Partial subband reporting of received signal and channel estimation accuracy based on low density channel state information

Abstract

The device may receive a channel state information (CSI) reference signal from a base station on at least one of a first set of frequency units or a first set of antenna ports. The first set of frequency units or the first set of antenna ports may include less than all available frequency units or less than all available antenna ports. The device may generate the CSI based on the CSI reference signal and transmit information associated with the CSI on a second set of frequency units or a second set of antenna ports for use in reconstructing the CSI on a third set of frequency units or a third set of antenna ports. The second set of frequency units or the second set of antenna ports may include less than all available frequency units or less than all available antenna ports.

Description

Technical Field

[0001] The present disclosure generally relates to a new method for reporting channel state information for a partial set of channel resources, such that a complete channel state associated with a complete set of channel resources can be determined based on the channel state information for the partial set of channel resources, thereby reducing the overhead necessary to report the state of the channel. Background Art

[0002] Wireless communication systems are deployed to provide various telecommunication and data services including telephony, video, data, messaging, and broadcasting. Broadband wireless communication systems have evolved through several generations, including first-generation analog wireless telephone service (1G), second-generation (2G) digital wireless telephone service (including transitional 2.5G networks), third-generation (3G) high-speed data wireless devices with Internet capabilities, and fourth-generation (4G) services (e.g., Long Term Evolution (LTE), WiMax). Examples of wireless communication systems 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, Global System for Mobile Communications (GSM) systems, etc. Other wireless communication technologies include 802.11 Wi-Fi, Bluetooth, etc.

[0003] The fifth-generation (5G) mobile standard requires higher data transfer speeds, a greater number of connections, better coverage, and other improvements. According to the Next Generation Mobile Networks Alliance, the 5G standard (also known as "New Radio" or "NR") is designed to provide data rates of tens of megabits per second to each of tens of thousands of users, and data rates of 1 gigabit per second to tens of employees in an office floor. To support large-scale sensor deployments, hundreds of thousands of simultaneous connections should be supported. Algorithms based on artificial intelligence (AI) and ML can be incorporated into 5G, 6G, and future standards to improve telecommunication and data services. Summary of the Invention

[0004] The following presents a simplified summary of one or more aspects related to the present disclosure. Accordingly, the following summary should not be considered an exhaustive overview of all contemplated aspects, nor should it be considered to identify key or critical elements of all contemplated aspects or to delineate the scope associated with any particular aspect. Accordingly, the following summary presents certain concepts in a simplified form prior to the detailed description that follows related to one or more aspects of the mechanisms disclosed herein.

[0005] The present disclosure describes systems and techniques for generating channel state information for at least one of a set of frequency units or a set of antenna ports based on channel state information feedback on at least one of a partial set of frequency units or a partial set of antenna ports. Performing channel estimation when using legacy functionality can become a bottleneck in channel state feedback performance, such as in scenarios where a large number (e.g., thousands) of antennas and transmit units are equipped at a base station for communicating with one or more user equipments (UEs). For example, a conventional channel state information (CSI) reference signal (CSI-RS) occupies one resource element (RE) per resource block (RB) per antenna port, which results in a large overhead. CSI-RS is a reference signal for channel measurement and generating CSI feedback.

[0006] The present disclosure describes systems and techniques for using fewer than all available resources and / or antenna ports for transmitting CSI. These systems and techniques can use low-density CSI-RS for generating a partial CSI report that facilitates full CSI generation at a network entity (e.g., a base station). For example, a UE can receive CSI reference signals (CSI-RS) on a first set of frequency units (e.g., RBs or subbands) and / or a first set of antenna ports. The UE can utilize a machine learning-based encoder trained to generate a representation of the CSI (e.g., a latent representation of the CSI), which can be included in a CSI report of a channel state feedback (CSF). The UE can generate CSI on a second set of frequency units and / or a second set of antenna ports, which can include fewer than all available frequency units and antenna ports. A base station receiving the CSI feedback (e.g., the latent representation of the CSI) can reconstruct the CSI (e.g., using a machine learning-based decoder) on a third set of frequency units and / or a third set of antenna ports (e.g., the full set of frequency units and antenna ports). For example, the third set is a superset of the second set. Such an approach enables generating and transmitting CSI feedback on a reduced set of frequency units and / or antenna ports while allowing extrapolation of the CSI for the full set of frequency units and antenna ports.

[0007] In some aspects, the techniques described herein relate to a method for wireless communication at a user equipment (UE), the method comprising: receiving, at the UE, a channel state information (CSI) reference signal from a base station on at least one of a first set of frequency units or a first set of antenna ports, wherein at least one of the first set of frequency units or the first set of antenna ports comprises less than all available frequency units or less than all available antenna ports; generating CSI based on the CSI reference signal; and transmitting, from the UE to the base station, information associated with the CSI on at least one of a second set of frequency units or a second set of antenna ports for use in reconstructing the CSI on at least one of a third set of frequency units or a third set of antenna ports, wherein at least one of the second set of frequency units or the second set of antenna ports comprises less than all available frequency units or less than all available antenna ports.

[0008] In some aspects, the techniques described herein relate to an apparatus (e.g., such as a UE) for wireless communication, the apparatus comprising: at least one memory; and at least one processor coupled to the at least one memory and configured to: receive, at the apparatus, a channel state information (CSI) reference signal from a base station on at least one of a first set of frequency units or a first set of antenna ports, wherein at least one of the first set of frequency units or the first set of antenna ports comprises less than all available frequency units or less than all available antenna ports; generate CSI based on the CSI reference signal; and transmit, from the apparatus to the base station, information associated with the CSI on at least one of a second set of frequency units or a second set of antenna ports for use in reconstructing the CSI on at least one of a third set of frequency units or a third set of antenna ports, wherein at least one of the second set of frequency units or the second set of antenna ports comprises less than all available frequency units or less than all available antenna ports.

[0009] In some aspects, the techniques described herein relate to a non-transitory computer-readable storage medium including instructions stored thereon that, when executed by at least one processor, cause the at least one processor to: receive a channel state information (CSI) reference signal from a base station on at least one of a first set of frequency units or a first set of antenna ports, wherein at least one of the first set of frequency units or the first set of antenna ports includes less than all available frequency units or less than all available antenna ports; generate CSI based on the CSI reference signal; and transmit information associated with the CSI to the base station on at least one of a second set of frequency units or a second set of antenna ports for use in reconstructing the CSI on at least one of a third set of frequency units or a third set of antenna ports, wherein at least one of the second set of frequency units or the second set of antenna ports includes less than all available frequency units or less than all available antenna ports.

[0010] In some aspects, the techniques described herein relate to an apparatus for wireless communication, the apparatus including: means for receiving a channel state information (CSI) reference signal from a base station on at least one of a first set of frequency units or a first set of antenna ports, wherein at least one of the first set of frequency units or the first set of antenna ports includes less than all available frequency units or less than all available antenna ports; means for generating CSI based on the CSI reference signal; and means for transmitting information associated with the CSI to the base station on at least one of a second set of frequency units or a second set of antenna ports for use in reconstructing the CSI on at least one of a third set of frequency units or a third set of antenna ports, wherein at least one of the second set of frequency units or the second set of antenna ports includes less than all available frequency units or less than all available antenna ports.

[0011] In some aspects, the techniques described herein relate to a method for wireless communication at a base station, the method comprising: transmitting a channel state information (CSI) reference signal to a user equipment (UE) on at least one of a first set of frequency units or a first set of antenna ports, wherein at least one of the first set of frequency units or the first set of antenna ports comprises less than all available frequency units or less than all available antenna ports; receiving information associated with the CSI from the UE on at least one of a second set of frequency units or a second set of antenna ports, wherein at least one of the second set of frequency units or the second set of antenna ports comprises less than all available frequency units or less than all available antenna ports; and generating a reconstructed CSI for at least one of a third set of frequency units or a third set of antenna ports based on the information associated with the CSI.

[0012] In some aspects, the techniques described herein relate to an apparatus for wireless communication (e.g., such as a base station), the apparatus comprising: at least one memory; and at least one processor coupled to the at least one memory and configured to: transmit a channel state information (CSI) reference signal to a user equipment (UE) on at least one of a first set of frequency units or a first set of antenna ports, wherein at least one of the first set of frequency units or the first set of antenna ports comprises less than all available frequency units or less than all available antenna ports; receive information associated with the CSI from the UE on at least one of a second set of frequency units or a second set of antenna ports, wherein at least one of the second set of frequency units or the second set of antenna ports comprises less than all available frequency units or less than all available antenna ports; and generate a reconstructed CSI for at least one of a third set of frequency units or a third set of antenna ports based on the information associated with the CSI.

[0013] In some aspects, the techniques described herein relate to a non-transitory computer-readable storage medium comprising instructions stored thereon that, when executed by at least one processor, cause the at least one processor to: transmit a channel state information (CSI) reference signal to a user equipment (UE) on at least one of a first set of frequency units or a first set of antenna ports, wherein at least one of the first set of frequency units or the first set of antenna ports comprises less than all available frequency units or less than all available antenna ports; receive information associated with the CSI from the UE on at least one of a second set of frequency units or a second set of antenna ports, wherein at least one of the second set of frequency units or the second set of antenna ports comprises less than all available frequency units or less than all available antenna ports; and generate a reconstructed CSI for at least one of a third set of frequency units or a third set of antenna ports based on the information associated with the CSI.

[0014] In some aspects, the techniques described herein relate to a device for wireless communication, the device comprising: means for transmitting a channel state information (CSI) reference signal to a user equipment (UE) on at least one of a first set of frequency units or a first set of antenna ports, wherein at least one of the first set of frequency units or the first set of antenna ports comprises less than all available frequency units or less than all available antenna ports; means for receiving information associated with the CSI from the UE on at least one of a second set of frequency units or a second set of antenna ports, wherein at least one of the second set of frequency units or the second set of antenna ports comprises less than all available frequency units or less than all available antenna ports; and means for generating a reconstructed CSI for at least one of a third set of frequency units or a third set of antenna ports based on the information associated with the CSI.

[0015] Based on the drawings and the detailed description, other objects and advantages associated with the aspects disclosed herein will be apparent to those of ordinary skill in the art. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The following examples of specific implementations are described in detail with reference to the following drawings:

[0017] Figure 1 is a block diagram illustrating an example of a wireless communication network according to some examples;

[0018] Figure 2is a diagram illustrating the design of a base station and a user equipment (UE) device according to some examples, the design enabling the sending and processing of signals exchanged between the UE and the base station;

[0019] Figure 3 is a diagram illustrating an example of a decomposed base station according to some examples;

[0020] Figure 4 is a block diagram illustrating components of a user equipment according to some examples;

[0021] Figure 5 illustrates an example architecture of a neural network that can be used according to some aspects of the present disclosure;

[0022] Figure 6 is a block diagram illustrating an ML engine according to aspects of the present disclosure;

[0023] Figure 7 illustrates a block diagram according to aspects of the present disclosure showing an encoder encoding an input to generate a latent message that is sent to a decoder at a 3rd Generation Partnership Project (3GPP) gNodeB (gNB), the decoder generating an output based on the latent message;

[0024] Figure 8 illustrates the low - density use of available resource blocks and antenna ports and an example code on the resource blocks according to aspects of the present disclosure;

[0025] Figure 9 illustrates performing channel estimation using separate functions according to aspects of the present disclosure;

[0026] Figure 10 illustrates a process of generating channel state information from channel state information reference signals according to aspects of the present disclosure;

[0027] Figure 11 illustrates an alternative method for determining frequency units and antenna ports related to generating channel state information according to aspects of the present disclosure;

[0028] Figure 12 is a block diagram illustrating encoder and decoder functions related to generating channel state information according to aspects of the present disclosure;

[0029] Figure 13 is a block diagram illustrating encoder and decoder functions related to generating channel state information according to aspects of the present disclosure;

[0030] Figure 14 illustrates additional encoder and decoder functions related to generating channel state information according to aspects of the present disclosure;

[0031] Figure 15Illustrate additional encoder and decoder functions related to generating channel state information according to aspects of the present disclosure;

[0032] Figure 16 Is a flowchart illustrating an example of a process for wireless communication according to aspects of the present disclosure;

[0033] Figure 17 Is a flowchart illustrating an example of a process for wireless communication according to aspects of the present disclosure;

[0034] Figure 18 Is a block diagram illustrating autoencoder-based CSI feedback according to aspects of the present disclosure;

[0035] Figure 19 Is a graph showing the squared generalized cosine similarity (SGCS) performance of channel estimation according to aspects of the present disclosure;

[0036] Figure 20 Illustrate a graph of the average SGCS performance of channel state information feedback (CSF) according to aspects of the present disclosure;

[0037] Figure 21 Is a block diagram illustrating a proposed framework for CSF at low-density pilots according to aspects of the present disclosure;

[0038] Figure 22 Is a diagram illustrating an example of a neural network architecture of a base station for implementing certain aspects of the present technology according to aspects of the present disclosure;

[0039] Figure 23 Is a diagram illustrating an example of a neural network architecture of a user equipment for implementing certain aspects of the present technology according to aspects of the present disclosure; and

[0040] Figure 24 Is a diagram illustrating an example of a system for implementing certain aspects of the present technology according to aspects of the present disclosure. Detailed Description

[0041] Certain aspects of the present disclosure are provided below. Some of these aspects can be applied independently, and some of them can be applied in combination, which will be obvious to those skilled in the art. In the following description, specific details are set forth for the purpose of explanation to provide a thorough understanding of the aspects of the present application. However, it will be obvious that the various aspects can be implemented without these specific details. The accompanying drawings and description are not intended to be restrictive.

