configuring handover conditions for triggering the handover between channel state feedback processing types. For example, UE 120a can receive signaling from base station 110 identifying a threshold power level at which it switches from a relatively power-intensive channel state feedback (CSF) processing type to a less power-intensive CSF processing type. Additionally or alternatively, UE 120a can autonomously set the threshold power level, such as based at least in part on a specified static threshold power level, at least in part on tracking data related to previous CSF processing and power levels, etc.

[0140] As in Figure 9As further illustrated by reference numeral 920 in the accompanying drawing, UE 120a may determine to switch to a second channel state feedback processing type. For example, UE 120a may determine that a threshold power level configured by base station 110 or autonomously configured by UE 120a as described above is met, and may switch to a less power-intensive channel state feedback processing type. As described above, the less power-intensive channel state feedback processing type may be, for example, a second neural network architecture with, for example, fewer layers. In one or more examples, channel state feedback processing using a second neural network architecture may result in lower spectral efficiency compared to using a first neural network architecture, but may also use fewer processing resources and correspondingly fewer power resources.

[0141] Additionally or alternatively, UE 120a may switch from a neural network-based channel state feedback processing type to a non-neural network-based channel state feedback processing type. For example, UE 120a may switch from transmitting Type-III channel state information to transmitting Type-I or Type-II channel state information, each of which may be associated with reduced power consumption relative to generating Type-III channel state information. Type-I channel state information may be a beam selection scheme, where the encoding device (UE 120a) selects the optimal beam index and sends the channel state information as channel state feedback to the decoding device (e.g., base station 110). Type-II channel state information may be a beam combining scheme, where the encoding device also calculates the optimal linear combination of coefficients for various beams on a sub-band basis (e.g., configured sub-bands) and sends back the beam index and coefficients used for beam combining. Type-III CSI is a neural network-based processing and reporting technique, as described above.

[0142] As in Figure 9 As further illustrated by reference numerals 930 and 940, UE 120a can use a second channel state feedback processing type to process channel state feedback and can report such feedback. For example, UE 120a can use a second neural network architecture, a non-neural network-based processing type, etc., to process channel state information to generate channel state feedback for reporting. In some aspects, UE 120a can provide an indicator of the second channel state feedback processing type. For example, in conjunction with the transmission of channel state feedback (such as in a message transmitted within the same message or in a message using time or frequency resources within a threshold proximity of the channel state feedback), UE 120a can provide an identifier of the second channel state feedback processing type. In such examples, UE 120a can transmit PUCCH, PUSCH, etc., to convey the identifier of the second channel state feedback type.

[0143] As a result, base station 110 can use the identifier to determine which decoding algorithm to use to decode the channel state feedback. Additionally or alternatively, base station 110 may perform blind decoding of the channel state feedback, at least in part, based on attempting to decode the channel state feedback using one or more different algorithms and using a checksum to confirm successful decoding. Additionally or alternatively, UE 120 may transmit an identifier indicating that UE 120a has switched the channel state feedback processing type without explicitly identifying the second channel state feedback processing type. In such examples, base station 110 may decode the channel state feedback without receiving an explicit identifier of the second channel state feedback processing type from UE 120a, at least in part, based on base station 110 signaling the second channel state feedback processing type to UE 120a.

[0144] As in Figure 9 As further illustrated by reference numeral 950, after a period of time, UE 120a may return to the first channel state feedback processing type. For example, UE 120a may return to the first channel state feedback processing type at least in part based on the detection that an external power supply has been connected to UE 120a. Additionally or alternatively, UE 120a may return to the first channel state feedback processing type at least in part based on the detection that the current power level exceeds a threshold power level. In such examples, UE 120a may switch back to the first channel state feedback processing type at least in part based on conditions configured by base station 110 or at least in part based on autonomous determination. In some aspects, UE 120a may transmit signaling indicating a switch back to the first channel state feedback processing type or explicitly identifying the first channel state feedback processing type, such as using PUCCH, PUSCH, etc. Additionally or alternatively, UE 120a may further switch to a third channel state feedback processing type, a fourth channel state feedback processing type, etc., such as at least in part based on meeting another handover criterion (lower threshold power level).

[0145] As indicated above, Figure 9 This is provided as an example. Other examples may differ from the one provided. Figure 9 The example described.

[0146] Figure 10 This is a diagram illustrating an example process 1000 performed by a first device, for example, according to this disclosure. Example process 1000 is an example of a first device (e.g., an encoding device, UE 120, etc.) performing operations associated with power control for channel state feedback processing.

[0147] like Figure 10As shown, in some aspects, process 1000 may include generating first channel state feedback using a first channel state feedback processing type (block 1010). For example, a first device (e.g., using generation component 1112) may use the first channel state feedback processing type to generate the first channel state feedback, as described above.

[0148] like Figure 10 As shown, in some aspects, process 1000 may include transmitting first channel state feedback (block 1020). For example, a first device (e.g., using transmission component 1104) may transmit the first channel state feedback as described above.

[0149] like Figure 10 As shown, in some aspects, process 1000 may include determining that a power threshold of the first device is met (block 1030). For example, the first device (e.g., using determining component 1108) may determine that a power threshold of the first device is met, as described above.

[0150] like Figure 10 As further shown, in some aspects, process 1000 may include switching from a first channel state feedback processing type to a second channel state feedback processing type at least in part based on determining that a power threshold of the first device is met (block 1040). For example, the first device (e.g., using switching component 1110) may switch from the first channel state feedback processing type to the second channel state feedback processing type at least in part based on determining that a power threshold of the first device is met, as described above.

[0151] like Figure 10 As shown, in some aspects, process 1000 may include generating a second channel state feedback using a second channel state feedback processing type (block 1050). For example, a first device (e.g., using generation component 1112) may use the second channel state feedback processing type to generate the second channel state feedback as described above.

[0152] like Figure 10 As shown, in some aspects, process 1000 may include transmitting a second channel status feedback (block 1060). For example, a first device (e.g., using transmission component 1104) may transmit the second channel status feedback as described above.

[0153] like Figure 10 As shown, in some aspects, process 1000 may include transmitting information identifying a second channel state feedback type (block 1062). For example, a first device (e.g., using transmission component 1104) may transmit information identifying a second channel state feedback type as described above.

[0154] like Figure 10 As further shown, in some aspects, process 1000 may include switching back to a first channel state feedback processing type (block 1070). For example, a first device (e.g., using switching component 1110) may switch from a second channel state feedback processing type to a first channel state feedback processing type at least in part based on determining that a power threshold of the first device is met, as described above.

[0155] Process 1000 may include additional aspects, such as any single aspect or any combination of aspects described below and / or in conjunction with one or more other processes described elsewhere herein.

[0156] In a first aspect, process 1000 includes transmitting first channel state feedback processed using a first channel state feedback processing type before determining that the power threshold of the first device is met; and transmitting second channel state feedback processed using a second channel state feedback processing type after switching from the first channel state feedback processing type to a second channel state feedback processing type.

[0157] In a second aspect, either alone or in combination with the first aspect, process 1000 includes using a second channel state feedback processing type to determine channel state information for reporting, based at least in part on a change from a first channel state feedback processing type to a second channel state feedback processing type.

[0158] In the third aspect, individually or in combination with one or more of the first and second aspects, at least one of the first channel state feedback processing type or the second channel state feedback processing type includes generating type-I channel state information, type-II channel state information, type-III channel state information, or a combination thereof.

[0159] In the fourth aspect, either alone or in combination with one or more of the first to third aspects, the first channel state feedback processing type is a first neural network processing type with a first architecture.

[0160] In the fifth aspect, either alone or in combination with one or more of the first to fourth aspects, the second channel state feedback processing type is a second neural network processing type with a second architecture.

[0161] In the sixth aspect, either alone or in combination with one or more of the first to fifth aspects, the second channel state feedback processing type is a non-neural network processing type.

[0162] In a seventh aspect, alone or in combination with one or more of the first to sixth aspects, process 1000 includes: receiving signaling identifying a configuration for switching channel state feedback processing; and wherein switching from a first channel state feedback processing type to a second channel state feedback processing type includes switching from the first channel state feedback processing type to the second channel state feedback processing type at least in part based on the configuration for switching channel state feedback processing.

[0163] In the eighth aspect, the signaling, alone or in combination with one or more of the first to seventh aspects, includes radio resource control signaling, downlink control information signaling, MAC-CE signaling, or a combination thereof.

