Scheduling for Energy Autoencoder-Based Non-Coherent Transmission

Abstract

Aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may identify a plurality of resource element (RE) segments associated with a scheduled communication including a source bit sequence, each RE segment including one or more REs in one or more scheduled physical resource blocks associated with the scheduled communication. The UE may communicate with a device at least in part based on corresponding energy included on one or more REs included in the plurality of RE segments associated with the scheduled communication. For example, communicating with the device may include using a neural network to transmit or detect a subsequence associated with the RE segment, the neural network modulating the subsequence associated with the RE segment onto one or more REs in the RE segment. Numerous other aspects are provided.

Description

[0001] Public domain

[0002] Aspects of the present disclosure generally relate to wireless communications and relate to techniques and apparatus for scheduling non - coherent transmissions based on energy auto - encoders.

[0003] Background

[0004] Wireless communication systems are widely deployed to provide various telecommunication services such as telephony, video, data, messaging, and broadcasting. A typical wireless communication system may employ a multiple access technique that is capable of supporting communication with multiple users by sharing available system resources (e.g., bandwidth, transmit power, etc.). Examples of such multiple access techniques 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 enhanced set of mobile standards for the universal mobile telecommunications system (UMTS) promulgated by the 3rd Generation Partnership Project (3GPP).

[0005] A wireless network may include several base stations (BSs) capable of supporting communication of several user equipments (UEs). A user equipment (UE) may communicate with a base station (BS) via a downlink and an uplink. The downlink (or forward link) refers to the communication link from the BS to the UE, and the uplink (or reverse link) refers to the communication link from the UE to the BS. As will be described in more detail herein, a BS may be referred to as a B - node, gNB, access point (AP), radio head, transmission reception point (TRP), new radio (NR) BS, 5G B - node, and so on.

[0006] The above multiple access techniques have been adopted in various telecommunication standards to provide a common protocol that enables different user equipments to communicate at the urban, national, regional, and even global levels. New Radio (NR) (which may also be referred to as 5G) is an enhanced set of the LTE mobile standard promulgated by the 3rd Generation Partnership Project (3GPP). NR is designed to better support mobile broadband Internet access by using Orthogonal Frequency Division Multiplexing with Cyclic Prefix (CP-OFDM) on the downlink (DL), CP-OFDM and / or SC-FDM (e.g., also referred to as Discrete Fourier Transform Spread OFDM (DFT-s-OFDM)) on the uplink (UL), and supporting beamforming, Multiple-Input Multiple-Output (MIMO) antenna technology, and carrier aggregation to improve spectral efficiency, reduce costs, improve services, utilize new spectrum, and better integrate with other open standards. As the demand for mobile broadband access continues to grow, further improvements to LTE, NR, and other radio access technologies are still useful.

[0007] Overview

[0008] In some aspects, a method of performing wireless communication by a User Equipment (UE) includes: identifying a plurality of Resource Element (RE) segments associated with a scheduled communication including a source bit sequence, where each of the plurality of RE segments includes one or more REs in one or more Scheduled Physical Resource Blocks (PRBs) associated with the scheduled communication; and communicating with a device at least in part based on corresponding energy included on one or more REs in the plurality of RE segments associated with the scheduled communication, where each of the plurality of RE segments is associated with a subsequence of the source bit sequence segmented into a plurality of subsequences, and where communicating with the device includes using a neural network to transmit or detect a subsequence associated with an RE segment in the plurality of RE segments, the neural network modulating the subsequence associated with the RE segment onto one or more REs in the RE segment.

[0009] In some aspects, a UE for wireless communication includes a memory; and one or more processors operatively coupled to the memory, the memory and the one or more processors being configured to: identify a plurality of RE segments associated with a scheduled communication including a source bit sequence, wherein the plurality of RE segments each include one or more REs in one or more scheduled PRBs associated with the scheduled communication; and communicate with a device at least in part based on corresponding energy included in one or more REs in the plurality of RE segments associated with the scheduled communication, wherein the plurality of RE segments are each associated with a subsequence of the source bit sequence segmented into a plurality of subsequences, and wherein communicating with the device includes using a neural network to transmit or detect a subsequence associated with an RE segment among the plurality of RE segments, the neural network modulating the subsequence associated with the RE segment onto one or more REs in the RE segment.

[0010] In some aspects, a non-transitory computer-readable medium storing an instruction set for wireless communication includes one or more instructions that, when executed by one or more processors of a UE, cause the UE to: identify a plurality of RE segments associated with a scheduled communication including a source bit sequence, wherein the plurality of RE segments each include one or more REs in one or more scheduled PRBs associated with the scheduled communication; and communicate with a device at least in part based on corresponding energy included in one or more REs in the plurality of RE segments associated with the scheduled communication, wherein the plurality of RE segments are each associated with a subsequence of the source bit sequence segmented into a plurality of subsequences, and wherein communicating with the device includes using a neural network to transmit or detect a subsequence associated with an RE segment among the plurality of RE segments, the neural network modulating the subsequence associated with the RE segment onto one or more REs in the RE segment.

[0011] In some aspects, a device for wireless communication includes: means for identifying a plurality of RE segments associated with a scheduled communication including a source bit sequence, wherein the plurality of RE segments each include one or more REs in one or more scheduled PRBs associated with the scheduled communication; and means for communicating with a device at least in part based on corresponding energy included in one or more REs in the plurality of RE segments associated with the scheduled communication, wherein the plurality of RE segments are each associated with a subsequence of the source bit sequence segmented into a plurality of subsequences, and wherein the means for communicating with the device includes means for using a neural network to transmit or detect a subsequence associated with an RE segment among the plurality of RE segments, the neural network modulating the subsequence associated with the RE segment onto one or more REs in the RE segment.

[0012] Each aspect generally includes, for example, methods, apparatuses, systems, computer program products, non-transitory computer-readable media, user equipment, base stations, wireless communication devices, and / or processing systems substantially as described herein with reference to the figures and as illustrated in the figures and the description.

[0013] The foregoing has outlined rather broadly the features and technical advantages of examples in accordance with the present disclosure in order that the detailed description that follows may be better understood. Additional features and advantages will be described hereinafter. The disclosed concepts and specific examples may be readily utilized as a basis for modifying or designing other structures for carrying out the same purposes as the present disclosure. Such equivalent constructions do not depart from the scope of the appended claims. The characteristics of the concepts disclosed herein, in terms of both their organization and method of operation, as well as the associated advantages, will be better understood from the following description when considered in conjunction with the accompanying figures. Each of the figures is provided for the purpose of illustration and description, and not as a definition of the limits of the claims. Brief Description of the Drawings

[0015] To understand in detail the features stated above of the present disclosure, a more specific description may be had with reference to the aspects, some of which are illustrated in the figures. It should be noted, however, that the figures illustrate only certain typical aspects of the present disclosure and should not be considered as limiting its scope, as the description may admit of other equally effective aspects. The same reference numerals in different figures may identify the same or similar elements.

[0016] Figure 1 is a diagram illustrating an example of a wireless network in accordance with various aspects of the present disclosure.

[0017] Figure 2 is a diagram illustrating an example of communication between a base station and a UE in a wireless network in accordance with various aspects of the present disclosure.

[0018] Figure 3 is a diagram illustrating an example of a time slot format in accordance with various aspects of the present disclosure.

[0019] Figure 4 is a diagram illustrating an example of coherent and non-coherent wireless communication in accordance with various aspects of the present disclosure.

[0020] Figure 5 is a diagram illustrating an example of non-coherent wireless communication using neural networks on the transmitter side and the receiver side for modulation and detection in accordance with various aspects of the present disclosure.

[0021] Figure 6 is a diagram illustrating an example associated with scheduling non-coherent transmission based on an energy autoencoder in accordance with various aspects of the present disclosure.

[0022] Figure 7is a diagram illustrating an example process associated with scheduling energy autoencoder - based non - coherent transmission in accordance with various aspects of the present disclosure.

[0023] Figure 8 is a block diagram of an example apparatus for wireless communication in accordance with various aspects of the present disclosure.

[0024] Detailed Description

[0025] Aspects of the present disclosure are described more fully hereinafter with reference to the accompanying drawings. However, the present disclosure may be embodied in many different forms and should not be construed as limited to any specific structure or function presented throughout this disclosure. Rather, these aspects are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the present disclosure to those skilled in the art. Based on the teachings herein, those skilled in the art should appreciate that the scope of the present disclosure is intended to cover any aspect of the present disclosure disclosed herein, whether implemented independently of or in combination with any other aspect of the present disclosure. For example, any number of the aspects set forth herein may be used to implement an apparatus or practice a method. Additionally, the scope of the present disclosure is intended to cover such apparatus or methods practiced using other structures, functionality, or a combination of structures and functionality that supplement or are additional to the various aspects of the present disclosure set forth herein. It should be understood that any aspect of the present disclosure disclosed herein may be implemented by one or more elements of a claim.

[0026] Certain aspects of a telecommunications system will now be presented with reference to various apparatuses and techniques. These apparatuses and techniques will be described in detail hereinafter and illustrated in the drawings by various blocks, modules, components, circuits, steps, processes, algorithms, etc. (collectively referred to as "elements"). These elements may be implemented using hardware, software, or a combination thereof. Whether such elements are implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system.

[0027] It should be noted that although aspects may be described herein using terminology commonly associated with 5G or NR radio access technology (RAT), aspects of the present disclosure may be applied to other RATs, such as 3G RAT, 4G RAT, and / or RATs after 5G (e.g., 6G).

[0028] Figure 1FIG. is an illustration depicting an example of a wireless network 100 in accordance with various aspects of the present disclosure. The wireless network 100 can be a 5G (NR) network and / or an LTE network, etc. or can include elements thereof. The wireless network 100 can include several base stations 110 (shown as BS 110a, BS 110b, BS 110c, and BS 110d) and other network entities. A base station (BS) is an entity that communicates with user equipment (UE) and can also be referred to as an NR BS, Node B, gNB, 5G Node B (NB), access point, transmission reception point (TRP), etc. Each BS can provide communication coverage for a specific geographic area. In 3GPP, the term "cell" can refer to the coverage area of a BS and / or the BS subsystem serving that coverage area, depending on the context in which the term is used.