[0042] The following description provides only example aspects and is not intended to limit the scope, applicability, or configuration of the present disclosure. Instead, the following description of example aspects will provide those skilled in the art with a description that can be used to implement the example aspects. It should be understood that various changes can be made to the functions and arrangements of the elements without departing from the essence and scope of the present application as set forth in the appended claims.

[0043] Various technologies are provided with reference to wireless technologies (e.g., the 3rd Generation Partnership Project (3GPP) 5G / New Radio (NR) standard) to provide improvements to wireless communication. Wireless networks are deployed to provide various communication services such as voice, video, packet data, messaging, broadcasting, etc. A wireless network can support two access links for communication between various wireless devices. An access link can refer to any communication link between a client device (e.g., a user equipment (UE), a station (STA), or other client device) and a base station (e.g., a 3GPP gNodeB (gNB) for 5G / NR, a 3GPP eNodeB (eNB) for LTE, a Wi-Fi access point (AP), or other base station) or components of a decomposed base station (e.g., a central unit, a distributed unit, and / or a radio unit). In one example, the access link between a UE and a 3GPP gNB can be via the Uu interface. In some cases, the access link can support uplink signaling, downlink signaling, connection procedures, etc.

[0044] Channel state information (CSI) feedback can be used by a network entity (e.g., a base station such as a 3GPP gNodeB (NB)) in a wireless communication system to determine the channel condition for scheduling downlink data transmission. For example, a user equipment (UE) can receive a CSI reference signal (CSI-RS) from a base station (e.g., a gNB) and perform channel estimation based on the CSI-RS. According to the current 3GPP standard, the CSI report configuration includes a codebook that is used as a precoding matrix indicator (PMI) dictionary, according to which the UE can report the best PMI codeword based on channel and / or interference measurements from the received CSI-RS. The UE can use a bit sequence to report the PMI.

[0045] In some cases, AI / ML-based CSI feedback can use a CSIML encoder and / or a CSIML decoder instead of the PMI. For example, a UE intending to convey CSI to the gNB can use a CSIML encoder (e.g., an encoder neural network model) to derive a compressed representation (also referred to as a latent representation or latent message) of the CSI for transmission to the gNB. The gNB can use a CSIML decoder (e.g., a decoder neural network model) to reconstruct the target CSI from the compressed representation. The CSIML encoder is similar to the PMI search algorithm in the current system. The CSIML decoder is similar to the PMI codebook and is used to convert CSI report bits into PMI codewords.

[0046] Conventional CSI-RS occupies 1 resource element (RE) per resource block (RB) per port. Example types of resource configurations can cause large overheads, especially when a large number (e.g., thousands) of antennas and / or transmit resource units (TxRUs) are equipped at a base station (e.g., for holographic multi-input multi-output (MIMO)) or other network devices or entities (e.g., reconfigurable intelligent surfaces (RIS), etc.).

[0047] In some cases, low-density RS can be implemented by an RB comb pattern (e.g., a non-uniform RB pattern), or (random) Tx-RB selection, or Nt ports multiplexed on L REs per RB via a learned coverage code (where Nt > L). For CSI feedback (or channel state feedback (CSF)) under low-density CSI-RS, a decision can be made as to whether to use an ML function that jointly performs channel estimation or two separate functions as currently performed. One problem with using separate functions is that channel estimation can become a bottleneck, thus limiting CSF performance.

[0048] Furthermore, for CSI feedback (or channel state feedback (CSF)) under low-density CSI-RS, a decision can be made as to whether the UE should report CSI on fewer than all Tx-RB (or Tx sub-band) resources or report CSI for all resources. Reporting CSI for all resources can be problematic. For example, the UE can recover the channel to obtain the full resources and then perform compression again. However, some resources may have poor channel estimation quality, in which case there is no benefit in providing CSI reports.

[0049] This document describes systems, apparatuses, processes (also referred to as methods), and computer-readable media (collectively referred to herein as "systems and techniques") for providing partial sub-band reporting based on low-density CSI-RS and channel estimation accuracy. For example, a UE may receive CSI-RS transmissions on a first set of frequency units (e.g., RBs or sub-bands) from all available frequency resources and / or on a first set of antenna ports from all available antenna ports. The UE may generate CSI feedback for a second set of frequency units and / or a second set of antenna ports to facilitate CSI generation or reconstruction on a third set of frequency units and / or a third set of antenna ports (e.g., at a base station such as a gNB). In some cases, the second set of frequency units and / or the second set of antenna ports are determined at least in part based on the first set of frequency units and / or the first set of antenna ports, the third set of frequency units and / or the third set of antenna ports, received signal power, interference level, channel estimation accuracy of the received CSI-RS, based on gNB configuration (e.g., configuration received from the gNB), any combination thereof, and / or other information. In some cases, the third set of frequency units and / or the third set of antenna ports are the complete set of available resources and / or ports, a configured set of frequency units and / or ports, or at least in part dependent on the second set of resources and / or ports. In some cases, the third set of frequency units and / or the third set of antenna ports are equal to the second set of frequency units and / or the second set of antenna ports. The UE may then send a CSI report to the base station that includes a representation of the CSI (e.g., a latent representation generated by an ML encoder).

[0050] A base station (e.g., gNB) or a part thereof (e.g., a central unit (CU), a distributed unit (DU), a radio unit (RU), a near real-time (near-RT) radio access network (RAN) intelligent controller (RIC), or a non-real-time (non-RT) RIC of the base station) may transmit CSI-RS on a first set of frequency units and / or a first set of antenna ports. The base station (or a part thereof) may receive CSI feedback (from a UE) for a second set of frequency units and / or on a second set of antenna ports. The base station (or a part thereof) may include an ML model (e.g., an ML-based encoder) that enables determination of CSI for a complete set of resources based on CSI feedback received on a partial set of resources (e.g., frequency units on a set of antenna ports). For example, the base station (or a part thereof) may generate final CSI (e.g., by using the ML encoder to reconstruct CSI) for a third set of frequency units and / or a third set of antenna ports. As noted above, the third set of resources may be all available frequency resources (e.g., a complete subband of a bandwidth part (BWP)), and the third set of antenna ports may be all available antenna ports. In another example, the third set of frequency resources and / or antenna ports may depend at least in part on the second set of frequency resources and / or antenna ports.

[0051] One drawback of methods for transmitting CSI for a complete set of frequency resources and / or antenna ports is that some frequency resources in the frequency resources (e.g., subbands) may have poor channel quality, while other parts of the frequency resources may have good channel quality. For example, some blocks representing RBs on an antenna port may have good quality, while other blocks may represent RBs with poor quality on the antenna port. If the system still reports CSI for the complete resources, the system may mix good-quality subband data with poor-quality subband data, which may degrade the compression efficiency of the CSI report. By not including poor-quality subband data, the compression efficiency of good subband data can be improved. Using the systems and techniques described herein, a base station (e.g., gNB) can accurately recover or reconstruct CSI for good subband data and can use a trained ML model (e.g., a trained neural network) to reconstruct CSI for the complete set of resources. The method can selectively recover a subset of the complete subbands. Thus, in one scenario, when some RBs and / or antenna ports in the RBs and / or antenna ports have poor quality, the system may not even report on those RBs and / or antenna ports and leave the determination of CSI for those subbands to the base station to extrapolate. The base station can thus reconstruct CSI for the complete set of resources based on a partial set of CSI data.

[0052] Additional aspects of the present disclosure are described in more detail below with reference to the accompanying drawings. Exemplary aspects are also provided in Appendix A provided herewith.

[0053] As used herein, the terms “user equipment” (UE) and “network entity” are not intended to be dedicated to or otherwise limited to any particular radio access technology (RAT) unless otherwise specified. In general, a UE can be any wireless communication device (e.g., a mobile phone, router, tablet computer, laptop computer, and / or tracking device, etc.), a wearable device (e.g., a smart watch, smart glasses, wearable ring, and / or an extended reality (XR) device such as a virtual reality (VR) headset, an augmented reality (AR) headset or glasses, or a mixed reality (MR) headset), a vehicle (e.g., a car, motorcycle, bicycle, etc.), and / or an Internet of Things (IoT) device, etc., for a user to communicate over a wireless communication network. The UE can be mobile or can be stationary (e.g., at certain times) and can communicate with a radio access network (RAN). As used herein, the term “UE” can be interchangeably referred to as “access terminal” or “AT”, “client device”, “wireless device”, “subscriber device”, “subscriber terminal”, “subscriber station”, “user terminal” or “UT”, “mobile device”, “mobile terminal”, “mobile station” or variations thereof. Generally speaking, a UE can communicate with a core network via a RAN, and through the core network, the UE can communicate with external networks such as the Internet and with other UEs. Of course, other mechanisms for connecting to the core network and / or the Internet are also possible for the UE, such as via a wired access network, a wireless local area network (WLAN) network (e.g., based on the IEEE 802.11 communication standard, etc.).

[0054] The network entity can be implemented in a centralized or monolithic base station architecture, or alternatively, in a split base station architecture, and can include one or more of a Central Unit (CU), a Distributed Unit (DU), a Radio Unit (RU), a Near Real-Time (Near RT) RAN Intelligent Controller (RIC), or a Non-Real-Time (Non RT) RIC. A base station (e.g., having a centralized / monolithic base station architecture or a split base station architecture) can operate to communicate with a UE according to one of several Radio Access Technologies (RATs) depending on the network in which the base station is deployed, and can alternatively be referred to as an Access Point (AP), a network node, a NodeB (NB), an evolved NodeB (eNB), a next-generation eNB (ng-eNB), a New Radio (NR) NodeB (also referred to as a gNB or gNodeB), etc. The base station can mainly be used to support the wireless access of a UE, including supporting the data, voice, and / or signaling connections of the supported UE. In some systems, the base station can provide edge node signaling functions, while in other systems, the base station can provide additional control and / or network management functions. The communication link through which the UE transmits signals to the base station is called an Uplink (UL) channel (e.g., a reverse traffic channel, a reverse control channel, an access channel, etc.). The communication link through which the base station transmits signals to the UE is called a Downlink (DL) or a forward link channel (e.g., a paging channel, a control channel, a broadcast channel, or a forward traffic channel, etc.). As used herein, the term Traffic Channel (TCH) can refer to an uplink, reverse, or downlink, and / or a forward traffic channel.

[0055] The term "network entity" or "base station" (e.g., having an integrated / monolithic base station architecture or a disaggregated base station architecture) may refer to a single physical transmit-receive point (TRP) or multiple physical TRPs that may or may not be co-located. For example, in the case where the term "network entity" or "base station" refers to a single physical TRP, the physical TRP may be a base station antenna corresponding to a cell (or a number of cell sectors) of the base station. In the case where the term "network entity" or "base station" refers to multiple co-located physical TRPs, these physical TRPs may be an antenna array of the base station (e.g., as in a multiple-input multiple-output (MIMO) system or in the case where the base station employs beamforming). In the case where the term "base station" refers to multiple non-co-located physical TRPs, the physical TRPs may be a distributed antenna system (DAS) (a network of spatially separated antennas connected to a common source via a transmission medium) or a remote radio head (RRH) (a remote base station connected to a serving base station). Alternatively, the non-co-located physical TRPs may be a serving base station that receives measurement reports from a UE and a neighbor base station whose reference radio frequency (RF) signal (or simply "reference signal") the UE is measuring. Since, as used herein, a TRP is the point by which a base station transmits and receives wireless signals, a reference to transmission from or reception at a base station should be understood to refer to a particular TRP of the base station.