[0164] In the ninth aspect, the configuration for switching channel state feedback processing, either alone or in combination with one or more of the first to eighth aspects, includes information identifying the following: the power threshold, the first channel state feedback processing type, the second channel state feedback processing type, or a combination thereof.

[0165] In the tenth aspect, either alone or in combination with one or more of the first to ninth aspects, the power threshold is a threshold defined by the first device.

[0166] In the eleventh aspect, alone or in combination with one or more of the first to tenth aspects, process 1000 includes: transmitting information identifying a second channel state feedback processing type based at least in part on a change from a first channel state feedback processing type to a second channel state feedback processing type.

[0167] In the twelfth aspect, the information identifying the second channel state feedback processing type is included in the physical uplink control channel or the physical uplink shared channel, either alone or in combination with one or more of the first to eleventh aspects.

[0168] In the thirteenth aspect, alone or in combination with one or more of the first to twelfth aspects, process 1000 includes: after switching to the second channel state feedback processing type, switching from the second channel state feedback processing type to the first channel state feedback processing type.

[0169] In the fourteenth aspect, alone or in combination with one or more of the first to thirteenth aspects, the first channel state feedback processing type is transformed into one that is at least partially based on the expiration of a threshold time period, satisfaction of the power threshold, satisfaction of another power threshold, connection of the first device to a power source, or a combination thereof.

[0170] In the fifteenth aspect, the transition to a first channel state feedback processing type is based, alone or in combination with one or more of the first to fourteenth aspects, at least in part on receiving signaling configuring the transition to the first channel state feedback processing type, the first device's determination of satisfying the handover criteria, or a combination thereof.

[0171] In the sixteenth aspect, alone or in combination with one or more of the first to fifteenth aspects, process 1000 includes: transmitting information identifying the first channel state feedback processing type based at least in part on the transition to the first channel state feedback processing type.

[0172] although Figure 10 An example box of process 1000 is shown, but in some respects, process 1000 may include... Figure 10 The boxes depicted in the process are compared to additional boxes, fewer boxes, different boxes, or boxes arranged differently. Additionally or alternatively, two or more boxes of process 1000 can be executed in parallel.

[0173] Figure 11 This is a block diagram of an example device 1100 for wireless communication. Device 1100 may be a first device (encoding device, UE (such as UE 120a)), or the first device may include device 1100. In some aspects, device 1100 includes a receiving component 1102 and a transmitting component 1104, which may be in communication with each other (e.g., via one or more buses and / or one or more other components). As shown, device 1100 may use the receiving component 1102 and the transmitting component 1104 to communicate with another device 1106 (such as a second device, which may be a UE, a base station, or another wireless communication device). As further shown, device 1100 may include a communication manager 140, which includes one or more of a determining component 1108, a transformation component 1110, or a generating component 1112, etc.

[0174] In some respects, Equipment 1100 can be configured to perform the actions described in this article. Figure 9 One or more operations described herein. Additionally or alternatively, equipment 1100 may be configured to perform one or more processes described herein, such as Figure 10 The process 1000, etc. In some aspects, equipment 1100 and / or Figure 11 One or more components shown may include the above combination Figure 2 One or more components of the described UE. Additionally or alternatively, Figure 11 One or more components shown can be combined as described above. Figure 2Implemented within one or more of the described components. Additionally or alternatively, one or more components in the component set may be implemented at least partially as software stored in memory. For example, a component (or a portion of a component) may be implemented as instructions or code stored in a non-transitory computer-readable medium and may be executed by a controller or processor to perform the function or operation of that component.

[0175] Receiver 1102 may receive communications (such as reference signals, control information, data communications, or combinations thereof) from equipment 1106. In some aspects, receiver 1102 may receive signaling identifying configurations for switching channel state feedback processing. Receiver 1102 may provide the received communications to one or more other components of equipment 1100. In some aspects, receiver 1102 may perform signal processing on the received communications (such as filtering, amplification, demodulation, analog-to-digital conversion, demultiplexing, deinterleaving, demapping, equalization, interference cancellation, or decoding, and other examples), and may provide the processed signal to one or more other components of equipment 1106. In some aspects, receiver 1102 may include combinations of the above. Figure 2 The described UE includes one or more antennas, demodulators, MIMO detectors, receiver processors, controllers / processors, memory, or combinations thereof.

[0176] Transmission component 1104 can transmit communications (such as reference signals, control information, data communications, or combinations thereof) to equipment 1106. In some aspects, transmission component 1104 can transmit first channel state feedback processed using a first channel state feedback processing type, second channel state feedback processed using a second channel state feedback processing type, and so on. In some aspects, transmission component 1104 can transmit information identifying the channel state feedback processing type used to process the channel state feedback. In some aspects, one or more other components of equipment 1106 can generate communications and provide the generated communications to transmission component 1104 for transmission to equipment 1106. In some aspects, transmission component 1104 can perform signal processing (such as filtering, amplification, modulation, digital-to-analog conversion, multiplexing, interleaving, mapping, encoding, etc.) on the generated communications and can transmit the processed signals to equipment 1106. In some aspects, transmission component 1104 can include combinations of the above. Figure 2 The described UE includes one or more antennas, modulators, transmit MIMO processors, transmit processors, controllers / processors, memory, or combinations thereof. In some aspects, the transmit component 1104 may coexist with the receive component 1102 in a transceiver.

[0177] The determining component 1108 can determine that the UE's power threshold is met. In some aspects, the determining component 1108 can use a specific channel state feedback processing type to determine channel information. In some aspects, the determining component 1108 can determine that handover criteria or handover conditions are met. In some aspects, the determining component 1108 may include a combination of the above. Figure 2 The described UE includes a receiver processor, a transmitter processor, a controller / processor, a memory, or a combination thereof.

[0178] The switching component 1110 can switch from a first channel state feedback processing type to a second channel state feedback processing type, at least in part, based on determining that the power threshold of the UE is met. In some aspects, the switching component 1110 may include a combination of the above. Figure 2 The described UE includes one or more antennas, demodulators, MIMO detectors, receive processors, modulators, transmit MIMO processors, transmit processors, controllers / processors, memory, or combinations thereof. In some aspects, the switching component 1110 can switch from a second channel state feedback processing type to a first channel state feedback processing type after switching to a second channel state feedback processing type.

[0179] The generation component 1112 can generate channel state information, such as Type-I channel state information, Type-II channel state information, Type-III channel state information, and so on. For example, the generation component 1112 can use a neural network or another non-neural network technique to generate the channel state information. In some aspects, the generation component 1112 may include a combination of the above. Figure 2 The described UE includes one or more antennas, demodulators, MIMO detectors, receiver processors, modulators, transmit MIMO processors, transmit processors, controllers / processors, memories, or combinations thereof.

[0180] Figure 11 The number and arrangement of components shown are provided as an example. In practice, different arrangements may exist. Figure 11 The components shown are compared to additional components, fewer components, different components, or components arranged differently. Furthermore, Figure 11 The two or more components shown can be implemented within a single component, or Figure 11 The single component shown can be implemented as multiple distributed components. Additionally or alternatively, Figure 11 The set of components shown (e.g., one or more components) can be executed as described by Figure 11 The other set of components shown in the diagram performs one or more functions.

[0181] Figure 12This is a diagram illustrating an example 1200 of the hardware implementation of device 1205 employing processing system 1210. Device 1205 may be a UE (such as UE 120a).

[0182] Processing system 1210 can be implemented with a bus architecture generally represented by bus 1215. Depending on the specific application and overall design constraints of processing system 1210, bus 1215 may include any number of interconnect buses and bridges. Bus 1215 links together various circuits including one or more processors and / or hardware components (represented by processor 1220, the described components, and computer-readable medium / memory 1225). Bus 1215 may also link various other circuits, such as timing sources, peripheral devices, voltage regulators, power management circuits, etc.

[0183] Processing system 1210 may be coupled to transceiver 1230. Transceiver 1230 is coupled to one or more antennas 1235. Transceiver 1230 provides means for communicating with various other equipment via a transmission medium. Transceiver 1230 receives signals from the one or more antennas 1235, extracts information from the received signals, and provides the extracted information to processing system 1210 (specifically, receiving component 1102). In addition, transceiver 1230 receives information from processing system 1210 (specifically, transmission component 1104) and generates signals to be applied to the one or more antennas 1235, at least in part, based on the received information.