[0029] The BS can provide communication coverage for macro cells, pico cells, femto cells, and / or another type of cell. A macro cell can cover a relatively large geographic area (e.g., with a radius of several kilometers) and can allow unrestricted access by UEs having a service subscription. A pico cell can cover a relatively small geographic area and can allow unrestricted access by UEs having a service subscription. A femto cell can cover a relatively small geographic area (e.g., a residence) and can allow restricted access by UEs associated with the femto cell (e.g., UEs in a closed subscriber group (CSG)). The BS for a macro cell can be referred to as a macro BS. The BS for a pico cell can be referred to as a pico BS. The BS for a femto cell can be referred to as a femto BS or a home BS. In Figure 1 the example shown, BS 110a can be a macro BS for macro cell 102a, BS 110b can be a pico BS for pico cell 102b, and BS 110c can be a femto BS for femto cell 102c. The BS can support one or more (e.g., three) cells. The terms "eNB", "base station", "NR BS", "gNB", "TRP", "AP", "Node B", "5G NB", and "cell" can be used interchangeably herein.

[0030] In some aspects, a cell can be non-stationary and the geographic area of a cell can move according to the location of a mobile BS. In some aspects, the BSs can be interconnected with each other and / or interconnected to one or more other BSs or network nodes (not shown) in the wireless network 100 via various types of backhaul interfaces, such as direct physical connections or virtual networks, using any suitable transport network.

[0031] The wireless network 100 may also include a relay station. A relay station is an entity that can receive a transmission of data from an upstream station (e.g., a BS or a UE) and send the transmission of the data to a downstream station (e.g., a UE or a BS). A relay station can also be a UE that can relay transmissions for other UEs. In Figure 1 In the example shown in, relay BS 110d can communicate with macro BS 110a and UE 120d to facilitate communication between BS 110a and UE 120d. A relay BS can also be referred to as a relay station, a relay base station, a relay, etc.

[0032] The wireless network 100 can be a heterogeneous network that includes different types of BSs (such as macro BSs, pico BSs, femto BSs, relay BSs, etc.). These different types of BSs may have different transmit power levels, different coverage areas, and different impacts on interference in the wireless network 100. For example, a macro BS may have a high transmit power level (e.g., 5 to 40 watts), while pico BSs, femto BSs, and relay BSs may have lower transmit power levels (e.g., 0.1 to 2 watts).

[0033] The network controller 130 can be coupled to the set of BSs and can provide coordination and control of these BSs. The network controller 130 can communicate with each BS via a backhaul. These BSs can also communicate with each other directly or indirectly via a wireless or wired backhaul.

[0034] UEs 120 (e.g., 120a, 120b, 120c) can be dispersed throughout the wireless network 100, and each UE can be stationary or mobile. A UE can also be referred to as an access terminal, a terminal, a mobile station, a subscriber unit, a station, etc. A UE can be a cellular phone (e.g., a smart phone), 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, a camera, a gaming device, a netbook, a smartbook, a superbook, a medical device or equipment, a biometric sensor / device, a wearable device (smart watch, smart clothing, smart glasses, smart wristband, smart jewelry (e.g., smart ring, smart bracelet)), an entertainment device (e.g., a music or video device, or a satellite radio), a vehicle component or sensor, a smart meter / sensor, an industrial manufacturing equipment, a global positioning system device, or any other suitable device configured to communicate via a wireless or wired medium.

[0035] Some UEs may be considered machine type communication (MTC) devices, or evolved or enhanced machine type communication (eMTC) UEs. MTC and eMTC UEs include, for example, robots, drones, remote devices, sensors, meters, monitors, and / or location tags, which may communicate with a base station, another device (e.g., a remote device), or some other entity. A wireless node may provide connectivity to a network (e.g., a wide area network such as the Internet or a cellular network) or provide connectivity to the network, for example, via a wired or wireless communication link. Some UEs may be considered Internet of Things (IoT) devices and / or may be implemented as narrowband IoT (NB-IoT) devices. Some UEs may be considered customer premise equipment (CPE). UE 120 may be included inside a housing that houses components of UE 120, such as processor components and / or memory components. In some aspects, the processor components and the memory components may be coupled together. For example, the processor components (e.g., one or more processors) and the memory components (e.g., a memory) may be operatively coupled, communicatively coupled, electronically coupled, and / or electrically coupled.

[0036] Generally, any number of wireless networks may be deployed in a given geographical area. Each wireless network may support a particular RAT and may operate on one or more frequencies. The RAT may also be referred to as a radio technology, an air interface, etc. The frequency may also be referred to as a carrier, a frequency channel, etc. Each frequency may support a single RAT in a given geographical area to avoid interference between wireless networks of different RATs. In some cases, an NR or 5G RAT network may be deployed.

[0037] In some aspects, 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., communicate with each other without using the base station 110 as an intermediary). For example, UE 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 or vehicle-to-infrastructure (V2I) protocols), and / or mesh networks. In such a case, UE 120 may perform scheduling operations, resource selection operations, and / or other operations described elsewhere herein as performed by the base station 110.

[0038] Devices of the wireless network 100 may communicate using the electromagnetic spectrum, which may be subdivided into various categories, bands, channels, etc. based on frequency or wavelength. For example, devices of the wireless network 100 may communicate using an operating band having a first frequency range (FR1) and / or may communicate using an operating band having a second frequency range (FR2), where the first frequency range (FR1) may span from 410 MHz to 7.125 GHz and the second frequency range (FR2) may span from 24.25 GHz to 52.6 GHz. The frequencies between FR1 and FR2 are sometimes referred to as mid-band frequencies. Although a portion of FR1 is greater than 6 GHz, FR1 is generally referred to as the “sub-6 GHz band”. Similarly, although different from the extremely high frequency (EHF) band (30 GHz – 300 GHz), which is identified by the International Telecommunication Union (ITU) as the “millimeter wave” band, FR2 is generally referred to as the “millimeter wave” band. Thus, unless specifically stated otherwise, it should be understood that if used herein, terms such as “sub-6 GHz” may generically represent frequencies less than 6 GHz, frequencies within FR1, and / or mid-band frequencies (e.g., greater than 7.125 GHz). Similarly, unless specifically stated otherwise, it should be understood that if used herein, terms such as “millimeter wave” may generically represent frequencies within the EHF band, frequencies within FR2, and / or mid-band frequencies (e.g., less than 24.25 GHz). It is contemplated that the frequencies included in FR1 and FR2 may be modified, and the techniques described herein are applicable to those modified frequency ranges.

[0039] As indicated above, Figure 1 is provided as an example. Other examples may be different from those Figure 1 described.

[0040] Figure 2 is a diagram illustrating example 200 in which a base station 110 and a UE 120 are in communication in the wireless network 100 in accordance with various aspects of the present disclosure. The base station 110 may be equipped with T antennas 234a through 234t, and the UE 120 may be equipped with R antennas 252a through 252r, where generally T ≥ 1 and R ≥ 1.

[0041] At base station 110, transmit processor 220 may receive data for one or more UEs from data source 212, select one or more modulation and coding schemes (MCSs) for each UE at least in part based on channel quality indicators (CQIs) received from each UE, process (e.g., encode and modulate) the data for each UE at least in part based on the selected MCS(s) for each UE, and provide data symbols for all UEs. Transmit processor 220 may also process system information (e.g., for semi-static resource partitioning information (SRPI)) and control information (e.g., CQI requests, grants, and / or upper layer signaling), and provide overhead symbols and control symbols. Transmit processor 220 may also generate reference symbols for reference signals (e.g., cell-specific reference signal (CRS) or demodulation reference signal (DMRS)) and synchronization signals (e.g., primary synchronization signal (PSS) or secondary synchronization signal (SSS)). Transmit (TX) multiple-input multiple-output (MIMO) processor 230 may perform spatial processing (e.g., precoding) on the data symbols, control symbols, overhead symbols, and / or reference symbols, if applicable, and may provide T output symbol streams to T modulators (MODs) 232a through 232t. Each modulator 232 may process its respective output symbol stream (e.g., for OFDM) to obtain an output sample stream. Each modulator 232 may further process (e.g., convert to analog, amplify, filter, and upconvert) the output sample stream to obtain a downlink signal. The T downlink signals from modulators 232a through 232t may be transmitted via T antennas 234a through 234t, respectively.

[0042] At the UE 120, antennas 252a through 252r may receive downlink signals from the base station 110 and / or other base stations and may provide the received signals to demodulators (DEMOD) 254a through 254r, respectively. Each demodulator 254 may condition (e.g., filter, amplify, down-convert, and digitize) the received signal to obtain input samples. Each demodulator 254 may further process the input samples (e.g., for OFDM) to obtain received symbols. The MIMO detector 256 may obtain the received symbols from all R demodulators 254a through 254r, perform MIMO detection on the received symbols when applicable, and provide detected symbols. The receive processor 258 may process (e.g., demodulate and decode) the detected symbols, provide the decoded data for the UE 120 to the data sink 260, and provide the decoded control information and system information to the controller / processor 280. The term "controller / processor" may refer to one or more controllers, one or more processors, or a combination thereof. The channel processor may determine reference signal received power (RSRP) parameters, received signal strength indicator (RSSI) parameters, reference signal received quality (RSRQ) parameters, and / or channel quality indicator (CQI) parameters, etc. In some aspects, one or more components of the UE 120 may be included in the housing 284.

[0043] The network controller 130 may include a communication unit 294, a controller / processor 290, and a memory 292. The network controller 130 may include, for example, one or more devices in the core network. The network controller 130 may communicate with the base station 110 via the communication unit 294.

[0044] Antennas (e.g., antennas 234a through 234t and / or antennas 252a through 252r) may include one or more antenna panels, antenna groups, antenna element sets, and / or antenna arrays, etc., or may be included therein. The antenna panel, antenna group, antenna element set, and / or antenna array may include one or more antenna elements. The antenna panel, antenna group, antenna element set, and / or antenna array may include a coplanar antenna element set and / or a non-coplanar antenna element set. The antenna panel, antenna group, antenna element set, and / or antenna array may include antenna elements within a single housing and / or antenna elements within multiple housings. The antenna panel, antenna group, antenna element set, and / or antenna array may include one or more antenna elements coupled to one or more transmission and / or reception components (such as Figure 2 one or more components) of

[0045] On the uplink, at the UE 120, the transmit processor 264 may receive and process data from the data source 262 and control information from the controller / processor 280 (e.g., for reports including RSRP, RSSI, RSRQ, and / or CQI). The transmit processor 264 may also generate reference symbols for one or more reference signals. The symbols from the transmit processor 264 may be precoded by the TX MIMO processor 266 when applicable, further processed by the modulators 254a through 254r (e.g., for DFT-s-OFDM or CP-OFDM), and transmitted to the base station 110. In some aspects, the modulator and demodulator (e.g., MOD / DEMOD 254) of the UE 120 may be included in the modem of the UE 120. In some aspects, the UE 120 includes a transceiver. The transceiver may include any combination of antennas 252, modulator and / or demodulator 254, MIMO detector 256, receive processor 258, transmit processor 264, and / or TX MIMO processor 266. The transceiver may be used by a processor (e.g., controller / processor 280) and the memory 282 to perform aspects of any of the methods described herein, e.g., as described with reference to Figures 6 - 7 as described.