[0056] In some specific implementations that support UE positioning, a network entity or base station may not support wireless access of the UE (e.g., may not support data, voice, and / or signaling connections regarding the UE), but instead may alternatively send a reference signal to be measured by the UE and / or may receive and measure signals transmitted by the UE. Such a base station may be referred to as a positioning beacon (e.g., in the case of sending a signal to the UE) and / or as a position measurement unit (e.g., in the case of receiving and measuring signals from the UE).

[0057] An RF signal includes an electromagnetic wave of a given frequency that transmits information through the space between a transmitter and a receiver. As used herein, a transmitter may send a single "RF signal" or multiple "RF signals" to a receiver. However, due to the propagation characteristics of an RF signal through a multipath channel, a receiver may receive multiple "RF signals" corresponding to each transmitted RF signal. The same transmitted RF signal on different paths between the transmitter and the receiver may be referred to as a "multipath" RF signal. As used herein, where the context clearly indicates that the term "signal" refers to a wireless signal or an RF signal, the RF signal may also be referred to as a "wireless signal" or simply as a "signal".

[0058] Various aspects of the systems and techniques described herein will be discussed below with reference to the figures. According to various aspects, Figure 1An example of a wireless communication system 100 is illustrated. The wireless communication system 100 (which may also be referred to as a wireless wide area network (WWAN)) may include various base stations 102 and various UEs 104. In some aspects, a base station 102 may also be referred to as a “network entity” or a “network node”. One or more of the base stations 102 may be implemented in an aggregated or monolithic base station architecture. Additionally or alternatively, one or more of the base stations 102 may be implemented in a disaggregated base station architecture and may include one or more of a central unit (CU), a distributed unit (DU), a radio unit (RU), a near real-time (near-RT) RAN intelligent controller (RIC), or a non-real-time (non-RT) RIC. The base stations 102 may include macrocell base stations (high-power cellular base stations) and / or small cell base stations (low-power cellular base stations). In one aspect, a macrocell base station may include an eNB and / or an ng-eNB (where the wireless communication system 100 corresponds to a Long-Term Evolution (LTE) network), or a gNB (where the wireless communication system 100 corresponds to a New Radio (NR) network), or a combination of both, and a small cell base station may include a femtocell, a picocell, a microcell, etc.

[0059] The base stations 102 may together form a RAN and interface with a core network 170 (e.g., an evolved packet core (EPC) or a 5G core (5GC)) via a backhaul link 122 and interface to one or more location servers 172 (which may be part of the core network 170 or may be external to the core network 170) via the core network 170. Among other functions, the base stations 102 may perform functions related to one or more of the following: transferring user data, radio channel encryption and decryption, integrity protection, header compression, mobility control functions (e.g., handover, dual connectivity), inter-cell interference coordination, connection establishment and release, load balancing, distribution of non-access stratum (NAS) messages, NAS node selection, synchronization, RAN sharing, multimedia broadcast multicast service (MBMS), subscriber and equipment tracking, RAN information management (RIM), paging, positioning, and delivery of warning messages. The base stations 102 may communicate with each other directly or (e.g., via the EPC or 5GC) indirectly via a backhaul link 134 (which may be wired and / or wireless).

[0060] Base station 102 can communicate wirelessly with UE 104. Each base station in base station 102 can provide communication coverage for a corresponding geographical coverage area 110. In one aspect, one or more cells can be supported by the base stations in base station 102 in each coverage area 110. A "cell" is a logical communication entity used to communicate with a base station (e.g., on a certain frequency resource, which is called carrier frequency, component carrier, carrier, frequency band, etc.), and can be associated with an identifier (e.g., physical cell identifier (PCI), virtual cell identifier (VCI), cell global identifier (CGI)) to distinguish cells operating via the same or different carrier frequencies. In some cases, different cells can be configured according to different protocol types that can provide access for different types of UEs (e.g., machine type communication (MTC), narrowband IoT (NB-IoT), enhanced mobile broadband (eMBB) or other protocol types). Since a cell is supported by a specific base station, the term "cell" can refer to either or both of the logical communication entity and the base station supporting it depending on the context. In addition, since the TRP is usually the physical transmission point of a cell, the terms "cell" and "TRP" can be used interchangeably. In some cases, the term "cell" can also refer to the geographical coverage area of a base station (e.g., a sector), as long as a carrier frequency can be detected within a certain part of the geographical coverage area 110 and this carrier frequency is used for communication within this part.

[0061] Although the geographical coverage areas 110 of adjacent macro cell base stations of base station 102 can partially overlap (e.g., in a handover area), some of the geographical coverage areas in geographical coverage area 110 can substantially overlap with a larger geographical coverage area 110. For example, the small cell base station 102' can have a coverage area 110' that substantially overlaps with the coverage areas 110 of one or more macro cell base stations 102. A network including both small cell base stations and macro cell base stations can be called a heterogeneous network. The heterogeneous network can also include a home eNB (HeNB), which can provide services to a restricted group called a closed subscriber group (CSG).

[0062] The communication link 120 between base station 102 and UE 104 can include an uplink (also called reverse link) transmission from the UE in UE 104 to the base station in base station 102 and / or a downlink (also called forward link) transmission from the base station in base station 102 to the UE in UE 104. The communication link 120 can use MIMO antenna technology, including spatial multiplexing, beamforming, and / or transmit diversity. The communication link 120 can pass through one or more carrier frequencies. The allocation of carriers can be asymmetric for the downlink and uplink (e.g., more or fewer carriers can be allocated to the downlink compared to the uplink).

[0063] The wireless communication system 100 may also include a WLAN AP 150 that communicates with a WLAN station (STA) 152 via a communication link 154 in an unlicensed spectrum (e.g., 5 gigahertz (GHz)). When communicating in an unlicensed spectrum, the WLAN STA 152 and / or the WLAN AP 150 may perform a Clear Channel Assessment (CCA) or Listen Before Talk (LBT) procedure before communication to determine whether the channel is available. In some examples, the wireless communication system 100 may include devices (e.g., UEs, etc.) that communicate with one or more of the UEs 104, the base station 102, the AP 150, etc. using the Ultra-Wideband (UWB) spectrum. The range of the UWB spectrum may be from 3.1 GHz to 10.5 GHz.

[0064] The small cell base station 102' may operate in licensed and / or unlicensed spectrum. When operating in an unlicensed spectrum, the small cell base station 102' may employ LTE or NR technologies and use the same 5 GHz unlicensed spectrum used by the WLAN AP 150. Small cell base stations 102' that employ LTE and / or 5G in unlicensed spectrum may boost the coverage of the access network and / or increase the capacity of the access network. NR in unlicensed spectrum may be referred to as NR-U. LTE in unlicensed spectrum may be referred to as LTE-U, Licensed-Assisted Access (LAA), or MulteFire.

[0065] The wireless communication system 100 may also include a millimeter wave (mmW) base station 180 that may operate at mmW frequencies and / or near mmW frequencies to communicate with a UE 182. The mmW base station 180 may be implemented in an integrated or monolithic base station architecture, or alternatively, in a disaggregated base station architecture (e.g., including one or more of a CU, a DU, an RU, a near-RT RIC, or a non-RT RIC). The Extremely High Frequency (EHF) is a part of the RF in the electromagnetic spectrum. The EHF has a range of 30 GHz to 300 GHz and a wavelength between 1 millimeter and 10 millimeters. The radio waves in the reference band may be referred to as millimeter waves. Near mmW may extend down to frequencies of 3 GHz with a wavelength of 100 millimeters. The Super High Frequency (SHF) band extends between 3 GHz and 30 GHz, which is also referred to as centimeter waves. Communications using mmW and / or near mmW radio frequency bands have high path loss and relatively short distances. The mmW base station 180 and the UE 182 may utilize beamforming (transmission and / or reception) on the mmW communication link 184 to compensate for the extremely high path loss and short distances. Additionally, it should be understood that in an alternative configuration, one or more of the base stations 102 may also use mmW or near mmW and beamforming for transmission. Therefore, it should be understood that the foregoing illustrations are merely examples and should not be construed as limiting the various aspects disclosed herein.

[0066] In some aspects related to 5G, the spectrum in which a radio network node or entity (e.g., base station 102 / 180, UE 104 / 182) operates is divided into multiple frequency ranges: FR1 (from 450 megahertz (MHz) to 6000 MHz), FR2 (from 24250 MHz to 52600 MHz), FR3 (above 52600 MHz), and FR4 (between FR1 and FR2). In a multi-carrier system such as 5G, one of the carrier frequencies is referred to as the "primary carrier" or "anchor carrier" or "primary serving cell" or "PCell", and the remaining carrier frequencies are referred to as "secondary carriers" or "secondary serving cells" or "SCells". In carrier aggregation, the anchor carrier is a carrier that operates on the primary frequency (e.g., FR1) utilized by the UE 104 / 182 and the cell, where the UE 104 / 182 performs the initial radio resource control (RRC) connection establishment procedure or initiates the RRC connection re-establishment procedure in this cell. The primary carrier carries all common control channels as well as UE-specific control channels, and can be a carrier in a licensed frequency (however, this is not always the case). The secondary carrier is a carrier that operates on a second frequency (e.g., FR2), which can be configured and used to provide additional radio resources once an RRC connection is established between the UE in the UE 104 and the anchor carrier. In some cases, the secondary carrier can be a carrier in an unlicensed frequency. The secondary carrier may only contain necessary signaling information and signals. For example, since the primary uplink carrier and the primary downlink carrier are usually UE-specific, those UE-specific signaling information and signals may not exist in the secondary carrier. In other words, different UEs 104 / 182 in a cell may have different downlink primary carriers. The same holds for the uplink primary carrier. The network is able to change the primary carrier of any UE 104 / 182 at any time. Changing the primary carrier is done, for example, to balance the load on different carriers. Since the "serving cell" (whether it is a PCell or an SCell) corresponds to the carrier frequency and / or component carrier through which some base station is communicating, the terms "cell", "serving cell", "component carrier", "carrier frequency", etc. can be used interchangeably.

[0067] For example, still referring to Figure 1, one of the frequencies used by the macro cell base station of base station 102 can be an anchor carrier (or "PCell"), and the other frequencies used by the macro cell base station and / or the mmW base station 180 of base station 102 can be secondary carriers ("SCell"). In carrier aggregation, base station 102 and / or UE 104 can use up to Y MHz (e.g., 5 MHz, 10 MHz, 15 MHz, 20 MHz, 100 MHz) of spectrum bandwidth per carrier, with up to a total of Yx MHz (x component carriers) in each direction for transmission. The component carriers can be adjacent to each other in the spectrum or may not be adjacent to each other. The allocation of carriers can be asymmetric with respect to the downlink and the uplink (e.g., more or fewer carriers can be allocated to the downlink compared to the uplink). Simultaneous transmission and / or reception of multiple carriers enables UE 104 / 182 to significantly increase its data transmission and / or reception rate. For example, compared to the data rate obtained with a single 20 MHz carrier, two 20 MHz aggregated carriers in a multi-carrier system would theoretically result in a doubling of the data rate (i.e., 40 MHz).

[0068] To operate on multiple carrier frequencies, the base station in base station 102 and / or the UE in UE 104 can be equipped with multiple receivers and / or transmitters. For example, UE 104 can have two receivers, namely "Receiver 1" and "Receiver 2", where "Receiver 1" is a multi-band receiver that can be tuned to band (i.e., carrier frequency) "X" or band "Y", and "Receiver 2" is a single-band receiver that can be tuned to only band "Z". In one example, if the UE in UE 104 is being served in band "X", then band "X" will be referred to as the PCell or the active carrier frequency, and "Receiver 1" will need to be tuned from band "X" to band "Y" (SCell) to measure band "Y" (and vice versa). In contrast, regardless of whether the UE in UE 104 is being served in band "X" or band "Y", due to the separate "Receiver 2", the UE in UE 104 can measure band "Z" without interrupting the service on band "X" or band "Y".

[0069] The wireless communication system 100 can also include UE 164, which can communicate with the macro cell base station of base station 102 on communication link 120 and / or communicate with mmW base station 180 on mmW communication link 184. For example, the macro cell base station of base station 102 can support a PCell and one or more SCell for UE 164, and the mmW base station 180 can support one or more SCell for UE 164.

[0070] The wireless communication system 100 may also include one or more UEs (such as UE 190), which are indirectly connected to one or more communication networks via one or more device-to-device (D2D) peer-to-peer (P2P) links (referred to as "sidelinks"). In Figure 1 the example of, UE 190 has a D2D P2P link 192 with one of the UEs in UE 104 connected to one of the base stations in base station 102 (e.g., UE 190 can indirectly obtain a cellular connection through this D2D P2P link), and has a D2D P2P link 194 with WLAN STA 152 connected to WLAN AP 150 (UE 190 can indirectly obtain a WLAN-based Internet connection through this D2D P2P link). In one example, D2D P2P links 192 and 194 can use any well-known D2D RAT (such as LTE Direct (LTE-D), WiFi Direct (WiFi-D), etc.) to support.