[0184] Processing system 1210 includes a processor 1220 coupled to a computer-readable medium / memory 1225. Processor 1220 is responsible for general processing, including the execution of software stored on the computer-readable medium / memory 1225. When executed by processor 1220, the software causes processing system 1210 to perform the various functions described herein with respect to any particular apparatus. Computer-readable medium / memory 1225 may also be used to store data manipulated by processor 1220 during software execution. The processing system further includes at least one of the described components. Each component may be a software module running in processor 1220, a software module residing in / stored in computer-readable medium / memory 1225, one or more hardware modules coupled to processor 1220, or some combination thereof.

[0185] In some aspects, the processing system 1210 may be a component of the UE 120 (UE 120a) and may include a memory 282 and / or at least one of the following: a TX MIMO processor 266, a receive (RX) processor 258, and / or a controller / processor 280. In some aspects, the apparatus 1205 for wireless communication includes: means for determining that a power threshold of the UE is met; means for switching from a first channel state feedback processing type to a second channel state feedback processing type based at least in part on the determination that the power threshold of the UE is met; means for transmitting first channel state feedback processed using the first channel state feedback processing type before determining that the power threshold of the UE is met; and so on.

[0186] Additionally or alternatively, the apparatus 1205 may include: means for transmitting second channel state feedback processed using the second channel state feedback processing type after switching from a first channel state feedback processing type to a second channel state feedback processing type; means for determining channel state information for reporting based at least in part on the switch from the first channel state feedback processing type to the second channel state feedback processing type; and so on. Additionally or alternatively, the apparatus 1205 may include: means for receiving signaling identifying a configuration for switching channel state feedback processing; means for switching from the first channel state feedback processing type to the second channel state feedback processing type based at least in part on the configuration for switching channel state feedback processing; and so on.

[0187] Additionally or alternatively, the apparatus 1205 may include: means for transmitting information identifying a second channel state feedback processing type based at least in part on a transition from a first channel state feedback processing type to a second channel state feedback processing type; means for transitioning from a second channel state feedback type to a first channel state feedback processing type after transitioning to the second channel state feedback processing type; and means for transmitting information identifying a first channel state feedback processing type based at least in part on the transition to the first channel state feedback processing type.

[0188] The aforementioned apparatus may be one or more components of the aforementioned components of equipment 1100 and / or the processing system 1210 of equipment 1205 configured to perform the functions described herein. As described elsewhere herein, the processing system 1210 may include a TX MIMO processor 266, an RX processor 258, and / or a controller / processor 280. In one configuration, the aforementioned apparatus may be a TX MIMO processor 266, an RX processor 258, and / or a controller / processor 280 configured to perform the functions and / or operations described herein.

[0189] Figure 12This is provided as an example. Other examples may differ from this combination. Figure 12 The example described.

[0190] Figure 13 This is a diagram illustrating an example 1300 of the code and circuitry system implementation used for device 1305. Device 1305 can be a UE (such as UE 120a, etc.).

[0191] like Figure 13 As further shown, the equipment may include a circuit system (circuit system 1320) for determining that a power threshold is met. For example, the equipment may include a circuit system that enables the equipment to determine that a power threshold is met.

[0192] like Figure 13 As further shown, the equipment may include a circuit system (circuit system 1325) for switching from a first channel state feedback processing type to a second channel state feedback processing type. For example, the equipment may include a circuit system that enables the equipment to switch from a first channel state feedback processing type to a second channel state feedback processing type.

[0193] like Figure 13 As further shown, the equipment may include a circuit system (circuit system 1330) for transmitting first channel state feedback processed using a first channel state feedback processing type. For example, the equipment may include a circuit system that enables the equipment to transmit first channel state feedback processed using a first channel state feedback processing type.

[0194] like Figure 13 As further shown, the apparatus may include a circuit system (circuit system 1335) for transmitting second channel state feedback processed using a second channel state feedback processing type. For example, the apparatus may include a circuit system that enables the apparatus to transmit second channel state feedback processed using a second channel state feedback processing type.

[0195] like Figure 13 As further shown, the equipment may include a circuit system (circuit system 1340) for determining channel state information using a second channel state feedback processing type. For example, the equipment may include a circuit system that enables the equipment to determine channel state information using a second channel state feedback processing type.

[0196] like Figure 13 As further shown, the equipment may include a circuit system (circuit system 1345) for receiving signaling that identifies a configuration for switching channel state feedback processing. For example, the equipment may include a circuit system that enables the equipment to receive signaling that identifies a configuration for switching channel state feedback processing.

[0197] like Figure 13 As further shown, the equipment may include a circuit system (circuit system 1350) for transmitting information identifying the channel state feedback processing type. For example, the equipment may include a circuit system that enables the equipment to transmit information indicating whether a first channel state feedback processing type or a second channel state feedback processing type is being used.

[0198] like Figure 13 As further shown, the apparatus may include code (code 1355) stored in computer-readable medium 1225 for determining that a power threshold is met. For example, the apparatus may include code that, when executed by processor 1220, causes processor 1220 to determine that a power threshold is met.

[0199] like Figure 13 As further shown, the apparatus may include code (code 1360) stored in computer-readable medium 1225 for switching from a first channel state feedback processing type to a second channel state feedback processing type. For example, the apparatus may include code that, when executed by processor 1220, causes processor 1220 to switch from the first channel state feedback processing type to the second channel state feedback processing type.

[0200] like Figure 13 As further shown, the apparatus may include code (code 1365) stored in computer-readable medium 1225 for transmitting first channel state feedback processed using a first channel state feedback processing type. For example, the apparatus may include code that, when executed by processor 1220, causes transceiver 1230 to transmit first channel state feedback processed using the first channel state feedback processing type.

[0201] like Figure 13 As further shown, the apparatus may include code (code 1370) stored in computer-readable medium 1225 for transmitting second channel state feedback processed using a second channel state feedback processing type. For example, the apparatus may include code that, when executed by processor 1220, causes transceiver 1230 to transmit second channel state feedback processed using a second channel state feedback processing type.

[0202] like Figure 13 As further shown, the apparatus may include code (code 1375) stored in computer-readable medium 1225 for determining channel state information using a second channel state feedback processing type. For example, the apparatus may include code that, when executed by processor 1220, causes processor 1220 to determine channel state information using a second channel state feedback processing type.

[0203] like Figure 13 As further shown, the apparatus may include code (code 1380) stored in computer-readable medium 1225 for receiving signaling that identifies a configuration for switching channel state feedback processing. For example, the apparatus may include code that, when executed by processor 1220, causes transceiver 1230 to receive signaling that identifies a configuration for switching channel state feedback processing.

[0204] like Figure 13 As further shown, the apparatus may include code (code 1385) stored in computer-readable medium 1225 for transmitting information identifying a channel state feedback processing type. For example, the apparatus may include code that, when executed by processor 1220, causes transceiver 1230 to transmit information identifying a first channel state feedback processing type or a second channel state feedback processing type.

[0205] Figure 13 This is provided as an example. Other examples may differ from this combination. Figure 13 The example described.

[0206] Figure 14 This is a diagram illustrating an example procedure 1400 performed by a UE according to this disclosure. Example procedure 1400 is wherein a first device (e.g., an encoding device, UE 120, ...) Figure 11 Examples of equipment 1100, etc., performing operations associated with using neural networks to encode datasets.

[0207] like Figure 14 As shown, in some aspects, process 1400 may include encoding a dataset to produce a compressed dataset using one or more extraction and compression operations associated with a neural network, the one or more extraction and compression operations being at least partially based on a feature set of the dataset (box 1410). For example, a first device (e.g., using a determining component 1108, an encoding component, etc.) may use one or more extraction and compression operations associated with a neural network to encode a dataset to produce a compressed dataset, the one or more extraction and compression operations being at least partially based on a feature set of the dataset, as described above.

[0208] like Figure 14 As further shown, in some aspects, process 1400 may include transmitting the compressed dataset to a base station (block 1420). For example, the UE (e.g., using transmission component 1104) may transmit the compressed dataset to the base station as described above.

[0209] Process 1400 may include additional aspects, such as any single aspect or any combination of aspects described below and / or in conjunction with one or more other processes described elsewhere herein.

[0210] In the first aspect, the dataset is based at least in part on sampling of one or more reference signals.

[0211] In the second aspect, transmitting the compressed dataset to the base station, either alone or in combination with the first aspect, includes transmitting channel state information feedback to the base station.