[0046] At the base station 110, the uplink signals from the UE 120 and other UEs may be received by the antennas 234, processed by the demodulator 232, detected by the MIMO detector 236 when applicable, and further processed by the receive processor 238 to obtain the decoded data and control information transmitted by the UE 120. The receive processor 238 may provide the decoded data to the data sink 239 and the decoded control information to the controller / processor 240. The base station 110 may include a communication unit 244 and communicate with the network controller 130 via the communication unit 244. The base station 110 may include a scheduler 246 to schedule the UE 120 for downlink and / or uplink communication. In some aspects, the modulator and demodulator (e.g., MOD / DEMOD 232) of the base station 110 may be included in the modem of the base station 110. In some aspects, the base station 110 includes a transceiver. The transceiver may include any combination of antennas 234, modulator and / or demodulator 232, MIMO detector 236, receive processor 238, transmit processor 220, and / or TX MIMO processor 230. The transceiver may be used by a processor (e.g., controller / processor 240) and the memory 242 to perform aspects of any of the methods described herein, e.g., as described with reference to Figures 6 - 7 as described.

[0047] The controller / processor 240 of base station 110, the controller / processor 280 of UE 120, and / or Figure 2 any other component of Figure 2 may perform one or more techniques associated with scheduling energy autoencoder-based non-coherent transmissions, 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 of Figure 7 may perform or direct the operation of, for example Figure 7 process 700 and / or other processes as described herein. Memories 242 and 282 may store data and program codes for base station 110 and UE 120, respectively. In some aspects, memory 242 and / or memory 282 may include: a non-transitory computer-readable medium storing one or more instructions for wireless communication (e.g., code and / or program code). For example, when the one or more instructions are executed by one or more processors of base station 110 and / or UE 120 (e.g., directly executed, or after compilation, conversion, and / or interpretation), the one or more processors, UE 120, and / or base station 110 may be caused to perform or direct the operation of, for example Figure 7 process 700 and / or other processes as described herein. In some aspects, executing the instructions may include running the instructions, converting the instructions, compiling the instructions, and / or interpreting the instructions, etc.

[0048] In some aspects, UE 120 includes: means for identifying a plurality of resource element (RE) segments associated with a scheduled communication including a source bit sequence, where each of the plurality of RE segments includes one or more REs in one or more scheduled physical resource blocks (PRBs) associated with the scheduled communication, and / or means for communicating with a device based at least in part on respective energies included in one or more REs in the plurality of RE segments associated with the scheduled communication, where each of the plurality of RE segments is associated with a subsequence of the source bit sequence segmented into a plurality of subsequences, and where communicating with the device includes using a neural network to transmit or detect a subsequence associated with an RE segment in the plurality of RE segments, the neural network modulating the subsequence associated with the RE segment onto one or more REs in the RE segment. The means for UE 120 to perform the operations described herein may include, for example, one or more of antenna 252, demodulator 254, MIMO detector 256, receive processor 258, transmit processor 264, TX MIMO processor 266, modulator 254, controller / processor 280, or memory 282.

[0049] In some aspects, UE 120 includes means for receiving signaling indicating one or more of: a segmentation method associated with one or more resource elements (REs) in an RE segmentation, a segmentation method associated with one or more bits in a subsequence associated with the RE segmentation, or a neural network that modulates a subsequence associated with the RE segmentation onto one or more REs in the RE segmentation.

[0050] In some aspects, UE 120 includes means for determining that a scheduled communication includes a physical uplink control channel (PUCCH), means for determining a PUCCH format at least in part based on one or more segmentation methods or a transmission neural network associated with modulating the plurality of subsequences onto one or more RE segments among the plurality of RE segments, and / or means for transmitting the PUCCH at least in part based on the PUCCH format.

[0051] In some aspects, UE 120 includes means for determining a PUCCH resource set associated with the PUCCH, and / or means for modulating the plurality of subsequences onto one or more RE segments among the plurality of RE segments using one or more segmentation methods or a transmission neural network for different PUCCH resources within the PUCCH resource set, wherein the one or more segmentation methods or the transmission neural network are configured by a configuration associated with the PUCCH resource.

[0052] In some aspects, UE 120 includes: means for determining at least in part based on downlink control information (DCI) one or more segmentation methods or a transmission neural network associated with modulating the plurality of subsequences, the DCI indicating a PUCCH resource for hybrid automatic repeat request acknowledgement (HARQ-ACK) feedback associated with a physical downlink shared channel (PDSCH) scheduled by the DCI; and / or means for modulating the plurality of subsequences onto one or more RE segments among the plurality of RE segments using one or more segmentation methods or a transmission neural network for the PUCCH resource indicated in the DCI.

[0053] In some aspects, UE 120 includes: means for determining that a scheduled communication includes a physical downlink control channel (PDCCH); means for determining at least in part based on one or more resource element groups (REGs) bundled or control channel elements (CCEs) associated with the PDCCH one or more segmentation methods or a transmission neural network associated with modulating the plurality of subsequences onto one or more RE segments among the plurality of RE segments; and / or means for detecting a source bit sequence in the PDCCH at least in part based on the one or more segmentation methods or the transmission neural network.

[0054] In some aspects, UE 120 includes: means for determining a priority associated with one or more search spaces or control resource sets (CORESETs) at least in part based on the one or more segmentation methods or transmission neural networks, and / or means for monitoring the PDCCH at least in part based on the priority associated with the one or more search spaces or CORESETs.

[0055] In some aspects, UE 120 includes: means for determining a priority associated with the one or more search spaces or CORESETs at least in part based on the one or more segmentation methods or transmission neural networks, and / or means for suppressing the monitoring of the PDCCH at least in part based on the priority associated with the one or more search spaces or CORESETs.

[0056] Although Figure 2 the blocks in are illustrated as different components, the functions described above with respect to these blocks can be implemented using a single hardware, software, or combined component or a combination of various components. For example, the functions described with respect to the transmit processor 264, receive processor 258, and / or TX MIMO processor 266 can be performed by or under the control of the controller / processor 280.

[0057] As indicated above, Figure 2 is provided as an example. Other examples may be different from the example described with respect to Figure 2 .

[0058] Figure 3 is a diagram illustrating example 300 of a time slot format in accordance with various aspects of the present disclosure. As Figure 3 shown, the time-frequency resources in a radio access network can be divided into resource blocks, as shown by a single resource block (RB) 305. The RB 305 is sometimes referred to as a physical resource block (PRB). The RB 305 includes a set of subcarriers (e.g., 12 subcarriers) and a set of symbols (e.g., 14 symbols) that can be scheduled (e.g., by the base station 110) as a unit. In some aspects, the RB 305 can include a set of subcarriers in a single time slot. As shown, the single time-frequency resource included in the RB 305 can be referred to as a resource element (RE) 310. The RE 310 can include a single subcarrier (e.g., in frequency) and a single symbol (e.g., in time). The symbol can be referred to as an orthogonal frequency division multiplexing (OFDM) symbol. The RE 310 can be used to transmit a modulated symbol, which can be a real value or a complex value.

[0059] In some telecommunication systems (e.g., NR), an RB 305 can span 12 subcarriers (with subcarrier spacing such as 15 kilohertz (kHz), 30 kHz, 60 kHz, or 120 kHz, etc.) within a duration of 0.1 millisecond (ms). A radio frame can include 40 time slots and can have a length of 10 ms. Thus, each time slot can have a length of 0.25 ms. However, the time slot length can vary depending on the parameter design for communication (e.g., subcarrier spacing, cyclic prefix format, etc.). A time slot can be configured with a link direction for transmission (e.g., downlink or uplink). In some aspects, the link direction for a time slot can be dynamically configured.

[0060] As indicated above, Figure 3 is provided as an example. Other examples can be different from the example regarding Figure 3 described.

[0061] Figure 4 is a diagram illustrating Example 400 of coherent wireless communication and Example 450 of non - coherent wireless communication according to various aspects of the present disclosure. Figure 4 The coherent and / or non - coherent wireless communication illustrated in

[0062] As Figure 4 shown in Example 400, coherent wireless communication can involve the use of pilot signals and / or reference signals. A wireless communication device (referred to herein as the "transmitter") can transmit an information bit vector (e.g., a bit string carrying one or more types of information) by encoding the information bit vector to form one or more codewords each including a plurality of encoded bits. The transmitter can modulate the codewords to form one or more OFDM symbols, generate a pilot signal or a reference signal (e.g., demodulation reference signal (DMRS) and / or another suitable reference signal) associated with the one or more OFDM symbols, and transmit the pilot / reference signal and the OFDM symbols on a wireless physical channel (e.g., PxxCH, which can be a physical downlink control channel (PDCCH), physical downlink shared channel (PDSCH), physical uplink control channel (PUCCH), physical uplink shared channel (PUSCH), physical sidelink control channel (PSCCH), and / or physical sidelink shared channel (PSSCH)). The pilot / reference signal and the OFDM symbols can be transmitted on the wireless physical channel to another wireless communication device (referred to as the "receiver").

[0063] As Figure 4As further shown in [description], the receiver can receive pilot / reference signals and OFDM symbols via a physical channel, and can use the pilot / reference signals to obtain channel state information (CSI) associated with the physical channel. For example, the receiver can demodulate and decode the pilot / reference signals and OFDM symbols, can perform channel estimation of the physical channel based at least in part on the demodulation and / or decoding of the pilot / reference signals, and can adjust or modify demodulation and / or decoding parameters for the receiver based at least in part on the channel estimation, so as to improve the efficiency and performance of the receiver's demodulation and / or decoding.