[0071] Figure 2 A block diagram showing the design of a base station in base station 102 and a UE in UE 104 according to some aspects of the present disclosure, which enables the transmission and processing of signals exchanged between the UE and the base station. Design 200 includes components of the base station in base station 102 and the UE in UE 104, and the base station and the UE can be Figure 1 one of the base stations in base station 102 and one of the UEs in UE 104. The base station in base station 102 may be equipped with T antennas 234a to 234t, and the UE in UE 104 may be equipped with R antennas 252a to 252r, where generally T≥1 and R≥1.

[0072] At base station 102, 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 the UEs, process (e.g., encode and modulate) the data for each UE at least in part based on the MCSs selected for the UEs, and provide data symbols for all UEs. Transmit processor 220 may also process system information (e.g., for semi-static resource partitioning information (SRPI), etc.) and control information (e.g., CQI requests, grants, upper layer signaling, channel state information, channel state feedback, etc.), and provide overhead symbols and control symbols. Transmit processor 220 may also generate reference symbols for reference signals (e.g., cell-specific reference signals (CRSs)) and synchronization signals (e.g., primary synchronization signal (PSS) and 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. MODs 232a through 232t are shown as combined modulator-demodulators (MOD-DEMODs). In some cases, the modulator and demodulator may be separate components. Each modulator in MODs 232a through 232t may process the corresponding output symbol stream (e.g., for an orthogonal frequency division multiplexing (OFDM) scheme, etc.) to obtain an output sample stream. Each modulator in MODs 232a through 232t may further process (e.g., convert to analog, amplify, filter, and up-convert) the output sample stream to obtain a downlink signal. The T downlink signals may be transmitted from MODs 232a through 232t via T antennas 234a through 234t, respectively. According to certain aspects described in more detail below, position coding may be utilized to generate synchronization signals to convey additional information.

[0073] At the UE in UE 104, R antennas 252a through 252r may receive downlink signals from the base station in base station 102 and / or other base stations, and may provide the received signals to demodulators (DEMOD) 254a through 254r, respectively. DEMODs 254a through 254r are shown as combined modulator-demodulators (MOD-DEMOD). In some cases, the modulator and demodulator may be separate components. Each of the DEMODs 254a through 254r may condition (e.g., filter, amplify, down-convert, and digitize) the received signals to obtain input samples. Each of the DEMODs 254a through 254r may further process the input samples (e.g., for OFDM, etc.) to obtain the received symbols. The MIMO detector 256 may obtain the received symbols from all R DEMODs 254a through 254r, perform MIMO detection on the received symbols (if applicable), and provide the detected symbols. The receive processor 258 may process (e.g., demodulate and decode) the detected symbols, provide the decoded data for the UE in UE 104 to the data sink 260, and provide the decoded control information and system information to the controller / processor 280. The channel processor may determine the reference signal received power (RSRP), received signal strength indicator (RSSI), reference signal received quality (RSRQ), channel quality indicator (CQI), etc.

[0074] On the uplink, at the UE in UE 104, a transmit processor 264 may receive and process data from a data source 262 and control information from a controller / processor 280 (e.g., for reports including RSRP, RSSI, RSRQ, CQI, channel state information, channel feedback information, etc.). The transmit processor 264 may also generate reference symbols for one or more reference signals (e.g., at least partially based on a β value or set of β values associated with the one or more reference signals). Symbols from the transmit processor 264 may be pre-coded by a TX MIMO processor 266 in the case of application, further processed by DEMODs 254a to 254r (e.g., for DFT-s-OFDM, CP-OFDM, etc.), and transmitted to the base station 102. At the base station 102, uplink signals from the UE in UE 104 and other UEs may be received by T antennas 234a to 234t, processed by DEMODs 254a to 254r, detected by a MIMO detector 236 in the case of application, and further processed by a receive processor 238 to obtain decoded data and control information transmitted by the UE in UE 104. The receive processor 238 may provide the decoded data to a data sink 239 and the decoded control information to a controller (processor) 240. The base station in the base station 102 may include a communication unit 244 and communicate with a network controller 231 via the communication unit 244. The network controller 231 may include a communication unit 294, a controller / processor 290, and a memory 292.

[0075] In some aspects, one or more components of UE 104 may be included in a housing. The controller 240 of the base station 102, the controller / processor 280 of UE 104, and / or Figure 2 any other components may perform one or more techniques associated with implicit UCI β value determination for NR.

[0076] Memories 242 and 282 may store data and program codes for the base station in the base station 102 and the UE in UE 104, respectively. A scheduler 246 may schedule UEs for data transmission on the downlink, uplink, and / or sidelink.

[0077] In some aspects, the deployment of a communication system such as a 5G New Radio (NR) system can be arranged with various components or constituent parts in a variety of ways. In a 5G NR system or network, network nodes, network entities, mobility elements of the network, radio access network (RAN) nodes, core network nodes, network elements, or network equipment (such as a base station (BS)) or one or more units (or one or more components) performing base station functions can be implemented in an aggregated or disaggregated architecture. For example, a BS (such as a Node B (NB), evolved NB (eNB), NR BS, 5G NB, access point (AP), transmit receive point (TRP), or cell, etc.) can be implemented as an aggregated base station (also referred to as a stand-alone BS or monolithic BS) or a disaggregated base station.

[0078] An aggregated base station can be configured to utilize a radio protocol stack physically or logically integrated within a single RAN node. A disaggregated base station can be configured to utilize a protocol stack physically or logically distributed between two or more units (such as one or more central or centralized units (CUs), one or more distributed units (DUs), or one or more radio units (RUs)). In some aspects, a CU can be implemented within a RAN node, and one or more DUs can be co-located with the CU, or alternatively, can be geographically or virtually distributed in one or more other RAN nodes. A DU can be implemented to communicate with one or more RUs. Each of the CU, DU, and RU can also be implemented as a virtual unit, i.e., a virtual central unit (VCU), a virtual distributed unit (VDU), or a virtual radio unit (VRU).

[0079] Base station type operations or network designs can consider the aggregation characteristics of base station functionality. For example, a disaggregated base station can be used in an integrated access backhaul (IAB) network, an open radio access network (O-RAN (such as a network configuration initiated by the O-RAN Alliance)), or a virtualized radio access network (vRAN, also referred to as a cloud radio access network (C-RAN)). Disaggregation can include distributing functionality across two or more units at various physical locations and virtually distributing the functionality of at least one unit, which can achieve flexibility in network design. The individual units of a disaggregated base station or disaggregated RAN architecture can be configured for wired or wireless communication with at least one other unit.

[0080] Figure 3FIG. shows a diagram illustrating an exemplary disaggregated base station 300 architecture. The disaggregated base station 300 architecture may include one or more central units (CUs) 310, which may communicate directly with the core network 320 via a backhaul link, or indirectly with the core network 320 through one or more disaggregated base station units (such as a near real-time (near RT) RAN intelligent controller (RIC) 325 via an E2 link, or a non-real-time (non RT) RIC 315 associated with a service management and orchestration (SMO) framework 305, or both). The one or more CUs 310 may communicate with one or more distributed units (DUs) 330 via respective midhaul links (such as an F1 interface). The DUs 330 may communicate with one or more radio units (RUs) 340 via respective fronthaul links. The RUs 340 may communicate with a respective UE among the UEs 104 via one or more radio frequency (RF) access links. In some specific implementations, a UE among the UEs 104 may be served simultaneously by multiple RUs 340.

[0081] Each of these units (e.g., CU 310, DU 330, RU 340), as well as the near RT RIC 325, non-RT RIC 315, and SMO framework 305 may include one or more interfaces, or be coupled to one or more interfaces configured to receive or transmit signals, data, or information (collectively referred to as signals) via a wired or wireless transmission medium. Each of these units or an associated processor or controller providing instructions to the communication interfaces of these units may be configured to communicate with one or more of the other units via the transmission medium. For example, these units may include a wired interface configured to receive signals or transmit signals to one or more of the other units via a wired transmission medium. Additionally, these units may include a wireless interface, which may include a receiver, a transmitter, or a transceiver (such as a radio frequency (RF) transceiver) configured to receive signals or transmit signals to one or more of the other units via a wireless transmission medium, or both.

[0082] In some aspects, one or more CUs 310 may host one or more higher layer control functions. Such control functions may include Radio Resource Control (RRC), Packet Data Convergence Protocol (PDCP), Service Data Adaptation Protocol (SDAP), etc. Each control function may be implemented using an interface that is configured to communicate signals with other control functions hosted by the CU 310. One or more CUs 310 may be configured to handle user plane functionality (i.e., Central Unit - User Plane (CU-UP)), control plane functionality (i.e., Central Unit - Control Plane (CU-CP)), or a combination thereof. In some specific implementations, one or more CUs 310 may be logically split into one or more CU-UP units and one or more CU-CP units. When implemented in an O-RAN configuration, the CU-UP units may communicate bidirectionally with the CU-CP units via interfaces such as the E1 interface. As needed, one or more CUs 310 may be implemented to communicate with the DU 330 for network control and signaling.

[0083] The DU 330 may correspond to a logical unit that includes one or more base station functions for controlling the operation of one or more RUs 340. In some aspects, the DU 330 may host one or more of the Radio Link Control (RLC) layer, Media Access Control (MAC) layer, and one or more high Physical (PHY) layers (such as modules for forward error correction (FEC) encoding and decoding, scrambling, modulation, and demodulation, etc.) at least partially depending on function split (such as those defined by the Third Generation Partnership Project (3GPP)). In some aspects, the DU 330 may also host one or more low PHY layers. Each layer (or module) may be implemented using an interface that is configured to communicate signals with other layers (and modules) hosted by the DU 330 or with control functions hosted by the CU 310.

[0084] Lower layer functionality may be implemented by one or more RUs 340. In some deployments, the RUs 340 controlled by the DU 330 may correspond to logical nodes that host RF processing functions or low PHY layer functions (such as performing fast Fourier transform (FFT), inverse FFT (iFFT), digital beamforming, physical random access channel (PRACH) extraction and filtering, etc.) or both, at least in part based on function splitting (such as lower layer function splitting). In such an architecture, the RU 340 may be implemented to handle over-the-air (OTA) communication with one or more of the UEs 104. In some embodiments, the real-time and non-real-time aspects of the control plane communication and user plane communication with the RU 340 may be controlled by the DU 330. In some scenarios, the configuration may enable the DU 330 (which may be one or more DUs) and one or more CUs 310 to be implemented in a cloud-based RAN architecture such as a vRAN architecture.

[0085] The SMO framework 305 may be configured to support RAN deployment and orchestration of non-virtualized network elements and virtualized network elements. For non-virtualized network elements, the SMO framework 305 may be configured to support the deployment of dedicated physical resources for RAN coverage requirements, which may be managed via an operation and maintenance interface (such as the O1 interface). For virtualized network elements, the SMO framework 305 may be configured to interact with a cloud computing platform (such as the Open Cloud (O-Cloud) 390) to perform network element lifecycle management (such as instantiating virtualized network elements) via a cloud computing platform interface (such as the O2 interface). Such virtualized network elements may include, but are not limited to, the CU 310, DU 330, RU 340, and the near RT RIC 325. In some embodiments, the SMO framework 305 may communicate with the hardware aspects of the 4G RAN (such as the Open eNB (O-eNB) 311) via the O1 interface. Additionally, in some embodiments, the SMO framework 305 may communicate directly with one or more RUs 340 via the O1 interface. The SMO framework 305 may also include a non-RT RIC 315 configured to support the functionality of the SMO framework 305.

[0086] The non-RT RIC 315 can be configured to include a logic function that can implement non-real-time control and optimization of RAN elements and resources, an artificial intelligence / machine learning (AI / ML) workflow including model training and updating, or policy-based guidance of applications / features in the near-RT RIC 325. The non-RT RIC 315 can be coupled to or communicate with the near-RT RIC 325 (such as via the A1 interface). The near-RT RIC 325 can be configured to include a logic function that can implement near-real-time control and optimization of RAN elements and resources through an interface (such as via the E2 interface) via data collection and actions, and the interface (such as via the E2 interface) connects one or more CUs 310, DUs 330 (or multiple DUs) or both, and the O-eNB to the near-RT RIC 325.