[0212] In a third aspect, either alone or in combination with one or more of the first and second aspects, process 1400 includes identifying the feature set of the dataset, wherein the one or more extraction and compression operations include: a first type of operation performed in dimensions associated with features in the feature set of the dataset and a second type of operation performed in the remaining dimensions associated with other features in the feature set of the dataset, the second type of operation being different from the first type of operation.

[0213] In the fourth aspect, either alone or in combination with one or more of the first to third aspects, the first type of operation includes one-dimensional fully connected layer operations, while the second type of operation includes convolution operations.

[0214] In the fifth aspect, either alone or in combination with one or more of the first to fourth aspects, the one or more extraction and compression operations include a plurality of operations, including one or more of convolution operations, fully connected layer operations, or residual neural network operations.

[0215] In the sixth aspect, either alone or in combination with one or more of the first to fifth aspects, the one or more extraction and compression operations include: a first extraction operation and a first compression operation performed on a first feature in the feature set of the dataset, and a second extraction operation and a second compression operation performed on a second feature in the feature set of the dataset.

[0216] In the seventh aspect, either alone or in combination with one or more of the first to sixth aspects, process 1400 includes performing one or more additional operations on the intermediate dataset output after performing the one or more extraction and compression operations.

[0217] In the eighth aspect, either alone or in combination with one or more of the first to seventh aspects, the one or more additional operations include one or more of a quantization operation, a flattening operation, or a fully connected operation.

[0218] In the ninth aspect, alone or in combination with one or more of the first to eighth aspects, the feature set of the dataset includes one or more of spatial features or tapped domain features.

[0219] In the tenth aspect, either alone or in combination with one or more of the first to ninth aspects, the one or more extraction and compression operations include one or more of the following: spatial feature extraction using one-dimensional convolution operations, temporal feature extraction using one-dimensional convolution operations, residual neural network operations for refining extracted spatial features, residual neural network operations for refining extracted temporal features, pointwise convolution operations for compressing extracted spatial features, pointwise convolution operations for compressing extracted temporal features, flattening operations for flattening extracted spatial features, flattening operations for flattening extracted temporal features, or compression operations for compressing one or more of extracted temporal features or extracted spatial features into a low-dimensional vector for transmission.

[0220] In the eleventh aspect, alone or in combination with one or more of the first to tenth aspects, the one or more extraction and compression operations include: a first feature extraction operation associated with one or more features associated with a base station, a first compression operation for compressing one or more features associated with the base station, a second feature extraction operation associated with one or more features associated with the UE, and a second compression operation for compressing one or more features associated with the UE.

[0221] although Figure 14 An example box of process 1400 is shown, but in some respects, process 1400 may include... Figure 14 The boxes depicted in the process are compared to additional boxes, fewer boxes, different boxes, or boxes arranged differently. Additionally or alternatively, two or more boxes in process 1400 can be executed in parallel.

[0222] Figure 15 This is a diagram illustrating an example process 1500 performed, for example, by a base station according to this disclosure. Example process 1500 is an example in which a second device (e.g., a decoding device, base station 110, etc.) performs operations associated with using a neural network to decode a dataset.

[0223] like Figure 15 As shown, in some aspects, process 1500 may include receiving a compressed dataset from a first device (box 1510). For example, a second device (e.g., using a receiving component) may receive the compressed dataset from the first device as described above.

[0224] like Figure 15As further shown, in some aspects, process 1500 may include decoding the compressed dataset using one or more decompression and reconstruction operations associated with a neural network to produce a reconstructed dataset, the one or more decompression and reconstruction operations being at least partially based on a feature set of the compressed dataset (box 1520). For example, a second device (e.g., using a decoding component) may use one or more decompression and reconstruction operations associated with a neural network to decode the compressed dataset to produce a reconstructed dataset, the one or more decompression and reconstruction operations being at least partially based on a feature set of the compressed dataset, as described above.

[0225] Process 1500 may include additional aspects, such as any single aspect or any combination of aspects described below and / or in conjunction with one or more other processes described elsewhere herein.

[0226] In a first aspect, using the one or more decompression and reconstruction operations to decode the compressed dataset includes: performing the one or more decompression and reconstruction operations at least in part based on the assumption that the first device generates the compressed dataset using an operation set symmetric to the one or more decompression and reconstruction operations, or performing the one or more decompression and reconstruction operations at least in part based on the assumption that the first device generates the compressed dataset using an operation set asymmetric to the one or more decompression and reconstruction operations.

[0227] In the second aspect, either alone or in combination with the first aspect, the compressed dataset is at least partially based on sampling of one or more reference signals by the first device.

[0228] In a third aspect, receiving the compressed dataset, either alone or in combination with one or more of the first and second aspects, includes receiving channel state information feedback from the first device.

[0229] In the fourth aspect, either alone or in combination with one or more of the first to third aspects, the one or more decompression and reconstruction operations include: a first type of operation performed in dimensions associated with features in the feature set of the compressed dataset, and a second type of operation performed in the remaining dimensions associated with other features in the feature set of the compressed dataset, the second type of operation being different from the first type of operation.

[0230] In the fifth aspect, either alone or in combination with one or more of the first to fourth aspects, the first type of operation includes one-dimensional fully connected layer operations, and the second type of operation includes convolution operations.

[0231] In the sixth aspect, either alone or in combination with one or more of the first to fifth aspects, the one or more decompression and reconstruction operations include a plurality of operations, including one or more of convolution operations, fully connected layer operations, or residual neural network operations.

[0232] In the seventh aspect, either alone or in combination with one or more of the first to sixth aspects, the one or more decompression and reconstruction operations include: a first operation performed on a first feature of the feature set of the compressed dataset, and a second operation performed on a second feature of the feature set of the compressed dataset.

[0233] In the eighth aspect, either alone or in combination with one or more of the first to seventh aspects, process 1500 includes performing a reshaping operation on the compressed dataset.

[0234] In the ninth aspect, alone or in combination with one or more of the first to eighth aspects, the feature set of the compressed dataset includes one or more of spatial features or tapped domain features.

[0235] In the tenth aspect, either alone or in combination with one or more of the first to ninth aspects, the one or more decompression and reconstruction operations include one or more of the following: feature decompression operation, temporal feature reconstruction operation, or spatial feature reconstruction operation.

[0236] In the eleventh aspect, alone or in combination with one or more of the first to tenth aspects, the one or more decompression and reconstruction operations include: a first feature reconstruction operation performed on one or more features associated with the first device, and a second feature reconstruction operation performed on one or more features associated with the second device.

[0237] although Figure 15 An example box of process 1500 is shown, but in some respects, process 1500 may include... Figure 15 The boxes depicted in the process are compared to additional boxes, fewer boxes, different boxes, or boxes arranged differently. Additionally or alternatively, two or more boxes in process 1500 can be executed in parallel.

[0238] Figure 16 This is a diagram illustrating an example process 1600 performed, for example, by a second device according to this disclosure. Example process 1600 is an example in which a second device (e.g., base station 110, equipment 1106, etc.) performs operations associated with power control for channel state feedback processing.

[0239] like Figure 16As shown, in some aspects, process 1600 may include receiving first channel state feedback processed using a first channel state feedback processing type (block 1610). For example, a second device (e.g., using receiving component 1702) may receive first channel state feedback processed using the first channel state feedback processing type, as described above.

[0240] like Figure 16 As further shown, in some aspects, process 1600 may include receiving second channel state feedback processed using a second channel state feedback processing type (block 1620) after a power threshold is met. For example, a second device (e.g., using receiving component 1702) may receive second channel state feedback processed using a second channel state feedback processing type, as described above, after a power threshold is met.

[0241] Process 1600 may include additional aspects, such as any single aspect or any combination of aspects described below and / or in conjunction with one or more other processes described elsewhere herein.

[0242] In a first aspect, process 1600 includes decoding a first channel state feedback based at least in part on a first channel state feedback processing type; and decoding a second channel state feedback based at least in part on a second channel state feedback processing type.

[0243] In the second aspect, either alone or in combination with the first aspect, at least one of the first channel state feedback or the second channel state feedback includes type-I channel state information, type-II channel state information, type-III channel state information, or a combination thereof.

[0244] In the third aspect, either alone or in combination with one or more of the first and second aspects, the first channel state feedback processing type is a first neural network processing type with a first architecture.

[0245] In the fourth aspect, the second channel state feedback processing is a second neural network processing type with a second architecture, either alone or in combination with one or more of the first to third aspects.