[0064] In some cases, coherent communication in a wireless system may not be optimal at low signal-to-noise ratio (SNR). For example, the energy used to transmit, decode, and / or measure pilot / reference signals may be wasted because, at low SNR, the pilot / reference signals may contain little or no useful information for the receiver. Additionally, attempting to perform channel estimation at low SNR may result in inaccurate and / or poor-quality channel estimates, which may in turn lead to degraded performance in demodulation and / or decoding. Additionally or alternatively, coherent wireless communication may not be optimal in other use cases, such as high Doppler scenarios (e.g., when the transmitter and / or receiver are moving at a high rate), when the transmitted packet has a small payload size (e.g., such that the transmitted packet cannot accommodate additional payload for pilot signals or DMRS), and / or asynchronous communication use cases, etc.

[0065] Accordingly, as Figure 4 and further shown in Example 450, the transmitter and receiver can perform non-coherent communication to improve demodulation and / or decoding performance in low SNR scenarios. As described herein, "non-coherent communication" generally can refer to a wireless communication scheme in which the transmitter does not transmit any pilot signals or reference signals for the OFDM symbols carrying data / information (e.g., PxxCH without DMRS). In this case, the receiver directly demodulates and decodes the received OFDM symbols without performing channel estimation based on pilot signals or reference signals.

[0066] Non-coherent communication schemes rely on the principle of channel coherence, i.e., the channel properties adjacent to the encoded OFDM symbols (e.g., adjacent in time resources and / or frequency resources) are the same or approximately the same. This allows the transmitter to use differential modulation (e.g., where information is modulated at least in part based on the phase difference between adjacent encoded OFDM symbols) and / or sequence-based modulation (e.g., where information is jointly modulated over a sequence of OFDM symbols). However, the longer the channel coherence is used (e.g., the more adjacent encoded OFDM symbols that are considered coherent), the greater the complexity of encoding at the transmitter and decoding at the receiver. In some channel coding / decoding techniques, channel coherence can lead to exponential growth in encoding and decoding. Accordingly, non-coherent wireless communication is often difficult to implement in practice.

[0067] Some aspects described herein relate to techniques and apparatus for scheduling non-coherent transmissions at least in part based on an energy autoencoder. For example, an autoencoder can be an unsupervised neural network that can be trained to efficiently compress and encode data and / or reconstruct data from a reduced encoded representation that is as close as possible to the original input. Accordingly, as described herein, an energy autoencoder can be an unsupervised neural network that can modulate an input signal (e.g., an input bit sequence) onto the energy on a physical layer resource and / or demodulate a transmitted signal at least in part based on the energy on the physical layer resource. For example, in some aspects, a transmitter can use one or more neural networks to modulate a source bit sequence onto RE segments that include one or more REs in one or more PRBs associated with a scheduled communication (e.g., a PxxCH communication), where the total transmit power is normalized over each RE segment (e.g., the output from the one or more neural networks can include energy that is normalized over the REs in each RE segment). Accordingly, a receiver can use one or more neural networks to demodulate the transmitted bit sequence to detect the source bit sequence. In this way, energy-based modulation can be robust to fading in a wireless channel, which can be particularly useful for non-coherent transmissions where pilot signals, DMRS, or another suitable reference signal for enabling channel estimation are not available. Additionally, neural networks can provide computational efficiency to configure modulation schemes that are robust to different fading scenarios, and segmenting a source bit sequence with a large number of bits into multiple subsequences each corresponding to one RE segment reduces receiver complexity.

[0068] As indicated above, Figure 4 is provided as an example. Other examples may be different from the example described with respect to Figure 4 described.

[0069] Figure 5FIG. 500 is a diagram illustrating an example 500 of non - coherent wireless communication using a transmitter - side and a receiver - side neural network for modulation and detection in accordance with various aspects of the present disclosure. In some aspects, Figure 5 the non - coherent wireless communication shown in Figure 5 can be performed between a transmitter and a receiver in a wireless network. For example, in some aspects, the receiver can be a base station and the transmitter can be a UE that is scheduled to transmit PUCCH and / or PUSCH to the base station. Additionally or alternatively, the transmitter can be a base station and the receiver can be a UE that is scheduled to receive PDCCH and / or PDSCH from the base station. Additionally or alternatively, the transmitter can be a first UE and the receiver can be a second UE, in which case the first UE can be scheduled to transmit PSCCH and / or PSSCH on a sidelink and the second UE can be scheduled to receive PSCCH and / or PSSCH on the sidelink.

[0070] As Figure 5 shown in Figure 5 , the transmitter and the receiver can perform non - coherent wireless communication, whereby the transmitted PxxCH does not include DMRS, pilot signals, or another reference signal for enabling channel estimation at the receiver. Generally speaking, as described above, non - coherent wireless communication can improve demodulation and / or decoding performance in low SNR, high Doppler, small packet, and / or asynchronous communication scenarios, among other examples.

[0071] For example, when performing non - coherent transmission where PxxCH is transmitted without DMRS, pilot signals, or other signals for enabling channel estimation at the receiver, the transmitter can modulate source bits to a constellation suitable for non - coherent detection. For example, the transmitter can modulate the source bits to a hand - crafted constellation associated with one or more radio resources (e.g., defined across the REs associated with the scheduled PxxCH communication from the transmitter to the receiver). At the receiver, maximum - likelihood detection can be used to demodulate the transmitted bits (e.g., the modulated source bits transmitted over the wireless channel to the receiver) such that the detected bits decoded or otherwise determined at the receiver approximately reconstruct the source bits. Although non - coherent wireless communication using hand - crafted constellations and maximum - likelihood detection can improve demodulation and / or decoding performance in some use cases, hand - crafted constellations and maximum - likelihood detection metrics tend to be sensitive to different fading scenarios. For example, hand - crafted constellations and maximum - likelihood detection metrics can be robust in the presence of additive white Gaussian noise but not robust in the case of large delay spread, and so on.

[0072] Accordingly, some aspects described herein relate to joint transmit - receive (Tx - Rx) designs where artificial intelligence techniques are used to implement non - coherent wireless communication using one or more neural networks in an encoder (e.g., an auto - encoder) and a decoder. For example, as shown by reference numeral 510, a transmitter may provide source bits (e.g., an input bit sequence) to a transmit neural network that modulates the source bits onto radio resources (e.g., a group of REs in one or more scheduled PRBs associated with a scheduled PxxCH communication from the transmitter to the receiver). As further shown by reference numeral 520, a receiver may use a receive neural network to demodulate the transmitted bits (e.g., the modulated source bits transmitted over a wireless channel to the receiver) in order to decode detected bits that approximately reconstruct the source bits.

[0073] In some aspects, the transmit neural network for modulating source bits and the receive neural network for demodulating and / or decoding may be jointly trained (e.g., offline using CSI samples). In this way, a joint Tx - Rx design using the transmit neural network at the transmitter and the receive neural network at the receiver can provide data - driven robustness based on a channel model, since an auto - encoder may not need to know the underlying data distribution of the input or an explicit identification of the structure of the input. For example, neural - network - based encoders / decoders are sometimes applied to CSI feedback in large - scale multiple - input multiple - output (MIMO) systems. CSI feedback in MIMO frequency - division duplex (FDD) systems is typically associated with significant overhead and is related to sparse channels, which results in significant compression gains using neural - network - based encoders / decoders. Additionally, using simple neural networks to implement non - coherent wireless communication can provide comparable or reduced receiver complexity compared to maximum - likelihood detection techniques.

[0074] As indicated above, Figure 5 is provided as an example. Other examples may be different from the example described with respect to Figure 5 the example.

[0075] Figure 6 is a diagram illustrating example 600 associated with scheduling energy - auto - encoder - based non - coherent transmission in accordance with various aspects of the present disclosure. As Figure 6As shown in the example 600 includes a UE (e.g., UE 120), which may transmit one or more scheduled communications to another device in a wireless network (e.g., wireless network 100) and / or receive one or more scheduled communications from it. For example, the other device may be a base station (e.g., base station 110) communicating with the UE via a radio access link, the radio access link may include an uplink and a downlink, and the UE may be scheduled to transmit PUCCH and / or PUSCH to the base station via the radio access link and / or receive PDCCH and / or PDSCH from the base station. Additionally or alternatively, the other device may be another UE communicating with the UE via a wireless sidelink, and the UE may be scheduled to transmit PSCCH and / or PSSCH to the other UE via the wireless sidelink and / or receive PSCCH and / or PSSCH from the other UE.

[0076] In some aspects, as described herein, the UE and the other device may use an energy-based autoencoder suitable for non-coherent transmission to communicate (e.g., transmit and / or receive) scheduled communications (e.g., where the transmitted PxxCH does not include pilot signals, DMRS, or other suitable signals for enabling channel estimation at the receiver). For example, in some aspects, the transmitter may use a neural network to modulate a source bit sequence onto one or more REs in one or more scheduled PRBs associated with the scheduled communication using only energy (e.g., where the total transmit power is normalized over one or more RE groups), and a neural network may be used at the receiver to demodulate the transmitted bit sequence. In this way, modulating the source bit sequence onto the energy associated with the physical layer resources can be robust to fading, especially in non-coherent wireless communications where DMRS or other channel estimation signals are not available (e.g., because the receiver does not need to know the phase of the received signal, alternatively only needs to detect the energy in the physical layer resources). Additionally, using neural networks for transmission and reception can enable computationally efficient modulation schemes that are robust to different fading scenarios (e.g., high Doppler or high delay spread), and segmenting the long source bit sequence into multiple subsequences can significantly reduce the complexity at the receiver (e.g., because more complex neural networks and / or more complex maximum likelihood detection may be required to demodulate the long source bit sequence).

[0077] As shown by reference numeral 610, the UE may be configured as a transmitter or receiver for one or more scheduled communications. For example, as described above, the UE may be scheduled to transmit PUCCH or PUSCH to a base station, transmit PSCCH or PSSCH to another UE, receive PDCCH or PDSCH from a base station, and / or receive PSCCH or PSSCH from another UE. In some aspects, as described herein, the UE may be configured to transmit and / or receive the one or more scheduled communications using RE segmentation based on the energy level associated with the RE segmentation. For example, as shown in the figure, the transmitter may segment the source bit sequence into a plurality of subsequences, each subsequence associated with a corresponding RE segmentation, and each RE segmentation may include one or more REs within one or more scheduled PRBs associated with the scheduled communication. In some aspects, the REs within the RE segmentation may be contiguous or non-contiguous in the time domain and / or frequency domain, where contiguous REs may provide reduced encoding and decoding complexity, and non-contiguous REs may increase diversity (e.g., using interleaved control channel elements (CCEs) and / or RE group (REG) bundling to improve the reliability of the PDCCH). In some aspects, each subsequence and the corresponding RE segmentation may be associated with a neural network that modulates the associated subsequence onto the REs within the corresponding RE segmentation. Specifically, the output from each neural network may be the energy on the corresponding physical layer resource set (e.g., the REs within the RE segmentation), where the energy is normalized on the physical layer resource set (e.g., on the RE segmentation) based on the transmit power configuration associated with the transmitter.