[0087] In some specific implementations, in order to generate an AI / ML model to be deployed in the near-RT RIC 325, the non-RT RIC 315 can receive parameters or external enrichment information from an external server. Such information can be utilized by the near-RT RIC 325 and can be received from non-network data sources or from network functions at the SMO framework 305 or the non-RT RIC 315. In some examples, the non-RT RIC 315 or the near-RT RIC 325 can be configured to tune RAN behavior or performance. For example, the non-RT RIC 315 can monitor long-term trends and patterns of performance and employ an AI / ML model to perform corrective actions through the SMO framework 305 (such as via reconfiguration of O1) or via creating RAN management policies (such as A1 policies).

[0088] Figure 4An example of a computing system 470 of a wireless device 407 is illustrated. The wireless device 407 may include a client device such as a UE (e.g., a UE among UE 104, UE 152, UE 190) or other types of devices that can be used by an end user (e.g., a station (STA) configured to communicate using a Wi-Fi interface). For example, the wireless device 407 may include a mobile phone, a router, a tablet computer, a laptop computer, a tracking device, a wearable device (e.g., a smartwatch, glasses, an extended reality (XR) device (such as a virtual reality (VR), augmented reality (AR), or mixed reality (MR) device), etc.), an Internet of Things (IoT) device, an access point, and / or another device configured to communicate via a wireless communication network. The computing system 470 includes software and hardware components that may be electrically coupled or communicatively coupled via a bus 489 (or may communicate in other ways, as appropriate). For example, the computing system 470 includes one or more processors 484. The one or more processors 484 may include one or more CPUs, ASICs, FPGAs, APs, GPUs, VPUs, NSPs, microcontrollers, dedicated hardware, any combination thereof, and / or other processing devices or systems. The one or more processors 484 may use the bus 489 to communicate between cores and / or with one or more memory devices 486.

[0089] The computing system 470 may also include one or more memory devices 486, one or more digital signal processors (DSPs) 482, one or more subscriber identity modules (SIMs) 474, one or more modems 476, one or more wireless transceivers 478, one or more antennas 487, one or more input devices 472 (e.g., a camera, a mouse, a keyboard, a touch-sensitive screen, a touchpad, a keypad, a microphone, and / or the like), and one or more output devices 480 (e.g., a display, a speaker, a printer, and / or the like).

[0090] In some aspects, computing system 470 may include one or more RF interfaces configured to send and / or receive radio frequency (RF) signals. In some examples, the RF interface may include components such as one or more modems 476, wireless transceivers 478, and / or antennas 487. One or more wireless transceivers 478 may send and receive wireless signals (e.g., wireless signal 488) via one or more antennas 487 from one or more other devices, such as other wireless devices, network devices (e.g., base stations such as eNBs and / or gNBs, Wi-Fi access points (APs) such as routers, range extenders, etc.), cloud networks, and the like. In some examples, computing system 470 may include multiple antennas or antenna arrays that may facilitate simultaneous transmit and receive functionality. One or more antennas 487 may be omnidirectional antennas such that radio frequency (RF) signals may be received from all directions and transmitted in all directions. Wireless signal 488 may be transmitted via a wireless network. The wireless network may be any wireless network, such as a cellular or telecommunications network (e.g., 3G, 4G, 5G, etc.), a wireless local area network (e.g., a WiFi network), a BluetoothTM network, and / or other networks.

[0091] In some examples, wireless signal 488 may be sent directly to other wireless devices using sidelink communication (e.g., using the PC5 interface, using the DSRC interface, etc.). The wireless transceiver 478 may be configured to send RF signals via one or more antennas 487 for performing sidelink communication according to one or more transmit power parameters that may be associated with one or more regulatory modes. The wireless transceiver 478 may also be configured to receive sidelink communication signals from other wireless devices with different signal parameters.

[0092] In some examples, one or more wireless transceivers 478 may include an RF front end that includes one or more components such as amplifiers, mixers for signal downconversion (also known as signal multipliers), frequency synthesizers (also known as oscillators) that supply signals to the mixers, baseband filters, analog-to-digital converters (ADCs), one or more power amplifiers, and other components. The RF front end generally may handle the selection of wireless signal 488 and the conversion of the wireless signal to a baseband frequency or an intermediate frequency, and may convert the RF signal to the digital domain.

[0093] In some cases, computing system 470 may include a codec (or CODEC) configured to encode and / or decode data sent and / or received using one or more wireless transceivers 478. In some cases, computing system 470 may include an encryption-decryption device or component configured to encrypt and / or decrypt data sent and / or received by one or more wireless transceivers 478 (e.g., according to the AES and / or DES standards).

[0094] One or more SIMs 474 may each securely store an International Mobile Subscriber Identity (IMSI) number and associated keys assigned to a user of the wireless device 407. The IMSI and keys may be used to identify and authenticate the subscriber when accessing a network provided by a network service provider or carrier associated with the one or more SIMs 474. One or more modems 476 may modulate one or more signals to encode information for transmission using one or more wireless transceivers 478. One or more modems 476 may also demodulate signals received by one or more wireless transceivers 478 to decode the transmitted information. In some examples, one or more modems 476 may include a Wi-Fi modem, a 4G (or LTE) modem, a 5G (or NR) modem, and / or other types of modems. One or more modems 476 and one or more wireless transceivers 478 may be used to communicate data of the one or more SIMs 474.

[0095] The computing system 470 may also include one or more non-transitory machine-readable storage media or storage devices (e.g., one or more memory devices 486) (and / or communicate with them), which may include but are not limited to local and / or network-accessible storage, disk drives, drive arrays, optical storage devices, solid-state storage devices such as RAM and / or ROM, which may be programmable, flash-updateable, etc. Such storage devices may be configured to implement any suitable data storage, including but not limited to various file systems, database structures, etc.

[0096] In various aspects, the functionality may be stored as one or more computer program products (e.g., instructions or code) in the memory device 486 and executed by one or more processors 484 and / or one or more DSPs 482. The computing system 470 may also include software elements (e.g., located within one or more memory devices 486), including, for example, an operating system, device drivers, executable libraries, and / or other code, such as one or more applications, which may include computer programs implementing the functionality provided by the various aspects, and / or may be designed to implement methods and / or configure systems as described herein.

[0097] Figure 5An example architecture of a neural network 500 that can be used according to some aspects of the present disclosure is illustrated. The example architecture of the neural network 500 can be defined by an example neural network description 502 in a neural controller 501. The neural network 500 is an example of a machine learning model that can be deployed and implemented at a base station 102, a central unit (CU) 310, a distributed unit (DU) 330, a radio unit (RU) 340 (which can be one or more RUs), and / or at a UE of the UE 104. The neural network 500 can be a feedforward neural network or any other known or to-be-developed neural network or machine learning model.

[0098] The neural network description 502 can include a complete specification of the neural network 500, including Figure 5 the neural architecture shown in. For example, the neural network description 502 can include: a description or specification of the architecture of the neural network 500 (e.g., layers, layer interconnections, the number of nodes in each layer, etc.); input and output descriptions indicating how the input and output are formed or processed; indications of activation functions, operations or filters in the neural network, etc.; neural network parameters such as weights, biases, etc.; and so on.

[0099] The neural network 500 can reflect the neural architecture defined in the neural network description 502. The neural network 500 can include any suitable neural or deep learning type of network. In some cases, the neural network 500 can include a feedforward neural network. In other cases, the neural network 500 can include a recurrent neural network, which can have loops that allow information to be carried across nodes when reading the input. The neural network 500 can include any other suitable neural network or machine learning model. One example includes a convolutional neural network (CNN), which includes an input layer and an output layer, with a plurality of hidden layers between the input layer and the output layer. The hidden layers of the CNN include a series of hidden layers as described below, such as convolutional layers, non-linear layers, pooling layers (for downsampling), and fully connected layers. In other examples, the neural network 500 can represent any other neural network or deep learning network, such as autoencoders, deep belief networks (DBNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), etc.

[0100] In Figure 5In a non-limiting example, neural network 500 includes an input layer 503 that can receive one or more input data sets. The input data can be any type of data (e.g., image data, video data, network parameter data, user data, etc.). Neural network 500 can include hidden layers 504A through 504N (collectively referred to hereinafter as "hidden layer 504"). Hidden layer 504 can include a number n of hidden layers, where n is an integer greater than or equal to one. The number n of hidden layers can include many layers required for the desired processing result and / or presentation intent. In one illustrative example, any one of the hidden layers 504 can include data representing one or more of the data provided at the input layer 503. Neural network 500 also includes an output layer 506 that provides an output generated by the processing performed by the hidden layer 504. Output layer 506 can provide output data based on the input data.

[0101] In Figure 5 an example, neural network 500 is a multi-layer neural network of interconnected nodes. Each node can represent a piece of information. The information associated with these nodes is shared between different layers, and each layer retains the information when processing the information. Information can be exchanged between the nodes through node-to-node interconnections between the various layers. The nodes of the input layer 503 can activate a set of nodes in the hidden layer 504A. For example, as shown, each input node of the input layer 503 is connected to each node of the hidden layer 504A. The nodes of the hidden layer 504A can transform the information by applying an activation function to the information of each input node. Then, the information derived from the transformation can be passed to the nodes of the next hidden layer (e.g., 504B) and can activate those nodes, which can perform their own specified functions. Example functions include convolution, upsampling, data transformation, pooling, and / or any other suitable function. The output of the hidden layer (e.g., 504B) can then activate the nodes of the next hidden layer (e.g., 504N), and so on. The output of the last hidden layer can activate one or more nodes of the output layer 506, at which point the output is provided. In some cases, although the nodes in neural network 500 (e.g., nodes 508A, 508B, 508C) are shown as having multiple output lines, a node can have a single output and all the lines shown as output from the node can represent the same output value.

[0102] In some cases, each node or the interconnections between the nodes can have weights, which are a set of parameters derived from training the neural network 500. For example, the interconnections between the nodes can represent a piece of information learned about the interconnected nodes. The interconnections can have numerical weights that can be tuned (e.g., based on a training data set) to allow the neural network 500 to adapt to the input and be able to learn as it processes more data.

[0103] The neural network 500 can be pre-trained to process the features of data from the input layer 503 using different hidden layers 504, so as to provide an output through the output layer 506. For example, in some cases, the neural network 500 can use a training process called backpropagation to adjust the weights of the nodes. Backpropagation can include forward pass, loss function, backward pass, and weight update. The forward pass, loss function, backward pass, and parameter update can be performed for one training iteration. This process can be repeated for each training data set for a certain number of iterations until the weights of these layers are accurately tuned (e.g., meet a configurable threshold determined based on experimental and / or empirical studies).

[0104] An increasing number of ML (e.g., AI) algorithms (e.g., models) are being incorporated into a variety of technologies including wireless communication standards. Figure 6 FIG. is a block diagram illustrating an ML engine 600 according to aspects of the present disclosure. As an example, one or more devices in a wireless system can include the ML engine 600. In some cases, the ML engine 600 can be similar to the neural network 500. In one example, the ML engine 600 includes three parts: an input 602 to the ML engine 600, the ML engine, and an output 604 from the ML engine 600. The input 602 to the ML engine 600 can be data that the ML engine 600 can use to make predictions or otherwise operate on it. As an example, the ML engine 600 configured to select an RF beam can take data on current RF conditions, location information, network load, etc. as the input 602. As another example, data related to data packets transmitted to a UE along with historical packet data can be used as the input 602 to the ML engine 600 configured to predict the discontinuous reception (DRX) schedule of the UE. In some cases, the output 604 can be a prediction or other information generated by the ML engine 600, and the output 604 can be used to configure wireless devices, adjust settings, parameters, operating modes, etc. Continuing with the previous example, the ML engine 600 configured to select an RF beam can output an RF beam or a set of RF beams that can be used for the output 604. Similarly, the ML engine 600 configured to predict the DRX schedule of the UE can output the DRX schedule of the UE.

[0105] In another example, the ML engine 600 can be an encoder for compressing channel state information (e.g., channel state information (CSI) or channel state feedback (CSF)) determined by a UE to generate a representation (e.g., latent representation) of control information. In another example, the ML engine 600 can be a decoder used by a network entity (e.g., a base station) to decode a representation (e.g., latent representation) of control information (e.g., CSI) generated by a UE.

[0106] Figure 7FIG. is an illustration showing an example of a network 750 including a UE 751 and a base station (e.g., a gNB or a part of a gNB, such as a CU, DU, RU, etc., of a gNB having a split architecture). As Figure 7 shown, a downlink channel estimate 752 (e.g., CSI or CSF) is provided to an encoder 754 of the UE 751. The CSI encoder 754 encodes the CSI and the UE 751 transmits the encoded CSI (e.g., a potential representation of the CSI as a potential message 761, such as an eigenvector representing the CSI) to a receiving antenna 762 of the base station 753 via a data or control channel 756 through a radio or air interface 760 using an antenna 758. In some cases, the UE 751 may transmit a potential message representing the CSI as the potential message 761. As pointed out above, the CSI encoder 754 may replace the PMI codebook used to convert CSI report bits into PMI codewords.