[0246] In the fifth aspect, either alone or in combination with one or more of the first to fourth aspects, the second channel state feedback processing type is a non-neural network processing type.

[0247] In a sixth aspect, either alone or in combination with one or more of the first to fifth aspects, process 1600 includes transmitting signaling that identifies the configuration for switching the channel state feedback processing so that the first device switches to using a second channel state feedback processing type in response to a power threshold being met.

[0248] In the seventh aspect, the signaling, alone or in combination with one or more of the first to sixth aspects, includes: radio resource control signaling, downlink control information signaling, media access control control element signaling, or a combination thereof.

[0249] In the eighth aspect, the configuration for switching channel state feedback processing, either alone or in combination with one or more of the first to seventh aspects, includes information identifying the following: the power threshold, the first channel state feedback processing type, the second channel state feedback processing type, or a combination thereof.

[0250] In the ninth aspect, either alone or in combination with one or more of the first to eighth aspects, process 1600 includes receiving information identifying the type of second channel state feedback processing in conjunction with receiving second channel state feedback.

[0251] In the tenth aspect, the information identifying the second channel state feedback processing type is included in the physical uplink control channel or the physical uplink shared channel, either alone or in combination with one or more of the first to ninth aspects.

[0252] In the eleventh aspect, alone or in combination with one or more of the first to tenth aspects, process 1600 includes: after receiving the second channel state feedback, receiving a third channel state feedback processed using the first channel state feedback processing type.

[0253] In the twelfth aspect, the change from the second channel state feedback processing type to the first channel state feedback processing type, either alone or in combination with one or more of the first to eleventh aspects, is based at least in part on the expiration of a threshold time period, satisfaction of the power threshold, satisfaction of another power threshold, connection of the first device to a power source, or a combination thereof.

[0254] In the thirteenth aspect, alone or in combination with one or more of the first to twelfth aspects, process 1600 includes: transmitting signaling that configures a change from a second channel state feedback processing type to a first channel state feedback processing type.

[0255] In the fourteenth aspect, alone or in combination with one or more of the first to thirteenth aspects, process 1600 includes: receiving information identifying the processing type of the first channel state feedback in combination with receiving third channel state feedback.

[0256] although Figure 16 An example box of process 1600 is shown, but in some respects, process 1600 may include... Figure 16 The boxes depicted in the process are compared to additional boxes, fewer boxes, different boxes, or boxes arranged differently. Additionally or alternatively, two or more boxes in process 1600 can be executed in parallel.

[0257] Figure 17 This is a block diagram of an example device 1700 for wireless communication. Device 1700 may be a second device (decoding device, BS (such as base station 110)), or a second device may include device 1700. In some aspects, device 1700 includes a receiving component 1702 and a transmitting component 1704, which may be in communication with each other (e.g., via one or more buses and / or one or more other components). As shown, device 1700 may use the receiving component 1702 and the transmitting component 1704 to communicate with another device 1706 (such as a first device, which may be a UE or another wireless communication device). As further shown, device 1700 may include a communication manager 150, which includes a decoding component 1708, etc.

[0258] In some respects, Equipment 1700 can be configured to perform the actions described in this article. Figure 9 One or more operations described herein. Additionally or alternatively, equipment 1700 may be configured to perform one or more processes described herein, such as... Figure 16 The process 1600, etc. In some aspects, equipment 1700 and / or Figure 17 One or more components shown may include the above combination Figure 2 One or more components of the described base station. Additional or alternative. Figure 17 One or more components shown can be combined as described above. Figure 2 Implemented within one or more of the described components. Additionally or alternatively, one or more components in the component set may be implemented at least partially as software stored in memory. For example, a component (or a portion of a component) may be implemented as instructions or code stored in a non-transitory computer-readable medium and may be executed by a controller or processor to perform the function or operation of that component.

[0259] Receiver 1702 may receive communications (such as reference signals, control information, data communications, or combinations thereof) from equipment 1706. In some aspects, receiver 1702 may include channel state feedback, an identifier of the processing type used to process the channel state feedback, an indicator of transitions between channel state feedback processing types, etc. Receiver 1702 may provide the received communications to one or more other components of equipment 1700. In some aspects, receiver 1702 may perform signal processing on the received communications (such as filtering, amplification, demodulation, analog-to-digital conversion, demultiplexing, deinterleaving, demapping, equalization, interference cancellation, or decoding, and other examples), and may provide the processed signal to one or more other components of equipment 1706. In some aspects, receiver 1702 may include a combination of the above. Figure 2The described base station includes one or more antennas, demodulators, MIMO detectors, receiver processors, controllers / processors, memory, or combinations thereof.

[0260] Transmission component 1704 can transmit communications (such as reference signals, control information, data communications, or combinations thereof) to equipment 1706. In some aspects, transmission component 1704 can transmit information identifying configurations for channel state feedback processing. In some aspects, one or more other components of equipment 1706 can generate communications and provide the generated communications to transmission component 1704 for transmission to equipment 1706. In some aspects, transmission component 1704 can perform signal processing (such as filtering, amplification, modulation, digital-to-analog conversion, multiplexing, interleaving, mapping, coding, etc.) on the generated communications and can transmit the processed signals to equipment 1706. In some aspects, transmission component 1704 can include combinations of the above. Figure 2 The described base station includes one or more antennas, modulators, transmit MIMO processors, transmit processors, controllers / processors, memory, or combinations thereof. In some aspects, the transmit component 1704 may coexist with the receive component 1702 in a transceiver.

[0261] Decoding component 1708 can decode first channel state feedback processed using a first channel state feedback processing type, second channel state feedback processed using a second channel state feedback processing type, and so on. In some aspects, decoding component 1708 may include combinations of the above. Figure 2 The described base station includes a receiver processor, transmitter processor, controller / processor, memory, or a combination thereof.

[0262] Figure 17 The number and arrangement of components shown are provided as an example. In practice, different arrangements may exist. Figure 17 The components shown are compared to additional components, fewer components, different components, or components arranged differently. Furthermore, Figure 17 The two or more components shown can be implemented within a single component, or Figure 17 The single component shown can be implemented as multiple distributed components. Additionally or alternatively, Figure 17 The set of components shown (e.g., one or more components) can be executed as described by Figure 17 The other set of components shown in the diagram performs one or more functions.

[0263] Figure 18 This is a diagram illustrating an example 1800 of the hardware implementation of device 1805 employing processing system 1810. Device 1805 may be a base station, such as base station 110.

[0264] Processing system 1810 can be implemented with a bus architecture generally represented by bus 1815. Depending on the specific application and overall design constraints of processing system 1810, bus 1815 may include any number of interconnect buses and bridges. Bus 1815 links together various circuits including one or more processors and / or hardware components (represented by processor 1820, the illustrated components, and computer-readable medium / memory 1825). Bus 1815 may also link various other circuits, such as timing sources, peripheral devices, voltage regulators, power management circuits, etc.

[0265] Processing system 1810 may be coupled to transceiver 1830. Transceiver 1830 is coupled to one or more antennas 1835. Transceiver 1830 provides means for communicating with various other equipment via a transmission medium. Transceiver 1830 receives signals from the one or more antennas 1835, extracts information from the received signals, and provides the extracted information to processing system 1810 (specifically, receiving component 1702). In addition, transceiver 1830 receives information from processing system 1810 (specifically, transmission component 1704) and generates signals to be applied to the one or more antennas 1835, at least in part, based on the received information.

[0266] Processing system 1810 includes a processor 1820 coupled to a computer-readable medium / memory 1825. Processor 1820 is responsible for general processing, including the execution of software stored on the computer-readable medium / memory 1825. When executed by processor 1820, the software causes processing system 1810 to perform the various functions described herein with respect to any particular apparatus. Computer-readable medium / memory 1825 may also be used to store data manipulated by processor 1820 during software execution. The processing system further includes at least one of the described components. Each component may be a software module running in processor 1820, a software module residing in / stored in computer-readable medium / memory 1825, one or more hardware modules coupled to processor 1820, or some combination thereof.

[0267] In some aspects, the processing system 1810 may be a component of the base station 110 and may include a memory 242 and / or at least one of the following: a transmit processor 220, an RX processor 238, and / or a controller / processor 240. In some aspects, the apparatus 1805 for wireless communication includes: means for receiving first channel state feedback processed using a first channel state feedback processing type; means for receiving second channel state feedback processed using a second channel state feedback processing type; means for decoding the first channel state feedback; means for decoding the second channel state feedback; means for transmitting information identifying configurations for channel state feedback processing and / or transitions; and so on.