[0078] For example, as shown in the figure, the source bit sequence "0110…1101…0010…0101…" may be segmented into four subsequences, including the subsequences "0110…", "1101…", "0010…", and "0101". At the transmitter, each subsequence is provided to a neural network that modulates the associated subsequence onto a set of contiguous or non-contiguous REs within the RE segmentation. In general, the source bit sequence may be associated with a scheduled communication (e.g., PUCCH, PUSCH, PDCCH, PDSCH, PSSCH, or PSSCH), and the RE segmentations associated with the respective subsequences (and the REs included within each RE segmentation) may be included within one or more scheduled PRBs associated with the scheduled communication. For example, Figure 6An example is illustrated in which source bit sequences are modulated to the REs in four RE segments (shown with different shadings), and these RE segments are within one or more scheduled PRBs associated with the scheduled communication. Accordingly, the four subsequences associated with the source bit sequences can each be associated with a corresponding neural network (e.g., NN#0 to NN#4), where the output from the neural network is the energy on the corresponding REs normalized over the RE segment. In this way, the receiver can detect the energy on the REs within each RE segment (e.g., using the receiver neural network as shown, or another suitable technique such as maximum likelihood detection) to demodulate the transmitted subsequence, and thereby decode the detected bit sequence approximating the source bit sequence.

[0079] Accordingly, as indicated by reference numeral 620, the UE can determine one or more segmentation methods and / or associated neural networks to be used for transmitting and / or receiving the scheduled communication. For example, the one or more segmentation methods can indicate techniques for segmenting one or more scheduled PRBs into multiple RE segments corresponding to multiple subsequences associated with the source bit sequence. Additionally or alternatively, the one or more segmentation methods can indicate techniques for segmenting one or more RE segments into REs that can be contiguous or non - contiguous in the time domain and / or frequency domain (e.g., to define how many REs are within the RE segment). Additionally or alternatively, the one or more segmentation methods can indicate the number of bits to be included in each subsequence and / or the technique for segmenting the source bit sequence into the multiple subsequences.

[0080] In some aspects, the base station can signal to the UE the segmentation method associated with segmenting the scheduled PRB into RE segments and / or the segmentation method associated with segmenting the source bit sequence into multiple subsequences. For example, the base station can be a device that uses non - coherent wireless communication to convey the control channel and / or data channel to the UE, or can be a device that schedules non - coherent sidelink communication between the UE and other devices. In either case, the base station can transmit and the UE can receive signaling indicating the segmentation method associated with the RE segments and / or the bit sequence, where the signaling can include one or more radio resource control (RRC) and / or downlink control information (DCI) messages. For example, in some aspects, the signaling can include one or more RRC messages pre - configuring a set containing N segmentation method options and one or more DCI messages selecting one of the N segmentation method options (e.g., when scheduling PDSCH, PUSCH, and / or PSSCH). Additionally or alternatively, one or more RRC messages can pre - configure the segmentation method for a specific PUCCH resource, PUCCH resource set, PDCCH search space, and / or PDCCH control resource set (CORESET), etc.

[0081] In some aspects, as described above, each RE segment can be associated with a neural network that modulates a subsequence associated with the source bit sequence to the REs in the corresponding RE segment. For example, as Figure 6 shown, the first subsequence (e.g., "0100…") is associated with the first neural network (e.g., NN#0), which modulates the first subsequence to the first RE segment, the second subsequence (e.g., "1101…") is associated with the second neural network (e.g., NN#2), which modulates the second subsequence to the second RE segment, and so on. Accordingly, in some aspects, the configuration of the neural networks that modulate the respective subsequences to different RE segments can depend on the segmentation method configured across the one or more scheduled PRBs.

[0082] For example, in some aspects, a common segmentation method can be configured across the scheduled PRBs, in which case each RE segment can have the same number of REs and / or the same number of OFDM symbols. Additionally, in the case where a common segmentation method is configured across the scheduled PRBs, each RE segment can be associated with the same number of bits (e.g., the source bit sequence is segmented into multiple subsequences, each subsequence having the same number of bits). In this case, when a common segmentation method is indicated or otherwise configured across the scheduled PRBs, each RE segment can be associated with the same transmission neural network, which can be signaled to the UE in one or more RRC and / or DCI messages along with the common segmentation method. In some aspects, the transmission neural network for modulating the subsequences to the RE segments can generally include one or more parameters (e.g., parameters for input neurons, hidden layers, output neurons, and / or weights, etc.) that are pre-configured and / or network-configured (or indicated), and the neural network for downlink reception (e.g., PDCCH and / or PDSCH reception) can be configured and / or indicated via one or more RRC messages, media access control (MAC) control elements (MAC-CE), and / or one or more DCI messages.

[0083] Alternatively, in some aspects, a non-uniform segmentation method may be configured across the scheduled PRBs. In such a case, the RE segmentation associated with different subsequences may include at least a first RE segmentation and a second RE segmentation having different numbers of REs and / or different numbers of OFDM symbols. Additionally or alternatively, in the case of configuring a uniform segmentation method across the scheduled PRBs, any two RE segmentations may be associated with different numbers of bits (e.g., the source bit sequence may be segmented into multiple subsequences having non-uniform numbers of bits). In such a case, where a non-uniform segmentation method is indicated or otherwise configured across the scheduled PRBs, different RE segmentations may be associated with different transmission neural networks, which may be signaled to the UE together with the non-uniform segmentation method in one or more RRC and / or DCI messages. For example, in some aspects, different neural networks may include convolutional neural networks having different numbers of kernels and / or different kernel coefficients. In some aspects, the transmission neural network for modulating a subsequence onto an RE segmentation may include one or more parameters that are pre-configured and / or network-configured (or indicated), and the neural network for downlink reception may be configured and / or indicated via one or more RRC messages, MAC-CEs, and / or one or more DCI messages, etc.

[0084] Accordingly, as further shown by reference numeral 630, the UE and the other device may perform non-coherent wireless communication for the scheduled PxxCH communication using an energy-based autoencoder configured in the manner described in more detail above. For example, in some aspects, a transmitter (e.g., the UE or the other device) may use one or more neural networks to modulate a source bit sequence onto corresponding RE segmentations within one or more scheduled PRBs associated with the scheduled PxxCH communication, where the output from the (one or more) neural networks is the energy on the corresponding physical layer resources (e.g., RE segmentations). In some aspects, at the receiver, one or more receiving neural networks may be used to demodulate the transmitted bit sequence at least partially based on the energy on the corresponding physical layer resources.

[0085] In addition, in a case where the scheduled PxxCH is the PUCCH that the UE transmits to the base station using an energy autoencoder, the PUCCH format may be defined at least in part based on a segmentation method associated with segmenting the scheduled PRB into RE segments, a segmentation method associated with segmenting a source bit sequence into a plurality of subsequences, and / or an associated neural network used to modulate the subsequences onto the RE segments. Additionally or alternatively, different PUCCH resources within a PUCCH resource set may be associated with the same segmentation method, different segmentation methods, the same neural network, and / or different neural networks. Further, in a case where the PUCCH carries hybrid automatic repeat request acknowledgement (HARQ-ACK) feedback for the PDSCH, one or more DCI messages scheduling the PDSCH may indicate the PUCCH resources for the HARQ-ACK feedback associated with the PDSCH. In this case, the DCI message scheduling the PDSCH may indicate the segmentation method and / or the associated transmission neural network for non-coherent transmission of the PUCCH.

[0086] Alternatively, in a case where the scheduled PxxCH is a PDCCH that the base station transmits to the UE using an energy autoencoder, the segmentation method associated with segmenting the scheduled PRB into RE segments and / or segmenting the source bits into a plurality of subsequences may be based on one or more REG bundles and / or one or more CCEs. Additionally, the PDCCH may be associated with an aggregation level, a search space, and / or a CORESET at least in part based on the configured segmentation method and / or the associated neural network used to modulate the subsequence onto the RE segments associated with the PDCCH (e.g., different aggregation levels, search spaces, and / or CORESETS may be configured or defined for different segmentation methods and / or neural networks). Additionally, in a case where the PDCCH is overbooked (e.g., where the blind detection or channel estimation limit is lower than the determined number of PDCCH decodings) and / or the UE is configured to operate in a power saving mode (e.g., discontinuous reception (DRX) mode and / or sleep mode, etc.), the UE may determine the priority associated with a particular PDCCH search space and / or CORESET at least in part based on the segmentation method and / or the associated neural network. For example, the search space and / or CORESET associated with different segmentation methods and / or neural networks may have different priorities, whereby the UE may determine whether to monitor or suppress monitoring of the search space and / or CORESET associated with the PDCCH based on the priority associated with the segmentation method and / or the associated neural network corresponding to the search space and / or CORESET. For example, in a case where the blind detection or channel estimation limit is lower than the determined number of PDCCH decodings, when the UE is operating in DRX mode, the search space or CORESET associated with a neural network having a large number of neurons may have a relatively low priority.

[0087] As indicated above, Figure 6 is provided as an example. Other examples may be different from the example Figure 6 described.

[0088] Figure 7 is a diagram illustrating an example process 700, such as may be performed by a UE, in accordance with various aspects of the present disclosure. Example process 700 is an example where a UE (e.g., UE 120) performs operations associated with scheduling non-coherent transmissions based on an energy autoencoder.

[0089] As Figure 7 shown, in some aspects, process 700 may include identifying a plurality of RE segments associated with a scheduled communication including a source bit sequence, where each of the plurality of RE segments includes one or more REs from one or more of the scheduled PRBs associated with the scheduled communication (block 710). For example, the UE (e.g., using the identification component 808, as Figure 8(depicted in) can identify a plurality of RE segments associated with a scheduled communication including a source bit sequence, where each of the plurality of RE segments includes one or more REs in one or more scheduled PRBs associated with the scheduled communication, as described above.