[0107] The encoded CSI or potential message 761 is provided to a CSI decoder 767 of the base station 753 via a data or control channel 764 that can decode the encoded CSI to generate a reconstructed downlink channel estimate 768 (or a reconstructed CSI). In some cases, the base station 753 may then determine a precoding matrix, a modulation and coding scheme (MCS), and / or a rank associated with one or more antennas of the base station. Based on the precoding matrix, MCS, and / or rank, the base station 753 may determine the configuration of control resources (e.g., via a physical downlink control channel (PDCCH)) or data resources (e.g., via a physical downlink shared channel (PDSCH)).

[0108] The decoder output may be several different data structures. For example, the decoder output may be a downlink channel matrix (H), a transmit covariance matrix, a downlink precoder (V), an interference covariance matrix (R nn ) or the original whitened downlink channel. In some examples, when the encoder input is (H) (channel matrix), the decoder output may be H (channel matrix) or V (eigenvector) or SV (eigenvalue times V). When the encoder input is the eigenvector V, the decoder output may also be the eigenvector V. When the encoder input is the inferred covariance matrix R nn , the output may also be the interference covariance matrix R nn . The H or V values may correspond to the original channel or to the channel pre-whitened by the UE 751 based on its demodulation filter.

[0109] Conventional CSI-RS occupies one resource element per resource block per antenna port. When there are many antennas or transmit radio distribution units (TxRUs) equipped at the base station, the current transmission method for CSI-RS may require a large amount of overhead. Scenarios that require a large amount of overhead may be particularly applicable to holographic multiple-input multiple-output (MIMO) scenarios and reflective (or reconfigurable) intelligent surfaces (RIS). RIS or intelligent reflecting surface (IRS) is an emerging transmission technology for use in wireless communication. They can reconfigure the wireless propagation environment via software-controlled reflection. RIS can be applied to networks such as 6G networks and achieve seamless connection in wireless communication systems and intelligent software-based control of the environment. Since RIS reflection beamforming prediction requires perfect / imperfect channel knowledge, channel estimation is a key aspect for predicting the RIS interaction matrix. In one context, RIS can be combined with machine learning (ML) techniques that are particularly powerful in providing channel estimation.

[0110] Figure 8 Several methods for providing low-density reference signals are shown, such as the resource block comb method 800 where the resource block 802 can be occupied by the reference signal or does not span different antenna ports 804. The frame can represent a uniform or non-uniform pattern. In one aspect, the method reduces the density of the use in the frequency domain by, for example, making only the data in certain frequencies with other frequencies not have any reference signal in the resource block comb method 800. In another aspect, the pattern can be a random selection 810 of the antenna port 814 and the resource block (RB) or resource element (RE) 812. In each RB, the method is to select several antennas to track the CSI-RS. In one aspect, there may be Nt ports multiplexed on L REs per RB via a learned coverage code 820. The coverage code can multiplex Nt ports on L REs per RB. In some cases, Nt can be 32, where L can be 8 or 4. In other aspects, Nt can be a high value (e.g., 1024) and L can be a low value (e.g., 32 or 16).

[0111] Figure 9 FIG. 920 illustrates another aspect of the present disclosure, where channel state feedback under low-density CSI-RS can be implemented in several ways. Generally, for CSI-RS and CSI feedback, there are two functions. One function is to perform channel estimation with the CSI-RS signal as the input. The second function is to take the channel estimation as the input and compress the channel estimation into a potential message, and then report the potential message as the CSI feedback. Machine learning models that perform these different functions are usually designed and trained separately. Figure 9The illustrated diagram 920 shows a method with separate networks. Under low-density CSI-RS, when there are two separate functions as described above, errors can propagate through the system. The system will determine whether to perform channel estimation and CSI feedback jointly. A single neural network can more directly provide CSI feedback based on the input, which can reduce the likelihood of introducing errors. Figure 9 The model 900 in

[0112] In one example, the combined machine learning model 900 of UE 902 and base station 908 implements a single neural network (NN) that jointly performs the above two different functions related to channel estimation. In one aspect, on the UE side, UE 902 uses the CSI-RS received signal as input 904 to NN 903, and the output is the latent message 906. In some cases, the latent message is quantized into a bit sequence called the latency bit 906. The latency bit 906 can be provided (e.g., sent) as the latent message 914 to the base station 908, where the bits of the received latent message 914 are represented by bits 910. At the base station 908, NN 903 reconstructs the CSI (shown as data W' 912) from the bits 910 of the received latent message 914. The Y input (e.g., CSI-RS) and the output data V or W' 912 can be the output or CSI for all ports and all frequency resources.

[0113] The neural network is shown in the Figure 9 diagram 920 of a method representing two separate functions or machine learning models across UE 922 and base station 934. The first part or model includes the channel estimation neural network 923 and the second part or model includes the channel state feedback neural network 925. In one aspect, at UE 922, input 924 is received, and the channel estimation neural network 923 receives the Y input data and generates H data 926, which can be a channel matrix as pointed out above. UE 922 generates W data 928 from the H data 926 via singular value decomposition (SVD) 929. Across the parts of UE 922 and base station 934, the channel state feedback neural network 923 can receive as Figure 9The shown W (which may be represented as V in some cases) is taken as input and generates a latency bit 930 or a potential message as the reconstructed eigenvector. The latency bit 930 or the potential message is sent 932 to the base station 934 and is represented as input bits 936 representing CSI for all channel resources. The channel state feedback neural network 923 (e.g., the decoder of the neural network) processes the bits 936 and reconstructs the CSI 936 (represented as W'), which can then be output by the channel state feedback neural network 923. The method shown in illustration 920 can make the channel estimation process a bottleneck and limit the performance of the system. Whether the UE should report CSI for some resource blocks and / or sub-band resources in the resource block and / or sub-band resources or for all resources is the focus of this disclosure. The question is whether the UE can recover the channel for all resources to obtain complete resources and compress the data again. As pointed out above, some resources may have poor channel estimation quality and thus do not provide benefits for CSI reporting.

[0114] As also previously pointed out, systems and techniques are described herein for providing machine learning methods for channel state feedback that remove the bottlenecks experienced by using two separate neural networks for channel state feedback, as Figure 9 shown in illustration 920. The systems and techniques can also be applied to other types of control information other than CSI.

[0115] Figure 10 Illustrate the process of generating channel state information from CSI-RS. The shown process 1000 spans the UE 1002 and the gNB or base station 1016 using a single NN. From the perspective of the UE 1002, the solution includes receiving the CSI-RS 1001 transmission on a first set of frequency units (e.g., RBs or sub-bands) that are a partial set of all frequency units and / or on a first set of antenna ports out of a total number of antenna ports. The first set of frequency units may include downsampled CSI-RS (in an RB comb manner or in a non-uniform RB pattern as Figure 8 shown). The feature Y CSIRS 1004 represents the reception of the CSI-RS 1001 at the UE 1002.

[0116] The UE 1002 can generate CSI (as an intermediate output) V CSIRS for a second set of frequency units and / or a second set of antenna ports via the NN block 1006 and based on Y s1 1008 to facilitate CSI generation or reconstruction on a third set of frequency units and / or a third set of antenna ports. Then, a potential message 1010 can be generated from V s1 and reported to the gNB or base station 1016. In one aspect, it can be directly from Y CSIRThe value generates a potential message 1010, quantizes it into bits, and sends 1012 the potential message to the gNB or base station 1016. The second set of frequency units and / or the second set of antenna ports may be determined at least in part based on at least one of the first set of frequency units and / or the first set of antenna ports, the third set of frequency units and / or the third set of antenna ports, the received signal power, the interference level, the channel estimation accuracy of the received CSI-RS, or based on the gNB configuration.

[0117] The gNB or base station 1016 receives the potential bits 1014 and generates, via the NN block, a CSI feedback V' for the second set of frequency units and / or the second set of antenna ports s1 1018, whereby the last block of the NN generates or reconstructs CSI (V') for the third set of frequency units and / or the third set of antenna ports 1020. V' represents an estimate of the complete CSI for all resources. In one aspect, the third set of frequency units and / or the third set of antenna ports covers the complete resources and ports. In another aspect, the third set of frequency units and / or the third set of antenna ports may be configured in advance or dynamically by the network or alternatively may depend at least in part on the second set of frequency units and / or the second set of antenna ports. The UE 1002 sends a CSI report to the base station 1016.

[0118] Different options may be used to construct or select one or more of the first set of frequency units and antenna ports and the second set of frequency units and antenna ports. In one example, the second set of frequency units or the second set of antenna ports may be selected at least in part based on at least one of the first set of frequency units or the first set of antenna ports, at least one of the third set of frequency units or the third set of antenna ports, the received signal power, the interference level, the channel estimation accuracy of the CSI reference signal, or based on configuration information received from the base station. Generally, the third set of frequency units or the third set of antenna ports is the complete set of resources.

[0119] There may also be a relationship between a first set of frequency units and / or a first set of antenna ports and other sets. In a first option, a second set of frequency units may be equal to the first set of frequency units, or the second set of frequency units may represent a subband having at least one RB containing CSI-RS. For example, considering that the subband size is equal to 4 RBs, the frequency density may be equal to 0.125 and CSI-RS may be configured on RBs {7, 15, 23, 31, 39, 47} out of a total of 48 RBs corresponding to subbands {1, 3, 5, 7, 9, 11}. In one aspect, there will be CSI reporting in every two subbands. Note that in one example, RBs (such as RB 16, 32, 40, etc.) "close" to the selected RBs ({7, 15, 23, 31, 39, 47}) for transmitting CSI-RS may also be considered to have good quality, and thus the reported subbands may include subbands {1, 3, 4, 5, 7, 8, 9, 10, 11}.

[0120] In another option, a second set of frequency units may be equal to the first set of frequency units plus additional frequency units, where the additional units are configured by the network or determined based on predefined rules. For example, in one aspect, CSI-RS may be configured on RBs {7, 15, 23, 31, 39, 47} (and they correspond to subbands {1, 3, 5, 7, 9, 11}) where the edge subbands {0, 11} are always selected and also on a second set of subbands {0, 1, 3, 5, 7, 9, 11} even if subband 0 does not contain any CSI-RS. Different modes may be used, and these different modes may change the number of subbands used and whether that number includes one or more edge subbands. The average squared generalized cosine similarity (SGCS) may be used to evaluate CSI compression and reconstruction accuracy. The SGCS value may depend on the number of selected SBs and in some cases rise or fall depending on whether an edge subband is selected.

[0121] Another option may include that the second set of frequency units is on subbands having high channel estimation (CE) quality as determined by UE 1002 across RBs / subbands. In one aspect, UE 1002 may report the selection of the second set of frequency units based on high CE quality. In one example, high CE quality may be determined by one or more of high reference signal received power (RSRP), or interference measurement level, or signal-to-interference plus noise ratio (i.e., SINR), or the position of the corresponding RB or subband close to CSI-RS. In such a case, the RB or subband close to CSI-RS may have high CE quality.

[0122] In some cases, depending on the structure of the channel, different subband numbers may give good CE quality for the channel. For example, there may be different patterns and different usages of subbands. In one case, the pattern may include edge subbands and may include a total of six subbands. The selected subbands may be: {0, 2, 4, 7, 9, 11}. In another example, the pattern may include edge subbands and a total of eight subbands, and may thus include: {0, 2, 3, 4, 7, 8, 9, 11}. Another pattern may include edge subbands and a total of ten subbands with the following pattern: {0, 1, 2, 3, 4, 7, 8, 9, 10, 11}. Another example of a pattern may include all 12 subbands.

[0123] On the other hand, the process may include generating CSI feedback for a second set of frequency units and / or a second set of antenna ports to facilitate CSI generation or reconstruction on a third set of frequency units and / or a third set of antenna ports.

[0124] From the perspective of the gNB or base station 1016, the machine learning channel state feedback under the low-density method may include the gNB or base station 1016 transmitting CSI-RS on a first set of frequency units and / or a first set of antenna ports. The gNB or base station 1016 receives CSI feedback for a second set of frequency units and / or a second set of antenna ports. The gNB or base station 1016 may generate a final CSI V' for a third set of frequency units and / or a third set of antenna ports. In one aspect, the third set of frequency units and / or the third set of antenna ports represent all frequency resources (e.g., the complete subbands of a bandwidth part (BWP)) and all antenna ports. Alternatively, the third set of frequency units and / or the third set of antenna ports depend at least in part on the second set and may represent less than all frequency resources.