[0268] The aforementioned apparatus may be one or more components of the aforementioned components of equipment 1700 and / or the processing system 1810 of equipment 1805 configured to perform the functions described herein. As described elsewhere herein, the processing system 1810 may include a TX processor 220, an RX processor 238, and / or a controller / processor 240. In one configuration, the aforementioned apparatus may be the TX processor 220, the RX processor 238, and / or the controller / processor 240 configured to perform the functions and / or operations described herein.

[0269] Figure 18 This is provided as an example. Other examples may differ from this combination. Figure 18 The example described.

[0270] Figure 19 This is a diagram illustrating the implementation of the code and circuitry system used in Equipment 1905, specifically Example 1900. Equipment 1905 can be a base station, such as Base Station 110, etc.

[0271] like Figure 19 As further shown, the apparatus may include a circuit system (circuit system 1920) for receiving first channel state feedback processed using a first channel state feedback processing type. For example, the apparatus may include a circuit system that enables the apparatus to receive first channel state feedback processed using a first channel state feedback processing type.

[0272] like Figure 19 As further shown, the apparatus may include a circuit system (circuit system 1925) for receiving second channel state feedback processed using a second channel state feedback processing type. For example, the apparatus may include a circuit system that enables the apparatus to receive second channel state feedback processed using a second channel state feedback processing type.

[0273] like Figure 19 As further shown, the equipment may include a circuit system (circuit system 1930) for decoding the first channel state feedback. For example, the equipment may include a circuit system that enables the equipment to decode the first channel state feedback.

[0274] like Figure 19 As further shown, the equipment may include a circuit system (circuit system 1935) for decoding the second channel state feedback. For example, the equipment may include a circuit system that enables the equipment to decode the second channel state feedback.

[0275] like Figure 19As further shown, the equipment may include a circuit system (circuit system 1940) for transmitting signaling that identifies a configuration for switching channel state feedback processing. For example, the equipment may include a circuit system that enables the equipment to transmit signaling that identifies a configuration for switching channel state feedback processing.

[0276] like Figure 19 As further shown, the equipment may include a circuit system (circuit system 1945) for receiving information identifying the type of channel state feedback processing. For example, the equipment may include a circuit system that enables the equipment to receive information identifying the type of channel state feedback processing.

[0277] like Figure 19 As further shown, the apparatus may include code (code 1955) stored in computer-readable medium 1825 for receiving first channel state feedback processed using a first channel state feedback processing type. For example, the apparatus may include code that, when executed by processor 1820, causes transceiver 1830 to receive first channel state feedback processed using the first channel state feedback processing type.

[0278] like Figure 19 As further shown, the apparatus may include code (code 1960) stored in computer-readable medium 1825 for receiving second channel state feedback processed using a second channel state feedback processing type. For example, the apparatus may include code that, when executed by processor 1820, causes transceiver 1830 to receive second channel state feedback processed using a second channel state feedback processing type.

[0279] like Figure 19 As further shown, the apparatus may include code (code 1965) stored in computer-readable medium 1825 for decoding the first channel state feedback. For example, the apparatus may include code that, when executed by processor 1820, causes processor 1820 to decode the first channel state feedback.

[0280] like Figure 19 As further shown, the apparatus may include code (code 1970) stored in the computer-readable medium 1825 for decoding the second channel status feedback. For example, the apparatus may include code that, when executed by the processor 1820, causes the processor 1820 to decode the second channel status feedback.

[0281] like Figure 19As further shown, the apparatus may include code (code 1975) stored in computer-readable medium 1825 for transmitting signaling that identifies a configuration for switching channel state feedback processing. For example, the apparatus may include code that, when executed by processor 1820, causes transceiver 1830 to transmit signaling that identifies a configuration for switching channel state feedback processing.

[0282] like Figure 19 As further shown, the apparatus may include code (code 1980) stored in computer-readable medium 1825 for receiving information identifying the type of channel state feedback processing. For example, the apparatus may include code that, when executed by processor 1820, causes transceiver 1830 to receive information identifying the type of channel state feedback processing.

[0283] Figure 19 This is provided as an example. Other examples may differ from this combination. Figure 19 The example described.

[0284] The following provides an overview of some aspects of this disclosure:

[0285] Aspect 1: A wireless communication method performed by a first device, comprising: determining that a power threshold of the first device is met; and at least in part switching from a first channel state feedback processing type to a second channel state feedback processing type based on determining that the power threshold of the first device is met.

[0286] Aspect 2: The method of aspect 1 further includes: transmitting first channel state feedback processed using a first channel state feedback processing type before determining that the power threshold of the first device is met; and transmitting second channel state feedback processed using a second channel state feedback processing type after switching from the first channel state feedback processing type to the second channel state feedback processing type.

[0287] Aspect 3: The method of any one of Aspects 1 to 2 further includes: using a second channel state feedback processing type to determine channel state information for reporting, at least in part based on a change from a first channel state feedback processing type to a second channel state feedback processing type.

[0288] Aspect 4: The method of any one of Aspects 1 to 3, wherein at least one of the first channel state feedback processing type or the second channel state feedback processing type includes generating: type-I channel state information, type-II channel state information, type-III channel state information, or a combination thereof.

[0289] Aspect 5: The method of any one of Aspects 1 to 4, wherein the first channel state feedback processing type is a first neural network processing type having a first architecture.

[0290] Aspect 6: The method of aspect 5, wherein the second channel state feedback processing is a second neural network processing type with a second architecture.

[0291] Aspect 7: The method of aspect 5, wherein the second channel state feedback processing type is a non-neural network processing type.

[0292] Aspect 8: The method of any one of Aspects 1 to 7 further includes: receiving signaling identifying a configuration for switching channel state feedback processing; and wherein switching from a first channel state feedback processing type to a second channel state feedback processing type includes: switching from the first channel state feedback processing type to the second channel state feedback processing type at least in part based on the configuration for switching channel state feedback processing.

[0293] Aspect 9: The method of aspect 8, wherein the signaling includes: radio resource control signaling, downlink control information signaling, media access control (MAC) control element (CE) signaling, or a combination thereof.

[0294] Aspect 10: The method of any one of Aspects 8 to 9, wherein the configuration for switching the channel state feedback processing includes information identifying the following: the power threshold, the first channel state feedback processing type, the second channel state feedback processing type, or a combination thereof.

[0295] Aspect 11: The method of any one of Aspects 1 to 10, wherein the power threshold is a threshold defined by the first device.

[0296] Aspect 12: The method of any one of Aspects 1 to 11 further includes: transmitting information identifying the second channel state feedback processing type based at least in part on the transition from a first channel state feedback processing type to a second channel state feedback processing type.

[0297] Aspect 13: The method of aspect 12, wherein the information identifying the second channel state feedback processing type is included in the physical uplink control channel or the physical uplink shared channel.

[0298] Aspect 14: The method of any one of Aspects 1 to 13 further includes: after switching to the second channel state feedback processing type, switching from the second channel state feedback processing type to the first channel state feedback processing type.

[0299] Aspect 15: The method of aspect 14, wherein the conversion to a first channel state feedback processing type is based at least in part on the following: the expiration of a threshold time period, satisfaction of the power threshold, satisfaction of another power threshold, connection of a first device to a power source, or a combination thereof.

[0300] Aspect 16: The method of any one of Aspects 14 to 15, wherein the transition to the first channel state feedback processing type is based at least in part on receiving signaling configuring the transition to the first channel state feedback processing type, the first device's determination of satisfying the handover criteria, or a combination thereof.

[0301] Aspect 17: The method of any one of Aspects 14 to 16 further includes: transmitting information identifying the first channel state feedback processing type based at least in part on the transition to the first channel state feedback processing type.

[0302] Aspect 18: A method for performing wireless communication by a second device, comprising: receiving first channel state feedback processed using a first channel state feedback processing type; and receiving second channel state feedback processed using a second channel state feedback processing type after a power threshold is met.

[0303] Aspect 19: The method of aspect 18 further includes: decoding the first channel state feedback based at least in part on a first channel state feedback processing type; and decoding the second channel state feedback based at least in part on a second channel state feedback processing type.

[0304] Aspect 20: The method of any one of Aspects 18 to 19, wherein at least one of the first channel state feedback or the second channel state feedback includes: Type-I channel state information, Type-II channel state information, Type-III channel state information, or a combination thereof.