[0090] As Figure 7 further shown in, in some aspects, process 700 can include communicating with a device at least in part based on corresponding energy included on one or more REs in a plurality of RE segments associated with a scheduled communication, where each of the plurality of RE segments is associated with a subsequence of a source bit sequence segmented into a plurality of subsequences, and where communicating with the device includes using a neural network to transmit or detect a subsequence associated with an RE segment among the plurality of RE segments, the neural network modulating the subsequence associated with the RE segment onto one or more REs in the RE segment (block 720). For example, a UE (e.g., using Figure 8 the communication component 810 depicted in) can communicate with a device at least in part based on corresponding energy included on one or more REs in a plurality of RE segments associated with a scheduled communication, where each of the plurality of RE segments is associated with a subsequence of a source bit sequence segmented into a plurality of subsequences, and where communicating with the device includes using a neural network to transmit or detect a subsequence associated with an RE segment among the plurality of RE segments, the neural network modulating the subsequence associated with the RE segment onto one or more REs in the RE segment, as described above.

[0091] Process 700 can include additional aspects, such as any single aspect or any combination of aspects described below and / or in combination with one or more other processes described elsewhere in this document.

[0092] In a first aspect, the plurality of RE segments includes at least one RE segment in which one or more REs are contiguous.

[0093] In a second aspect, either alone or in combination with the first aspect, the plurality of RE segments includes at least one RE segment in which one or more REs are non - contiguous.

[0094] In a third aspect, either alone or in combination with one or more of the first and second aspects, the output from the neural network includes corresponding energy on one or more REs normalized over an RE segment.

[0095] In a fourth aspect, alone or in combination with one or more of the first to third aspects, process 700 includes receiving signaling indicating one or more of the following: a segmentation method associated with one or more REs in an RE segmentation, a segmentation method associated with one or more bits in a subsequence associated with the RE segmentation, or a neural network that modulates a subsequence associated with the RE segmentation onto one or more REs in the RE segmentation.

[0096] In a fifth aspect, alone or in combination with one or more of the first to fourth aspects, the signaling includes one or more RRC or DCI messages.

[0097] In a sixth aspect, alone or in combination with one or more of the first to fifth aspects, each RE segmentation has the same number of REs, symbols, and bits as each other RE segmentation.

[0098] In a seventh aspect, alone or in combination with one or more of the first to sixth aspects, the plurality of RE segmentations are each associated with the same neural network, and the same neural network modulates a subsequence associated with a corresponding RE segmentation onto one or more REs in the corresponding RE segmentation.

[0099] In an eighth aspect, alone or in combination with one or more of the first to seventh aspects, the plurality of RE segmentations include a first RE segmentation and a second RE segmentation, which include one or more of a different number of REs, a different number of symbols, or a different number of bits.

[0100] In a ninth aspect, alone or in combination with one or more of the first to eighth aspects, different RE segmentations are associated with different neural networks, and the different neural networks are used to modulate a subsequence associated with a corresponding RE segmentation onto one or more REs in the corresponding RE segmentation.

[0101] In a tenth aspect, alone or in combination with one or more of the first to ninth aspects, the different neural networks include different convolutional neural networks having different numbers of kernels or different kernel coefficients.

[0102] In an eleventh aspect, alone or in combination with one or more of the first to tenth aspects, the scheduled communication includes non-coherent control channel transmission or non-coherent data channel transmission.

[0103] In a twelfth aspect, either alone or in combination with one or more of the first to eleventh aspects, communicating with the device includes determining that the scheduled communication includes PUCCH, determining the PUCCH format at least in part based on one or more segmentation methods or transmission neural networks associated with modulating the plurality of subsequences onto one or more REs among the plurality of RE segments, and transmitting the PUCCH at least in part based on the PUCCH format.

[0104] In a thirteenth aspect, either alone or in combination with one or more of the first to twelfth aspects, transmitting the PUCCH includes determining a PUCCH resource set associated with the PUCCH, and using one or more segmentation methods or transmission neural networks for different PUCCH resources within the PUCCH resource set to modulate the plurality of subsequences onto one or more REs among the plurality of RE segments, where the one or more segmentation methods or transmission neural networks are configured by a configuration associated with the PUCCH resource.

[0105] In a fourteenth aspect, either alone or in combination with one or more of the first to thirteenth aspects, transmitting the PUCCH includes determining at least in part based on DCI one or more segmentation methods or transmission neural networks associated with modulating the plurality of subsequences, where the DCI indicates the PUCCH resource for HARQ-ACK feedback associated with the PDSCH scheduled by the DCI, and using one or more segmentation methods or transmission neural networks for the PUCCH resource indicated in the DCI to modulate the plurality of subsequences onto one or more REs among the plurality of RE segments.

[0106] In a fifteenth aspect, either alone or in combination with one or more of the first to fourteenth aspects, communicating with the device includes: determining that the scheduled communication includes PDCCH, determining at least in part based on one or more REG bundles or CCEs associated with the PDCCH one or more segmentation methods or transmission neural networks associated with modulating the plurality of subsequences onto one or more REs among the plurality of RE segments, and detecting the source bit sequence in the PDCCH at least in part based on the one or more segmentation methods or transmission neural networks.

[0107] In a sixteenth aspect, either alone or in combination with one or more of the first to fifteenth aspects, detecting the source bit sequence is at least in part based on one or more aggregation levels associated with the one or more segmentation methods or transmission neural networks.

[0108] In a seventeenth aspect, either alone or in combination with one or more of the first to sixteenth aspects, detecting the source bit sequence is at least in part based on one or more search spaces or CORESETs associated with the one or more segmentation methods or transmission neural networks.

[0109] In an eighteenth aspect, either alone or in combination with one or more of the first to seventeenth aspects, process 700 includes determining a priority associated with the one or more search spaces or CORESETs at least in part based on the one or more segmentation methods or transmission neural networks, and monitoring the PDCCH at least in part based on the priority associated with the one or more search spaces or CORESETs.

[0110] In a nineteenth aspect, either alone or in combination with one or more of the first to eighteenth aspects, process 700 includes determining a priority associated with the one or more search spaces or CORESETs at least in part based on the one or more segmentation methods or transmission neural networks, and suppressing the monitoring of the PDCCH at least in part based on the priority associated with the one or more search spaces or CORESETs.

[0111] Although Figure 7 example boxes of process 700 are shown, in some aspects, process 700 may include additional boxes, fewer boxes, different boxes, or boxes arranged differently compared to the boxes depicted in Figure 7 . Additionally or alternatively, two or more boxes of process 700 may be executed in parallel.

[0112] Figure 8 is a block diagram of an example device 800 for wireless communication. Device 800 may be a UE, or the UE may include device 800. In some aspects, device 800 includes a receiving component 802 and a transmitting component 804, 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 800 may use receiving component 802 and transmitting component 804 to communicate with another device 806 (such as a UE, a base station, or another wireless communication device). As further shown, device 800 may include one or more of an identification component 808, a communication component 810, a monitoring component 812, and so on.

[0113] In some aspects, device 800 may be configured to perform one or more operations described herein in connection with Figure 6 . Additionally or alternatively, device 800 may be configured to perform one or more processes described herein, such as Figure 7 process 700. In some aspects, device 800 and / or Figure 8 one or more components shown in Figure 2 may include one or more components of the UE described above in connection with Figure 8 one or more components shown in may be in the above in connection with Figure 2implemented within one or more of the described components. Additionally or alternatively, one or more of the components in the set of components may be implemented at least in part as software stored in a memory. For example, a component (or a part 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 a processor to perform the functions or operations of the component.

[0114] The receiving component 802 may receive a communication (such as a reference signal, control information, data communication, or a combination thereof) from the device 806. The receiving component 802 may provide the received communication to one or more other components of the device 800. In some aspects, the receiving component 802 may perform signal processing (such as filtering, amplification, demodulation, analog-to-digital conversion, demultiplexing, deinterleaving, demapping, equalization, interference cancellation, or decoding, etc.) on the received communication and may provide the processed signal to one or more other components of the device 806. In some aspects, the receiving component 802 may include one or more antennas, demodulators, MIMO detectors, receiving processors, controllers / processors, memories, or combinations thereof of the UE described above in connection with Figure 2 the UE.

[0115] The transmitting component 804 may transmit a communication (such as a reference signal, control information, data communication, or a combination thereof) to the device 806. In some aspects, one or more other components of the device 806 may generate a communication and may provide the generated communication to the transmitting component 804 for transmission to the device 806. In some aspects, the transmitting component 804 may perform signal processing (such as filtering, amplification, modulation, digital-to-analog conversion, multiplexing, interleaving, mapping, coding, etc.) on the generated communication and may transmit the processed signal to the device 806. In some aspects, the transmitting component 804 may include one or more antennas, modulators, transmit MIMO processors, transmit processors, controllers / processors, memories, or combinations thereof of the UE described above in connection with Figure 2 the UE. In some aspects, the transmitting component 804 may be co-located with the receiving component 802 in a transceiver.

[0116] The identification component 808 may identify a plurality of RE segments associated with a scheduled communication including a source bit sequence, where each of the plurality of RE segments includes one or more REs in one or more scheduled PRBs associated with the scheduled communication. The communication component 810 may or may cause the receiving component 802 and / or the transmitting component 804 to communicate with a device at least partially based on corresponding energies included in one or more REs in the plurality of RE segments associated with the scheduled communication, where each of the plurality of RE segments is associated with a subsequence of the source bit sequence segmented into a plurality of subsequences, and where communicating with the device includes using a neural network to transmit or detect a subsequence associated with an RE segment in the plurality of RE segments, and the neural network modulates the subsequence associated with the RE segment to one or more REs in the RE segment.

[0117] The receiving component 802 may receive signaling indicating one or more of the following: a segmentation method associated with one or more REs in an RE segment, a segmentation method associated with one or more bits in a subsequence associated with the RE segment, or a neural network that modulates a subsequence associated with the RE segment to one or more REs in the RE segment.

[0118] The monitoring component 812 may determine a priority associated with one or more search spaces or CORESETs at least partially based on one or more segmentation methods or a transmission neural network, and the monitoring component 812 may monitor the PDCCH at least partially based on the priority associated with the one or more search spaces or CORESETs.

[0119] The monitoring component 812 may determine a priority associated with the one or more search spaces or CORESETs at least partially based on the one or more segmentation methods or a transmission neural network, and the monitoring component 812 may inhibit monitoring the PDCCH at least partially based on the priority associated with the one or more search spaces or CORESETs.