[0125] Figure 11 Illustrate a set of alternative methods 1100 for determining frequency units and antenna ports related to generating channel state information. In a first example, a first set of frequency units 1102 and antenna ports 1106 may be selected by the base station via Tx-RB selection on which CSI-RS is transmitted. For example, on each resource block (RB) 1104, CSI-RS may be transmitted only via specifically selected antenna ports 1106. The filled blocks represent the corresponding RBs on the corresponding antenna ports for transmitting CSI-RS. In one aspect, the second set of frequency units and antenna ports may be equal to the first set of frequency units and antenna ports. In other words, on each RB 1104, CSI is generated and reported only for the transmitted ports.

[0126] In another example, a second set of frequency units 1108 and antenna ports 1112 may be equal to the first set of frequency units and antenna ports plus additional ports on each RB 1110. The additional ports may be predefined, configured by the network, or reported by the UE. One shading of the ports shown in the matrix or the second set of frequency units 1108 may represent the first set of frequency units and antenna ports and another shading may represent the additional ports. Two sets of ports are reported.

[0127] In another example, a third set of frequency units 1114 and antenna ports 1118 may be equal to the complete set of ports or selected ports (but these ports are common to all selected RBs 1116) plus other selected RBs. In one example, the selected RBs and ports may be predefined, configured by the network, or reported by the UE. Even if there is no CSI-RS on the ports of the RB, Figure 11 the shading associated with port 1118 in may also represent the reported ports. In one aspect, when CSI-RS is reported by the UE, the UE determines it based on the channel estimation quality.

[0128] In one aspect related to signaling or providing information about sets of frequency units and antenna ports, the first set of frequency units and antenna ports may be configured via a CSI-RS resource pattern. In another aspect, the third set of frequency units and antenna ports may be configured by CSI reports related to subband configuration and the number of antenna ports in the CSI report configuration. In another aspect, the third set of frequency units and antenna ports may be derived from the second set of frequency units and antenna ports. The second set of frequency units and antenna ports may be predefined, configured via dedicated signaling (radio resource control (RRC) or MAC control element (MACCE)), or reported by the UE in uplink control information (UCI) together with CSI reports.

[0129] In some cases, the first set of frequency units and the first set of antenna ports are selected by the base station and / or determined by the UE, such as using the following techniques. For example, the base station may use one or more of the following techniques to select the first set of frequency units and the first set of antenna ports. The UE may be made aware of how to select the first set of frequency units and the first set of antenna ports (e.g., based on techniques or rules specified in standards such as 3GPP standards). In one example, the base station may partition the frequency units into groups, where consecutive 2N RBs (e.g., N = 1, 2, etc.) are considered in the same group. For the first half of the RBs in each group, the base station may determine or select L ports out of all Nt ports. For the second half of the RBs in each group, the base station may determine or select another L ports out of Nt - L ports other than the L ports selected for the first half of the RBs. For example, if L = 4 and Nt = 32, then ports {0, 5, 19, 28} are selected for the first half of the RBs, and then another 4 ports are selected from the complementary set, i.e., {1, 2, 3, 4, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 20, 21, 22, 23, 24, 25, 26, 27, 29, 30, 31}, for the second half of the RBs. A possible result for the second half of the RBs may be ports {9, 14, 24, 31}. In an illustrative example, to select L ports for each half of the RBs, the base station may select L ports based on a random selection with a seed determined by the cell ID, BWP ID, or UE ID. In another illustrative example, the base station may select L ports for each half of the RBs by always selecting the first available L indices. An illustrative example of an algorithm is shown below, where N f is the total number of RBs, and B is the number of RBs with CSI-RS present, represents the set of all port indices (here we assume the indices start from 1 to Nt), and Ω b ,b = 1, …, B represents the set of ports selected for the b-th RB with CSI-RS present. Additionally, N may be set to 1 (N = 1), meaning every two RBs belong to one group.

[0130]

[0131] Figure 12 is a block diagram 1200 illustrating the encoder and decoder functions related to generating channel state information. Figure 10 The machine learning model across the UE 1002 and the base station 1016 shown in the process 1000 of Figure 12 and Figure 13 can be designed and trained in various ways as illustrated. As Figure 12As shown, the UE-side model on the UE encoder 1202 can be trained, for example, in a first aspect related to partial sub-band recovery and compression. The first transformer module 1201 (which can be an artificial intelligence / machine learning model (AI / ML) or a non-AI / ML model) can be used to generate CSI, which in one aspect is the V' of the second set of frequency units and antenna ports. p Or a pre-decoder value, where the input Y is the CSI-RS on the first set of frequency units and antenna ports. The second transformer module 1203 (AI model) can be used to compress the CSI on the second set of frequency units into the latent space.

[0132] The gNB decoder 1204 can include parts of its ML model. The parts of the model can be designed and trained in various ways. In one aspect, the first module 1205 (AI / ML model) can be used to reconstruct the CSI on the second set of frequency units and antenna ports, plus the second module 1207 (AI / ML model) can be used to generate the CSI on the complete set of frequency units and antenna ports with the second set as the input. Figure 12 The first aspect shown recovers V' on the second set of frequency units and antenna ports p' (downlink pre-decoder).

[0133] As discussed above regarding Figure 5 and the training process for machine learning models, Figure 12 and Figure 13 the loss functions disclosed in are used to determine what values to backpropagate through the network during training. The loss function 1206 for the AI / ML model can involve the weighted sum of at least two of the following: the loss between the third set of CSI (e.g., the final output at the gNB decoder 1204) and its true value (V); the second set of CSI (i.e., the output of the first transformer module 1201) generated at the UE encoder 1202 (V' p ) and its true value (V p ); and the reconstructed second set of CSI (i.e., the output V' of the first module 1205 at the gNB decoder 1204) p' and its true value (V p ). Among these values, "p" represents the partial sub-band.

[0134] Figure 12 It is also shown that the UE channel estimation neural network 1211 on the UE 1208 generates an output H' p matrix, which is processed into a pre-decoder value V' through singular value decomposition 1210. p, these values are provided to the UE encoder 1212. Module 1213 (AI model) can be used to compress V' on the second set of frequency units and antenna ports into the latent space. The loss function 1209 is shown as the normalized mean square error (NMSE) (H' p , H p , H p ). The gNB decoder 1214 may include a first module 1215 (AI / ML model) that can be used to reconstruct V' p' (CSI on the second set of resources), and a second module 1217 (AI / ML model) that can be used to generate CSI (V') on the complete set of frequency units and antenna ports or, in one aspect, to recover H (downlink channel matrix) on the second set of frequency units or antenna ports. The loss function 1216 is also shown in Figure 12 .

[0135] In another aspect, a single module can be used to reconstruct the CSI of the complete set of frequency units and antenna ports. Figure 13 is a block diagram illustrating the encoder and decoder functions 1300 related to generating channel state information. Figure 13 The top part of involves complete subband recovery and extraction. In one aspect, a first module 1302 (AI / ML model or non-AI / ML model) can be used to recover the channel or pre-coder on the complete subband and ports, where the input Y is the CSI-RS on the first set of frequency units and antenna ports. A second module 1304 can be used to extract the CSI (downlink channel matrix H estimate or H est ) on the second set of frequency units and antenna ports from the complete set. A third module 1303 (of the UE encoder 1306) can be used to generate a pre-coder on the second set of frequency units and / or antenna ports with the channel estimate of the second set of frequency units and / or antenna ports as the input. The output of the third module 1303 can be V' p and its true value (V p ). A fourth module 1305 (of the UE encoder 1306), which can be a machine learning or AI model (e.g., neural network model) in some cases, can be used to compress the CSI (or output V' P ) of the third module 1303 on the second set of frequency units and antenna ports into the latent space. The first module 1302 at the UE can be jointly trained or separately trained with other modules.

[0136] At the gNB decoder 1308, the first module 1307 can perform decompression of the received latent message and provide V' to the second module 1309 that performs complete subband estimation and outputs V p' . For one aspect, it is shown in Figure 13An example loss function 1310 is shown.

[0137] Figure 13 Another aspect is also shown where V on a second set of frequency units and antenna ports is found through singular value decomposition. In one aspect, a first module 1312 performs full channel estimation on the Y input and a second module 1314 performs singular value decomposition (SVD), and a third module 1316 extracts a partial subband V' from its output. p This partial subband is then compressed into the latent space by a fourth module 1317 on a UE encoder 1318. A gNB decoder 1320 performs decompression via a first module 1319 to generate V'. p' And performs full subband estimation via a second module 1321 to generate V. In Figure 13 a loss function 1322 is shown by way of example.

[0138] Figure 14 FIG. 1400 is a diagram illustrating additional encoder and decoder functions related to generating channel state information. Figure 12 The UE encoder 1202 of is shown in more detail. A first transformer module 1201 can recover a portion of the CSI with a corresponding CLS (classification) token. The CLS token corresponds to a subband in the second set. The Y input can be processed at a linear layer 1402 and its output is provided to a second transformer module 1203 including 6 transformer blocks 1404 to generate CSI for a second set of frequency units (6 subbands in one aspect). The second transformer module 1203 compresses the CSI with corresponding positional embeddings to store the positions of the reported subbands. Position (pos) information is added to the output of 1404 to store the position information of the second set of frequency units from the full frequency units. Then, the output of the positional embedding is passed to a transformer layer 1406, the output of which is provided to a flattening layer 1408, the output of which is provided to a linear layer or singular value decomposition 1410 to generate a Z output. A transformer in one example is a deep learning model that employs a self-attention mechanism and differentially weights the importance of each part of the input data. However, unlike a recurrent neural network (RNN), a transformer processes the entire input simultaneously. The attention mechanism provides context for any position in the input sequence. For example, if the input data is a natural language sentence, the transformer does not have to process one word at a time. This approach allows for more parallelization to be achieved than with an RNN and thus reduces the training time. Although these modules are described as transformer-based neural networks, other types of neural networks can also be implemented. Figure 14 The example shown uses 6 TF blocks in the first module and 6 TFs in the second module, and other numbers of TF blocks can be considered in other examples.

[0139] The gNB decoder 1204 includes a first transformer module 1205 having a linear weight layer 1420. Then the location information is added and its output is provided to a 3x transformer layer as the second transformer layer 1422, which restores the CSI on a partial sub-band (e.g., 6 sub-bands). The first transformer module 1205 restores the CSI on a partial sub-band (e.g., 6 sub-bands out of 12 sub-bands). Location embeddings are added to record the corresponding locations of the sub-bands and can then be interpolated to 12 sub-bands in the second TF module using the location embeddings of all 12 sub-bands. The second transformer module 1207 includes a 3x transformer layer as the first transformer layer 1424 and a linear layer 1426, which interpolates these values to 12 sub-bands using the location embeddings of all 12 sub-bands, including the padding required to fill from 6 sub-bands to 12 sub-bands. The output is V' representing the CSI for all resources. The location embeddings in both the first transformer layer 1424 and the second transformer layer 1422 are used to store the locations of the corresponding sets of sub-bands representing a partial set of all resources. The number of sub-bands mentioned above is only exemplary and other numbers of sub-bands can also be used. Figure 14 The example shown uses 3 transformer blocks in the first transformer layer 1424 and 3 transformer blocks in the second transformer layer 1422, and other numbers of transformer blocks can be considered in other examples.

[0140] Figure 15 FIG. 1500 is a diagram illustrating additional encoder and decoder functions related to generating channel state information. FIG. 1500 illustrates a transformer-based neural network that compresses the partial sub-band CSI (V estimate) with corresponding location embedding data to store the locations of the reported sub-bands. The UE encoder 1212 may include a compression module 1213 for compressing V estimate (V est ). The compression module 1213 may process Vest through a linear layer 1502 to provide location embeddings representing the locations of the sub-bands of the second set, which are then processed by a 6x transformer 1504, the output of which is processed by a flattening layer 1506, and the output of which is processed by a linear layer 1508 to produce a Z output. The gNB decoder in this figure may be the same as Figure 14 the gNB decoder shown.

[0141] Figure 16 FIG. 1600 is a flowchart of an example process 1600 for providing wireless communication at a user equipment (UE). Process 1600 may be performed by a UE (e.g., Figure 7 UE 751 or Figure 10 UE 1002) or other components or systems of the UE or any device. The operations of process 1600 may be implemented on one or more processors (e.g., Figure 24Software components that are executed and run on a processor 2410 or other processor). Additionally, the UE may be enabled to transmit and receive signals in process 1600, for example, via one or more antennas and / or one or more transceivers (e.g., a wireless transceiver).