[0305] Aspect 21: The method of any one of Aspects 18 to 20, wherein the first channel state feedback processing type is a first neural network processing type having a first architecture.

[0306] Aspect 22: The method of aspect 21, wherein the second channel state feedback processing type is a second neural network processing type with a second architecture.

[0307] Aspect 23: The method of aspect 21, wherein the second channel state feedback processing type is a non-neural network processing type.

[0308] Aspect 24: The method of any one of Aspects 18 to 23 further includes: transmitting signaling identifying the configuration for switching the channel state feedback processing so that the first device switches to using a second channel state feedback processing type in response to meeting the power threshold.

[0309] Aspect 25: The method of aspect 24, wherein the signaling includes: radio resource control signaling, downlink control information signaling, media access control (MAC) control element (CE) signaling, or a combination thereof.

[0310] Aspect 26: The method of any one of Aspects 24 to 25, wherein the configuration for switching the channel state feedback processing includes information identifying the following: the power threshold, the first channel state feedback processing type, the second channel state feedback processing type, or a combination thereof.

[0311] Aspect 27: The method of any one of aspects 18 to 26 further includes: receiving information identifying the processing type of the second channel state feedback in conjunction with receiving the second channel state feedback.

[0312] Aspect 28: The method of aspect 27, wherein the information identifying the second channel state feedback processing type is included in the physical uplink control channel or the physical uplink shared channel.

[0313] Aspect 29: The method of any one of Aspects 18 to 28 further includes: after receiving the second channel state feedback, receiving a third channel state feedback processed using the first channel state feedback processing type.

[0314] Aspect 30: The method of aspect 29, wherein the transition from the second channel state feedback processing type to the first channel state feedback processing type is based at least in part on the following: the expiration of a threshold time period, satisfaction of the power threshold, satisfaction of another power threshold, connection of the first device to a power source, or a combination thereof.

[0315] Aspect 31: The method of any one of Aspects 29 to 30 further includes: transmitting signaling that configures a change from a second channel state feedback processing type to a first channel state feedback processing type.

[0316] Aspect 32: The method of any one of aspects 29 to 31 further includes: receiving information identifying the processing type of the first channel state feedback in conjunction with receiving third channel state feedback.

[0317] Aspect 33: An apparatus for wireless communication at a device, comprising: a processor; a memory coupled to the processor; and instructions stored in the memory and executable by the processor to cause the apparatus to perform methods as described in one or more of aspects 1-17.

[0318] Aspect 34: An apparatus for wireless communication, comprising a memory and one or more processors coupled to the memory, the one or more processors being configured to perform methods as described in one or more aspects of aspects 1-17.

[0319] Aspect 35: An apparatus for wireless communication, comprising at least one means for performing a method as described in one or more aspects of aspects 1-17.

[0320] Aspect 36: A non-transient computer-readable medium storing code for wireless communication, the code including instructions executable by a processor to perform methods as described in one or more aspects of aspects 1-17.

[0321] Aspect 37: A non-transient computer-readable medium storing a set of instructions for wireless communication, the set of instructions including one or more instructions which, when executed by one or more processors of a device, cause the device to perform methods as described in one or more aspects of aspects 1-17.

[0322] Aspect 38: An apparatus for wireless communication at a device, comprising: a processor; a memory coupled to the processor; and instructions stored in the memory and executable by the processor to cause the apparatus to perform methods as described in one or more aspects of aspects 18-32.

[0323] Aspect 39: An apparatus for wireless communication, comprising a memory and one or more processors coupled to the memory, the one or more processors being configured to perform methods as described in one or more aspects of aspects 18-32.

[0324] Aspect 40: An apparatus for wireless communication, comprising at least one means for performing a method as described in one or more aspects of aspects 18-32.

[0325] Aspect 41: A non-transient computer-readable medium storing code for wireless communication, the code including instructions executable by a processor to perform methods as described in one or more aspects of aspects 18-32.

[0326] Aspect 42: A non-transient computer-readable medium storing a set of instructions for wireless communication, the set of instructions including one or more instructions which, when executed by one or more processors of a device, cause the device to perform methods as described in one or more aspects of aspects 18-32.

[0327] The foregoing disclosure provides explanations and descriptions, but is not intended to be exhaustive or to limit the aspects to the precise forms disclosed. Modifications and variations may be made in light of the foregoing disclosure or may be obtained through practice.

[0328] As used herein, the term "component" is intended to be broadly interpreted as hardware and / or a combination of hardware and software. "Software" should be broadly interpreted as instructions, instruction sets, code, code segments, program code, programs, subroutines, software modules, applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, and / or functions, whether referred to as software, firmware, middleware, microcode, hardware description languages, or other terms. As used herein, a "processor" is implemented in hardware and / or a combination of hardware and software. It will be apparent that the systems and / or methods described herein can be implemented in various forms of hardware and / or combinations of hardware and software. The actual dedicated control hardware or software code used to implement these systems and / or methods is not limited in any way. Therefore, the operation and behavior of these systems and / or methods are described herein without reference to any specific software code, as those skilled in the art will understand that the software and hardware can be designed to implement these systems and / or methods, at least in part, based on the description herein.

[0329] As used in this article, depending on the context, "meeting the threshold" can mean a value greater than the threshold, greater than or equal to the threshold, less than the threshold, less than or equal to the threshold, equal to the threshold, not equal to the threshold, etc.

[0330] Although specific combinations of features are described in the claims and / or disclosed in the specification, these combinations are not intended to limit the disclosure of aspects. Many of these features may be combined in ways not specifically described in the claims and / or disclosed in the specification. The disclosure of aspects includes each dependent claim in combination with each other claim in the claim set. As used herein, the phrase “at least one of” refers to any combination of these items, including a single member. As an example, “at least one of a, b, or c” is intended to cover: a, b, c, a+b, a+c, b+c, and a+b+c, as well as any combination having multiple identical elements (e.g., a+a, a+a+a, a+a+b, a+a+c, a+b+b, a+c+c, b+b, b+b+b, b+b+c, c+c, and c+c+c, or any other ordering of a, b, and c).

[0331] The elements, actions, or instructions used herein should not be construed as critical or necessary unless explicitly stated otherwise. Furthermore, as used herein, the articles “a” and “a certain” are intended to include one or more items and may be used interchangeably with “one or more.” Additionally, as used herein, the article “the” is intended to include one or more items referenced in conjunction with the article “the” and may be used interchangeably with “one or more.” Furthermore, as used herein, the terms “set” and “group” are intended to include one or more items and may be used interchangeably with “one or more.” In cases where only one item is intended, the phrase “only one” or similar language is used. Moreover, as used herein, the terms “have,” “contain,” “include,” etc., are intended to be open-ended terms that do not limit the elements they modify (e.g., the element “has” A may also have B). Furthermore, the phrase “based on” is intended to mean “at least partially based on” unless otherwise explicitly stated. Moreover, as used herein, the term “or” is intended to be inclusive when used in a sequence and may be used interchangeably with “and / or” unless otherwise explicitly stated (e.g., in combination with “either of” or “only one of”).

Claims

1. A method for performing wireless communication by a first device, comprising: Determine that the power threshold of the first device is met, wherein the power threshold is related to the battery level of the first device or the availability of the processing resources of the first device; as well as The channel state feedback processing type is switched from a first channel state feedback processing type using a first neural network architecture to a second channel state feedback processing type using a second neural network architecture or a non-neural network-based processing type, at least in part based on the determination that the power threshold of the first device is met, wherein the second channel state feedback processing type consumes less power than the first channel state feedback processing type.

2. The method of claim 1, further comprising: Before determining that the power threshold of the first device is met, transmit the first channel state feedback processed using the first channel state feedback processing type; as well as After switching from the first channel state feedback processing type to the second channel state feedback processing type, the second channel state feedback processed using the second channel state feedback processing type is transmitted.

3. The method of claim 1, further comprising: The second channel state feedback processing type is used at least in part to determine channel state information for reporting, based on a change from the first channel state feedback processing type to the second channel state feedback processing type.

4. The method of claim 1, wherein at least one of the first channel state feedback processing type or the second channel state feedback processing type includes generating the following: Type-I channel state information, wherein the Type-I channel state information is generated using a beam selection scheme, in which the first device selects the optimal beam index for channel state feedback. Type-II channel state information, wherein the Type-II channel state information is generated using a beam combining scheme in which the first device uses the beam index to calculate the optimal linear combination of coefficients for various beams on a per-subband basis for channel state feedback. Type-III channel state information, where Type-III channel state information is generated using neural network-based processing techniques, or Its combination.