[0120] Figure 8 The number and arrangement of the components shown are provided as an example. In practice, there may be additional components, fewer components, different components, or differently arranged components compared to those shown. Additionally, Figure 8 In addition, Figure 8 two or more of the components shown may be implemented within a single component, or Figure 8 a single component shown may be implemented as multiple distributed components. Additionally or alternatively, Figure 8 a set of components (e.g., one or more components) shown may perform one or more functions described as being performed by Figure 8 another set of components shown.

[0121] The following provides an overview of aspects of the present disclosure:

[0122] Aspect 1: A wireless communication method performed by a UE, comprising: identifying a plurality of RE segments associated with a scheduled communication including a source bit sequence, wherein each of the plurality of RE segments includes one or more REs in one or more scheduled PRBs associated with the scheduled communication; and communicating with a device at least in part based on respective energies on one or more REs included in the plurality of RE segments associated with the scheduled communication, wherein each of the plurality of RE segments is associated with a subsequence of the source bit sequence segmented into a plurality of subsequences, and wherein communicating with the device includes using a neural network to transmit or detect a subsequence associated with an RE segment among the plurality of RE segments, the neural network modulating the subsequence associated with the RE segment onto one or more REs in the RE segment.

[0123] Aspect 2: The method of aspect 1, wherein the plurality of RE segments includes at least one RE segment in which one or more REs are contiguous.

[0124] Aspect 3: The method of aspect 1, wherein the plurality of RE segments includes at least one RE segment in which one or more REs are non - contiguous.

[0125] Aspect 4: The method of any one of aspects 1 - 3, wherein the output from the neural network includes respective energies on one or more REs normalized on the RE segment.

[0126] Aspect 5: The method of any one of aspects 1 - 4, further comprising: receiving signaling indicating one or more of the following: a segmentation method associated with one or more REs in an RE segment, a segmentation method associated with one or more bits in the subsequence associated with the RE segment, or a neural network that modulates the subsequence associated with the RE segment onto one or more REs in the RE segment.

[0127] Aspect 6: The method of aspect 5, wherein the signaling includes one or more RRC or DCI messages.

[0128] Aspect 7: The method of any one of aspects 1 - 6, wherein each RE segment has the same number of REs, code elements, and bits as each other RE segment.

[0129] Aspect 8: The method of any one of aspects 1 - 7, wherein the plurality of RE segments are each associated with the same neural network, the same neural network modulating the subsequence associated with the respective RE segment onto one or more REs in the respective RE segment.

[0130] Aspect 9: The method as in any one of Aspects 1-6, wherein the plurality of RE segments includes a first RE segment and a second RE segment, which includes one or more of a different number of REs, a different number of symbols, or a different number of bits.

[0131] Aspect 10: The method as in any one of Aspects 1-9, wherein different RE segments are associated with different neural networks, and the different neural networks are used to modulate a subsequence associated with a corresponding RE segment to one or more REs in the corresponding RE segment.

[0132] Aspect 11: The method as in Aspect 10, wherein the different neural networks include different convolutional neural networks with different numbers of kernels or different kernel coefficients.

[0133] Aspect 12: The method as in any one of Aspects 1-11, wherein the scheduled communication includes non-coherent control channel transmission or non-coherent data channel transmission.

[0134] Aspect 13: The method as in any one of Aspects 1-12, wherein communicating with the device includes: determining that the scheduled communication includes PUCCH; determining the PUCCH format at least in part based on one or more segmentation methods or transmission neural networks associated with modulating the plurality of subsequences to one or more REs in the plurality of RE segments; and transmitting the PUCCH at least in part based on the PUCCH format.

[0135] Aspect 14: The method as in Aspect 13, wherein transmitting the PUCCH includes: determining a PUCCH resource set associated with the PUCCH; and for different PUCCH resources within the PUCCH resource set, using the one or more segmentation methods or transmission neural networks to modulate the plurality of subsequences to one or more REs in the plurality of RE segments, wherein the one or more segmentation methods or transmission neural networks are configured by a configuration associated with the PUCCH resource.

[0136] Aspect 15: The method as in any one of Aspects 13-14, wherein transmitting the PUCCH includes: determining at least in part based on DCI one or more segmentation methods or transmission neural networks associated with modulating the plurality of subsequences, the DCI indicating the PUCCH resources for HARQ-ACK feedback associated with a PDSCH scheduled by the DCI; and using the one or more segmentation methods or transmission neural networks for the PUCCH resources indicated in the DCI to modulate the plurality of subsequences to one or more REs in the plurality of RE segments.

[0137] Aspect 16: The method of any one of aspects 1 - 15, wherein communicating with the device includes: determining that the scheduled communication includes a PDCCH; determining, at least in part, one or more segmentation methods or transmission neural networks associated with one or more REs in which the plurality of subsequences are modulated into the plurality of RE segments based on one or more REG bundles or CCEs associated with the PDCCH; and detecting a source bit sequence in the PDCCH at least in part based on the one or more segmentation methods or transmission neural networks.

[0138] Aspect 17: The method of aspect 16, wherein the source bit sequence is detected at least in part based on one or more aggregation levels associated with the one or more segmentation methods or transmission neural networks.

[0139] Aspect 18: The method of any one of aspects 16 - 17, wherein the source bit sequence is detected at least in part based on one or more search spaces or CORESETs associated with the one or more segmentation methods or transmission neural networks.

[0140] Aspect 19: The method of any one of aspects 1 - 18, further comprising: determining, at least in part, a priority associated with the one or more search spaces or CORESETs based on the one or more segmentation methods or transmission neural networks; and monitoring the PDCCH at least in part based on the priority associated with the one or more search spaces or CORESETs.

[0141] Aspect 20: The method of any one of aspects 1 - 18, further comprising: determining, at least in part, a priority associated with the one or more search spaces or CORESETs based on the one or more segmentation methods or transmission neural networks; and suppressing the monitoring of the PDCCH at least in part based on the priority associated with the one or more search spaces or CORESETs.

[0142] Aspect 21: 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 the method of any one of aspects 1 to 20.

[0143] Aspect 22: A device for wireless communication, comprising: a memory and one or more processors coupled to the memory, the memory and the one or more processors being configured to perform the method of any one of aspects 1 to 20.

[0144] Aspect 23: A device for wireless communication, comprising at least one means for performing the method of any one of aspects 1 to 20.

[0145] Aspect 24: A non-transitory computer-readable medium storing code for wireless communication, the code including instructions executable by a processor to perform the method of any one of Aspects 1 to 20.

[0146] Aspect 25: A non-transitory computer-readable medium storing an instruction set for wireless communication, the instruction set including one or more instructions that, when executed by one or more processors of a device, cause the device to perform the method of any one of Aspects 1 to 20.

[0147] The foregoing disclosure provides illustration and description, but is not intended to be exhaustive or to limit the aspects to the precise forms disclosed. Modifications and variations can be made in light of the above disclosure or can be obtained by practicing the aspects.

[0148] As used herein, the term "component" is intended to be broadly interpreted as a combination of hardware and / or hardware and software. "Software" should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, and / or functions, etc., regardless of whether it is referred to in terms of software, firmware, middleware, microcode, hardware description language, or other terms. As used herein, a processor is implemented with 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 different forms of hardware and / or a combination of hardware and software. The actual specific control hardware or software code for implementing these systems and / or methods does not limit the aspects. Thus, the operation and behavior of these systems and / or methods are described herein without reference to specific software code - understanding that software and hardware can be designed to implement these systems and / or methods at least in part based on the description herein.

[0149] As used herein, depending on the context, meeting a 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, and so on.

[0150] Although specific feature combinations are recited in the claims and / or disclosed in the specification, these combinations are not intended to limit the disclosure of the various aspects. In fact, many of these features may be combined in ways not specifically recited in the claims and / or not disclosed in the specification. Although each of the dependent claims listed below may directly depend on only one claim, the disclosure of the various aspects includes each dependent claim in combination with every other claim in this group of claims. As used herein, a phrase that recites "at least one" of a list of items means 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).

[0151] Elements, acts, or instructions used herein should not be construed as critical or essential unless expressly described as such. Also, as used herein, the articles "a" and "an" 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 referred to in conjunction with the article "the" and may be used interchangeably with "one or more." Further, as used herein, the terms "set" and "group" are intended to include one or more items (e.g., related items, unrelated items, or a combination of related and unrelated items) and may be used interchangeably with "one or more." Where only one item is intended, the phrase "only one" or similar language is used. Also, as used herein, the terms "having," "containing," "including," etc. are intended to be open - ended terms. Additionally, the phrase "based on" is intended to mean "at least partially based on" unless otherwise expressly stated. Also, as used herein, the term "or" when used in a series is intended to be inclusive and may be used interchangeably with "and / or" unless otherwise expressly stated (e.g., when used in conjunction with "any of" or "only one of").

Claims

1. A method for wireless communication performed by a user equipment (UE), comprising: identifying a plurality of resource element (RE) segments associated with a scheduled communication including a source bit sequence, wherein each of the plurality of RE segments includes one or more REs in one or more scheduled physical resource blocks (PRBs) associated with the scheduled communication; and communicating with a device at least in part based on corresponding energy on one or more REs included in one or more of the plurality of RE segments associated with the scheduled communication, wherein each of the plurality of RE segments is associated with a subsequence of the source bit sequence segmented into a plurality of subsequences, and wherein communicating with the device includes using a neural network to transmit or detect a subsequence associated with an RE segment among the plurality of RE segments, the neural network modulating the subsequence associated with the RE segment onto one or more REs in the RE segment.

2. The method according to claim 1, wherein the plurality of RE segments includes at least one RE segment in which the one or more REs are contiguous.

3. The method according to claim 1, wherein the plurality of RE segments includes at least one RE segment in which the one or more REs are non - contiguous.

4. The method according to claim 3, wherein an output from the neural network includes corresponding energy on the one or more REs normalized on the RE segment.

5. The method according to claim 1, further comprising: receiving signaling indicating one or more of: a segmentation method associated with one or more REs in the RE segment, a segmentation method associated with one or more bits in the subsequence associated with the RE segment, or the neural network for modulating the subsequence associated with the RE segment onto one or more REs in the RE segment.

6. The method according to claim 5, wherein the signaling includes one or more radio resource control or downlink control information messages.