5. The method of claim 1, further comprising: Receive signaling indicating the configuration used for switching channel state feedback processing; and The transition from the first channel state feedback processing type to the second channel state feedback processing type includes: The switch from the first channel state feedback processing type to the second channel state feedback processing type is based at least in part on the configuration used for switching channel state feedback processing.

6. The method of claim 5, wherein the signaling includes: Radio resource control signaling, Downlink control information signaling, Media access control (MAC) control element CE signaling, or Its combination.

7. The method of claim 5, wherein the configuration for switching the channel state feedback processing includes information identifying the following: The power threshold, The first channel state feedback processing type. The second channel state feedback processing type, or Its combination.

8. The method of claim 1, wherein the power threshold is a threshold defined by the first device.

9. The method of claim 1, further comprising: Information identifying the second channel state feedback processing type is transmitted, at least in part, based on a transition from the first channel state feedback processing type to the second channel state feedback processing type.

10. The method of claim 9, wherein the information identifying the second channel state feedback processing type is included in the physical uplink control channel or the physical uplink shared channel.

11. The method of claim 1, further comprising: After switching to the second channel state feedback processing type, it switches back to the first channel state feedback processing type.

12. The method of claim 11, wherein the conversion to the first channel state feedback processing type is based at least in part on the following: The threshold time period has expired. The power threshold must be met. Meet another power threshold, The first device is connected to a power source, or Its combination.

13. The method of claim 11, wherein the conversion to the first channel state feedback processing type is based at least in part on the following: Upon receiving signaling configuring the transition to the first channel state feedback processing type. The first device determines whether the switching criteria are met, or Its combination.

14. The method of claim 11, further comprising: Information identifying the first channel state feedback processing type is transmitted, at least in part, based on the transition to the first channel state feedback processing type.

15. A first device for wireless communication, comprising: Memory; as well as One or more processors coupled to the memory, the memory and the one or more processors being configured to: Determining that a power threshold for the first device is met, wherein the power threshold is related to the battery level of the first device or the availability of the processing resources of the first device; and The channel state feedback processing type is switched from a first channel state feedback processing type using a first neural network architecture to a second channel state feedback processing type using a second neural network architecture or a non-neural network-based processing type, at least in part based on the determination that the power threshold of the first device is met, wherein the second channel state feedback processing type consumes less power than the first channel state feedback processing type.

16. The first device of claim 15, wherein the one or more processors are further configured to: Before determining that the power threshold of the first device is met, transmit first channel state feedback processed using the first channel state feedback processing type; and After switching from the first channel state feedback processing type to the second channel state feedback processing type, the second channel state feedback processed using the second channel state feedback processing type is transmitted.

17. The first device of claim 15, wherein the one or more processors are further configured to: The second channel state feedback processing type is used at least in part to determine channel state information for reporting, based on a change from the first channel state feedback processing type to the second channel state feedback processing type.

18. The first device of claim 15, wherein at least one of the first channel state feedback processing type or the second channel state feedback processing type includes generating the following: Type-I channel state information, wherein the Type-I channel state information is generated using a beam selection scheme, in which the first device selects the optimal beam index for channel state feedback. Type-II channel state information, wherein the Type-II channel state information is generated using a beam combining scheme in which the first device uses the beam index to calculate the optimal linear combination of coefficients for various beams on a per-subband basis for channel state feedback. Type-III channel state information, where Type-III channel state information is generated using neural network-based processing techniques, or Its combination.

19. The first device of claim 15, wherein the one or more processors are further configured to: Receive signaling indicating the configuration for switching channel state feedback processing; and The transition from the first channel state feedback processing type to the second channel state feedback processing type includes: The switch from the first channel state feedback processing type to the second channel state feedback processing type is based at least in part on the configuration used for switching channel state feedback processing.

20. The first device of claim 19, wherein the signaling includes: Radio resource control signaling, Downlink control information signaling, Media access control (MAC) control element CE signaling, or Its combination.

21. The first device of claim 19, wherein the configuration for switching the channel state feedback processing includes information identifying the following: The power threshold, The first channel state feedback processing type. The second channel state feedback processing type, or Its combination.

22. The first device of claim 15, wherein the power threshold is a threshold defined by the first device.

23. The first device of claim 15, wherein the one or more processors are further configured to: Information identifying the second channel state feedback processing type is transmitted, at least in part, based on a transition from the first channel state feedback processing type to the second channel state feedback processing type.

24. The first device of claim 23, wherein the information identifying the second channel state feedback processing type is included in the physical uplink control channel or the physical uplink shared channel.

25. The first device of claim 15, wherein the one or more processors are further configured to: After switching to the second channel state feedback processing type, it switches back to the first channel state feedback processing type.

26. The first device of claim 25, wherein the conversion to the first channel state feedback processing type is based at least in part on the following: The threshold time period has expired. The power threshold must be met. Meet another power threshold, The first device is connected to a power source, or Its combination.

27. The first device of claim 25, wherein the transition to the first channel state feedback processing type is based at least in part on the following: Upon receiving signaling configuring the transition to the first channel state feedback processing type. The first device determines whether the switching criteria are met, or Its combination.

28. The first device of claim 25, wherein the one or more processors are further configured to: Information identifying the first channel state feedback processing type is transmitted, at least in part, based on the transition to the first channel state feedback processing type.

29. A method for performing wireless communication by a second device, comprising: Receive first channel state feedback from a first device, which is processed using a first channel state feedback processing type, the first channel state feedback processing type using a first neural network architecture; as well as After meeting a power threshold related to the battery level of the first device or the availability of the processing resources of the first device, second channel state feedback is received using a second channel state feedback processing type that uses a second neural network architecture or a non-neural network-based processing type, wherein the second channel state feedback processing type consumes less power than the first channel state feedback processing type.

30. The method of claim 29, further comprising: The first channel state feedback is decoded at least in part based on the first channel state feedback processing type; as well as The second channel state feedback is decoded at least in part based on the second channel state feedback processing type.

31. The method of claim 29, wherein at least one of the first channel state feedback or the second channel state feedback comprises: Type-I channel state information, Type-II channel state information, Type-III channel state information, or Its combination.

32. The method of claim 29, further comprising: The signaling is transmitted to indicate the configuration for switching the channel state feedback processing so that the first device switches to using the second channel state feedback processing type in response to the power threshold being met.

33. The method of claim 32, wherein the signaling comprises: Radio resource control signaling, Downlink control information signaling, Media access control (MAC) control element CE signaling, or Its combination.

34. The method of claim 32, wherein the configuration for switching the channel state feedback processing includes information identifying the following: The power threshold, First channel state feedback processing type The second channel state feedback processing type, or Its combination.

35. A second device for wireless communication, comprising: Memory; as well as One or more processors coupled to the memory, the one or more processors being configured to: Receive first channel state feedback from a first device, which is processed using a first channel state feedback processing type, the first channel state feedback processing type using a first neural network architecture; as well as After meeting a power threshold related to the battery level of the first device or the availability of the processing resources of the first device, second channel state feedback is received using a second channel state feedback processing type that uses a second neural network architecture or a non-neural network-based processing type, wherein the second channel state feedback processing type consumes less power than the first channel state feedback processing type.

36. The second device of claim 35, wherein the one or more processors are further configured to: Decoding the first channel state feedback is based at least in part on the first channel state feedback processing type; and The second channel state feedback is decoded at least in part based on the second channel state feedback processing type.

37. The second device of claim 35, wherein at least one of the first channel state feedback or the second channel state feedback comprises: Type-I channel state information, Type-II channel state information, Type-III channel state information, or Its combination.

38. The second device of claim 35, wherein the one or more processors are further configured to: The signaling is transmitted to indicate the configuration for switching the channel state feedback processing so that the first device switches to using the second channel state feedback processing type in response to the power threshold being met.

39. The second device of claim 38, wherein the signaling includes: Radio resource control signaling, Downlink control information signaling, Media access control (MAC) control element CE signaling, or Its combination.

40. The second device of claim 38, wherein the configuration for switching the channel state feedback processing includes information identifying the following: The power threshold, First channel state feedback processing type The second channel state feedback processing type, or Its combination.

Images