7. The method according to claim 1, wherein each RE segment has the same number of REs, symbols, and bits as each other RE segment.

8. The method according to claim 7, wherein each of the plurality of RE segments is associated with the same neural network, the same neural network modulating the subsequence associated with the corresponding RE segment onto one or more REs in the corresponding RE segment.

9. The method according to claim 1, wherein the plurality of RE segments includes a first RE segment and a second RE segment, the first RE segment and the second RE segment including one or more of a different number of REs, a different number of symbols, or a different number of bits.

10. The method according to claim 9, wherein different RE segments are associated with different neural networks, the different neural networks being used to modulate the subsequence associated with the corresponding RE segment onto one or more REs in the corresponding RE segment.

11. The method according to claim 10, wherein the different neural networks include different convolutional neural networks having different numbers of kernels or different kernel coefficients.

12. The method according to claim 1, wherein the scheduled communication includes non-coherent control channel transmission or non-coherent data channel transmission.

13. The method according to claim 1, wherein communicating with the device comprises: determining that the scheduled communication includes a physical uplink control channel (PUCCH); determining the PUCCH format at least in part based on one or more segmentation methods or transmission neural networks associated with modulating the plurality of subsequences into one or more resource elements (REs) of the plurality of RE segments; and transmitting the PUCCH at least in part based on the PUCCH format.

14. The method according to claim 13, wherein transmitting the PUCCH comprises: determining a PUCCH resource set associated with the PUCCH; and for different PUCCH resources within the PUCCH resource set, using the one or more segmentation methods or transmission neural networks to modulate the plurality of subsequences into one or more REs of the plurality of RE segments, wherein the one or more segmentation methods or transmission neural networks are configured by a configuration associated with the PUCCH resource.

15. The method according to claim 13, wherein transmitting the PUCCH comprises: determining at least in part based on downlink control information (DCI) the one or more segmentation methods or transmission neural networks associated with modulating the plurality of subsequences, the DCI indicating a PUCCH resource for hybrid automatic repeat request acknowledgement (HARQ-ACK) feedback associated with a physical downlink shared channel (PDSCH) scheduled by the DCI; and for the PUCCH resource indicated in the DCI, using the one or more segmentation methods or transmission neural networks to modulate the plurality of subsequences into one or more REs of the plurality of RE segments.

16. The method according to claim 1, wherein communicating with the device comprises: determining that the scheduled communication includes a physical downlink control channel (PDCCH); determining at least in part based on one or more resource element groups (REGs) or control channel elements (CCEs) associated with the PDCCH the one or more segmentation methods or transmission neural networks associated with modulating the plurality of subsequences into one or more REs of the plurality of RE segments; and detecting the source bit sequence in the PDCCH at least in part based on the one or more segmentation methods or transmission neural networks.

17. The method according to claim 16, wherein the source bit sequence is detected at least in part based on one or more aggregation levels associated with the one or more segmentation methods or transmission neural networks.

18. The method according to claim 16, wherein the source bit sequence is detected based at least in part on one or more search spaces or control resource sets (CORESETs) associated with the one or more segmentation methods or transmission neural networks.

19. The method according to claim 18, further comprising: determining a priority associated with the one or more search spaces or CORESETs based at least in part on the one or more segmentation methods or transmission neural networks; and monitoring the PDCCH based at least in part on the priority associated with the one or more search spaces or CORESETs.

20. The method according to claim 18, further comprising: determining a priority associated with the one or more search spaces or CORESETs based at least in part on the one or more segmentation methods or transmission neural networks; and suppressing the monitoring of the PDCCH based at least in part on the priority associated with the one or more search spaces or CORESETs.

21. A user equipment (UE) for wireless communication, comprising: a memory; and one or more processors operatively coupled to the memory, the memory and the one or more processors being configured to: identify a plurality of resource element (RE) segments associated with a scheduled communication including a source bit sequence, wherein each of the plurality of RE segments includes one or more REs in one or more scheduled physical resource blocks (PRBs) associated with the scheduled communication; and communicate with a device based at least in part on respective energies included on one or more REs included in the plurality of RE segments associated with the scheduled communication, wherein each of the plurality of RE segments is associated with a subsequence of the source bit sequence segmented into a plurality of subsequences, and wherein communicating with the device includes using a neural network to transmit or detect a subsequence associated with an RE segment among the plurality of RE segments, the neural network modulating the subsequence associated with the RE segment onto one or more REs in the RE segment.

22. The UE according to claim 21, wherein the plurality of RE segments includes at least one RE segment in which one or more of the REs are contiguous.

23. The UE according to claim 21, wherein the plurality of RE segments includes at least one RE segment in which one or more of the REs are non - contiguous.

24. The UE according to claim 23, wherein the output from the neural network includes respective energies on one or more REs normalized on the RE segment.

25. The UE according to claim 21, wherein the one or more processors are further configured to: receive signaling indicating one or more of: a segmentation method associated with one or more REs in the RE segment, a segmentation method associated with one or more bits in the subsequence associated with the RE segment, or the neural network that modulates the subsequence associated with the RE segment onto one or more REs in the RE segment.

26. The UE according to claim 25, wherein the signaling comprises one or more radio resource control or downlink control information messages.

27. The UE according to claim 21, wherein each RE segment has the same number of REs, symbols, and bits as each other RE segment.

28. The UE according to claim 27, wherein the plurality of RE segments are each associated with the same neural network, and the same neural network modulates a subsequence associated with the corresponding RE segment onto one or more REs in the corresponding RE segment.

29. The UE according to claim 21, wherein the plurality of RE segments comprises a first RE segment and a second RE segment, and the first RE segment and the second RE segment comprise one or more of a different number of REs, a different number of symbols, or a different number of bits.

30. The UE according to claim 29, wherein different RE segments are associated with different neural networks, and the different neural networks are used to modulate a subsequence associated with the corresponding RE segment onto one or more REs in the corresponding RE segment.

31. The UE according to claim 30, wherein the different neural networks comprise different convolutional neural networks having different numbers of kernels or different kernel coefficients.

32. The UE according to claim 21, wherein the scheduled communication comprises non-coherent control channel transmission or non-coherent data channel transmission.

33. The UE according to claim 21, wherein when communicating with the device, the one or more processors are configured to: determine that the scheduled communication comprises a physical uplink control channel (PUCCH); determine the PUCCH format based at least in part on one or more segmentation methods or transmission neural networks associated with modulating the plurality of subsequences onto one or more REs in the plurality of RE segments; and transmit the PUCCH based at least in part on the PUCCH format.

34. The UE according to claim 33, wherein when transmitting the PUCCH, the one or more processors are configured to: determine a PUCCH resource set associated with the PUCCH; and for different PUCCH resources within the PUCCH resource set, use the one or more segmentation methods or transmission neural networks to modulate the plurality of subsequences onto one or more REs in the plurality of RE segments, wherein the one or more segmentation methods or transmission neural networks are configured by a configuration associated with the PUCCH resource.

35. The UE according to claim 33, wherein when transmitting the PUCCH, the one or more processors are configured to: determine the one or more segmentation methods or transmission neural networks associated with modulating the plurality of subsequences based at least in part on downlink control information (DCI), the DCI indicating a PUCCH resource for hybrid automatic repeat request acknowledgement (HARQ-ACK) feedback associated with a physical downlink shared channel (PDSCH) scheduled by the DCI; For the PUCCH resources indicated in the DCI, use the one or more segmentation methods or transmission neural networks to modulate the plurality of subsequences to one or more REs among the plurality of RE segments.

36. The UE according to claim 21, wherein when communicating with the device, the one or more processors are configured to: Determine that the scheduled communication includes a physical downlink control channel (PDCCH); Determine, at least in part, one or more segmentation methods or transmission neural networks associated with modulating the plurality of subsequences to one or more REs among the plurality of RE segments based at least in part on one or more resource element groups (REGs) bundling or control channel elements (CCEs) associated with the PDCCH; and Detect the source bit sequence in the PDCCH based at least in part on the one or more segmentation methods or transmission neural networks.

37. The UE according to claim 36, wherein the source bit sequence is detected based at least in part on one or more aggregation levels associated with the one or more segmentation methods or transmission neural networks.

38. The UE according to claim 36, wherein the source bit sequence is detected based at least in part on one or more search spaces or control resource sets (CORESETs) associated with the one or more segmentation methods or transmission neural networks.

39. The UE according to claim 38, wherein the one or more processors are further configured to: Determine, at least in part, a priority associated with the one or more search spaces or CORESETs based at least in part on the one or more segmentation methods or transmission neural networks; and Monitor the PDCCH based at least in part on the priority associated with the one or more search spaces or CORESETs.

40. The UE according to claim 38, wherein the one or more processors are further configured to: Determine, at least in part, a priority associated with the one or more search spaces or CORESETs based at least in part on the one or more segmentation methods or transmission neural networks; and Suppress monitoring the PDCCH based at least in part on the priority associated with the one or more search spaces or CORESETs.

41. A non-transitory 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 user equipment (UE), cause the UE to perform the following operations: Identify a plurality of resource element (RE) segments associated with a scheduled communication including a source bit sequence, wherein each of the plurality of RE segments includes one or more REs among one or more scheduled physical resource blocks (PRBs) associated with the scheduled communication; and Communicate with a device based at least in part on corresponding energy included in one or more resource elements (REs) among the plurality of RE segments associated with the scheduled communication, wherein each of the plurality of RE segments is associated with a subsequence of a source bit sequence segmented into a plurality of subsequences, and wherein communicating with the device includes using a neural network to transmit or detect a subsequence associated with an RE segment among the plurality of RE segments, the neural network modulating the subsequence associated with the RE segment onto one or more REs in the RE segment.

42. An apparatus for wireless communication, comprising: means for identifying a plurality of resource element (RE) segments associated with a scheduled communication including a source bit sequence, wherein each of the plurality of RE segments includes one or more REs among one or more scheduled physical resource blocks (PRBs) associated with the scheduled communication; and means for communicating with a device based at least in part on corresponding energy included in one or more REs among the plurality of RE segments associated with the scheduled communication, wherein each of the plurality of RE segments is associated with a subsequence of a source bit sequence segmented into a plurality of subsequences, and wherein the means for communicating with the device includes means for using a neural network to transmit or detect a subsequence associated with an RE segment among the plurality of RE segments, the neural network modulating the subsequence associated with the RE segment onto one or more REs in the RE segment.

Images