[0142] At block 1602, process 1600 may include (e.g., by Figure 7 UE 751 or Figure 10 UE 1002) receiving a channel state information (CSI) reference signal (e.g., Figure 10 CSI-RS1001) from a base station (or its components) on at least one of a first set of frequency units or a first set of antenna ports. In one aspect, at least one of the first set of frequency units or the first set of antenna ports includes less than all available frequency units or less than all available antenna ports. In some aspects, receiving the CSI reference signal may further include receiving the CSI reference signal on the first set of frequency units and via the first set of antenna ports.

[0143] At block 1604, process 1600 may include (e.g., by Figure 7 UE 751 or Figure 10 UE 1002) generating CSI based on the CSI reference signal.

[0144] At block 1606, process 1600 may include (e.g., by Figure 7 UE 751 or Figure 10 UE 1002) transmitting information associated with the CSI from the UE to the base station on at least one of a second set of frequency units or a second set of antenna ports for use (e.g., by Figure 7 base station 753 or Figure 10 gNB or base station 1016) in reconstructing the CSI on at least one of a third set of frequency units or a third set of antenna ports, where at least one of the second set of frequency units or the second set of antenna ports includes less than all available frequency units or less than all available antenna ports. In some aspects, the first set of frequency units and the second set of frequency units are the same set of frequency units.

[0145] In some aspects, the techniques described herein relate to a method where at least one of the second set of frequency units or the second set of antenna ports is determined at least in part based on at least one of the first set of frequency units or the first set of antenna ports, at least one of the third set of frequency units or the third set of antenna ports, received signal power, interference level, channel estimation accuracy of the CSI reference signal, or based on configuration information received from the base station.

[0146] In some aspects, the third set of frequency units may include all available frequency units and the third set of antenna ports includes all available antenna ports. In some aspects, transmitting information associated with CSI may include transmitting information associated with CSI on a second set of frequency units and using a second set of antenna ports. In some aspects, the second set of frequency units may include a subband having at least one resource block that includes a CSI reference signal.

[0147] In some aspects, the second set of frequency units may include a first set of frequency units and at least one additional frequency unit. The at least one additional frequency unit may be configured by the network or determined based on predefined rules. The second set of frequency units may be in a subband associated with high channel estimation quality in at least one of a set of resource blocks or a set of subbands. The high channel estimation quality may be determined by one or more of high reference signal received power, or interference and / or noise measurements, or a resource block / subband close to the CSI reference signal.

[0148] In some aspects, the first set of frequency units and the first set of antenna ports may be the same as the second set of frequency units and the second set of antenna ports.

[0149] In some aspects, the second set of frequency units and the second set of antenna ports may include the first set of frequency units and the first set of antenna ports and at least one additional antenna port. The at least one additional antenna port may be at least one of the following: predefined, based on configuration information received from a base station, or reported by a user equipment.

[0150] The second set of antenna ports may include all available antenna ports or a selected set of antenna ports. In some aspects, the second set of antenna ports may include a selected set of antenna ports, and the selected set of antenna ports may be predefined or based on configuration information received from a base station.

[0151] In some aspects, the first set of frequency units, the second set of frequency units, and the third set of frequency units are different sets of frequency units. In other aspects, the first set of antenna ports, the second set of antenna ports, and the third set of frequency units are different sets of antenna ports. The third set of frequency units may include all available frequency units.

[0152] In some aspects, at least the first set of frequency units or the first set of antenna ports may be configured based on a resource pattern of a CSI reference signal.

[0153] In some aspects, at least the third set of frequency cells or the third set of antenna ports is at least one of configured based on the CSI reporting subband configuration or dependent on at least one of the second set of frequency cells or the second set of antenna ports.

[0154] In some aspects, at least the second set of frequency units or the second set of antenna ports may be at least one of predefined, based on configuration information received from a base station, or sent in a CSI report including information associated with the CSI.

[0155] In some aspects, the information associated with the CSI includes a latent representation of the CSI generated using a machine learning encoder.

[0156] In some aspects, the techniques described herein relate to an apparatus for wireless communication (e.g., such as Figure 7 UE 751 or Figure 10 UE 1002), the apparatus comprising: at least one memory; and at least one processor, the at least one processor coupled to the at least one memory and configured to: receive a signal from a base station (e.g., such as Figure 7 Base station 753 or Figure 10 The gNB or base station 1016) receives a channel state information (CSI) reference signal, wherein a first set of frequency units or at least one of a first set of antenna ports includes less than all available frequency units or less than at least one of all available antenna ports; generates CSI based on the CSI reference signal; and sends information associated with the CSI to the base station on at least one of a second set of frequency units or a second set of antenna ports for use in reconstructing the CSI on a third set of frequency units or at least one of a third set of antenna ports, wherein the second set of frequency units or at least one of the second set of antenna ports includes less than all available frequency units or less than at least one of all available antenna ports.

[0157] In some aspects, the technology described herein relates to an apparatus (e.g., such as Figure 7 UE 751 or Figure 10 UE 1002), wherein at least one of the second set of frequency units or the second set of antenna ports is determined at least in part based on the first set of frequency units or at least one of the first set of antenna ports, the third set of frequency units or at least one of the third set of antenna ports, received signal power, interference level, channel estimation accuracy of CSI reference signal, or based on configuration information received from a base station.

[0158] In some aspects, the techniques described herein relate to an apparatus (e.g., a UE 751 such as Figure 7 or a UE 1002 such as Figure 10 ) where a third set of frequency units includes all available frequency units and a third set of antenna ports includes all available antenna ports.

[0159] In some aspects, the techniques described herein relate to an apparatus (e.g., a UE 751 such as Figure 7 or a UE 1002 such as Figure 10 ) where receiving CSI reference signals also includes receiving CSI reference signals on a first set of frequency units and via a first set of antenna ports.

[0160] In some aspects, the techniques described herein relate to an apparatus (e.g., a UE 751 such as Figure 7 or a UE 1002 such as Figure 10 ) where transmitting information associated with CSI includes transmitting information associated with CSI on a second set of frequency units and using a second set of antenna ports.

[0161] In some aspects, the techniques described herein relate to an apparatus (e.g., a UE 751 such as Figure 7 or a UE 1002 such as Figure 10 ) where the first set of frequency units and the second set of frequency units are the same set of frequency units.

[0162] In some aspects, the techniques described herein relate to an apparatus (e.g., a UE 751 such as Figure 7 or a UE 1002 such as Figure 10 ) where the second set of frequency units includes a subband having at least one resource block containing CSI reference signals.

[0163] In some aspects, the techniques described herein relate to an apparatus (e.g., a UE 751 such as Figure 7 or a UE 1002 such as Figure 10 ) where the second set of frequency units includes the first set of frequency units and at least one additional frequency unit.

[0164] In some aspects, the techniques described herein relate to an apparatus (e.g., a UE 751 such as Figure 7 or a UE 1002 such as Figure 10 ) where the at least one additional frequency unit is configured by the network or is determined based on predefined rules.

[0165] In some aspects, the techniques described herein relate to an apparatus where a second set of frequency units is in a sub-band associated with high channel estimation quality in at least one of a set of resource blocks or a set of sub-bands.

[0166] In some aspects, the techniques described herein relate to an apparatus (e.g., a UE 751 such as Figure 7 or a UE 1002 such as Figure 10 ), where high channel estimation quality is determined by one or more of high reference signal received power, or interference and / or noise measurements, or resource blocks / sub-bands close to a CSI reference signal.

[0167] In some aspects, the techniques described herein relate to an apparatus (e.g., a UE 751 such as Figure 7 or a UE 1002 such as Figure 10 ), where a first set of frequency units and a first set of antenna ports are the same as a second set of frequency units and a second set of antenna ports.

[0168] In some aspects, the techniques described herein relate to an apparatus (e.g., a UE 751 such as Figure 7 or a UE 1002 such as Figure 10 ), where the second set of frequency units and the second set of antenna ports include the first set of frequency units and the first set of antenna ports and at least one additional antenna port.

[0169] In some aspects, the techniques described herein relate to an apparatus (e.g., a UE 751 such as Figure 7 or a UE 1002 such as Figure 10 ), where at least one additional antenna port is at least one of the following: predefined, based on configuration information received from a base station, or reported by a user equipment.

[0170] In some aspects, the techniques described herein relate to an apparatus (e.g., a UE 751 such as Figure 7 or a UE 1002 such as Figure 10 ), where the second set of antenna ports includes all available antenna ports or a selected set of antenna ports.

[0171] In some aspects, the techniques described herein relate to an apparatus (e.g., a UE 751 such as Figure 7 or a UE 1002 such as Figure 10 ), where the second set of antenna ports includes a selected set of antenna ports, and where the selected set of antenna ports is predefined or based on configuration information received from a base station.

[0172] In some aspects, the techniques described herein relate to an apparatus (e.g., such asFigure 7 the UE 751 or Figure 10 the UE 1002), wherein the first set of frequency units, the second set of frequency units, and the third set of frequency units are different sets of frequency units.

[0173] In some aspects, the techniques described herein relate to an apparatus (e.g., such as Figure 7 the UE 751 or Figure 10 the UE 1002), wherein the first set of antenna ports, the second set of antenna ports, and the third set of frequency units are different sets of antenna ports.

[0174] In some aspects, the techniques described herein relate to an apparatus (e.g., such as Figure 7 the UE 751 or Figure 10 the UE 1002), wherein the third set of frequency units includes all available frequency units.

[0175] In some aspects, the techniques described herein relate to an apparatus (e.g., such as Figure 7 the UE 751 or Figure 10 the UE 1002), wherein at least the first set of frequency units or the first set of antenna ports is configured based on a resource pattern of a CSI reference signal.

[0176] In some aspects, the techniques described herein relate to an apparatus (e.g., such as Figure 7 the UE 751 or Figure 10 the UE 1002), wherein at least the third set of frequency units or the third set of antenna ports is at least one of the following: is configured based on a CSI reporting subband configuration or depends on at least one of the second set of frequency units or the second set of antenna ports.

[0177] In some aspects, the techniques described herein relate to an apparatus (e.g., such as Figure 7 the UE 751 or Figure 10 the UE 1002), wherein at least the second set of frequency units or the second set of antenna ports is at least one of the following: is predefined, based on configuration information received from a base station, or sent in a CSI report including information associated with CSI.

[0178] In some aspects, the techniques described herein relate to an apparatus (e.g., such as Figure 7 the UE 751 or Figure 10 the UE 1002), wherein the information associated with CSI includes a latent representation of CSI generated using a machine learning encoder.

[0179] In some aspects, the techniques described herein relate to a non-transitory computer-readable storage medium (e.g., a memory 2415 such as Figure 24 ), the non-transitory computer-readable storage medium including instructions stored thereon that, when executed by at least one processor, cause the at least one processor to: receive a channel state information (CSI) reference signal from a base station (e.g., a base station 753 such as Figure 7 or a gNB or base station 1016 such as Figure 10 ) on at least one of a first set of frequency units or a first set of antenna ports, wherein at least one of the first set of frequency units or the first set of antenna ports includes less than all available frequency units or less than all available antenna ports; generate CSI based on the CSI reference signal; and transmit information associated with the CSI on at least one of a second set of frequency units or a second set of antenna ports to the base station for use in reconstructing the CSI on at least one of a third set of frequency units or a third set of antenna ports, wherein at least one of the second set of frequency units or the second set of antenna ports includes less than all available frequency units or less than all available antenna ports.

[0180] In some aspects, the techniques described herein relate to an apparatus for wireless communication (e.g., a base station 753 such as Figure 7 or a gNB or base station 1016 such as Figure 10 ), the apparatus including one or more components for performing operations that include: receiving a channel state information (CSI) reference signal from a base station on at least one of a first set of frequency units or a first set of antenna ports, wherein at least one of the first set of frequency units or the first set of antenna ports includes less than all available frequency units or less than all available antenna ports; generating CSI based on the CSI reference signal; and transmitting information associated with the CSI on at least one of a second set of frequency units or a second set of antenna ports to the base station for use in reconstructing the CSI on at least one of a third set of frequency units or a third set of antenna ports, wherein at least one of the second set of frequency units or the second set of antenna ports includes less than all available frequency units or less than all available antenna ports.

[0181] Figure 17 Illustrates from the perspective of a base station (e.g., by a base station 753 such as Figure 7 or a base station 1016 such as Figure 10Flowchart of an example of a method or process 1700 for wireless communication by a gNB or base station 1016). Process 1700 may be performed by a base station, gNB, or by components or systems of any device. Operations of process 1700 may be implemented as software components executed and run on one or more processors (e.g., Figure 24 processor 2410 of or other processors). Additionally, transmission and reception of signals by the UE in process 1700 may be enabled, for example, by one or more antennas and / or one or more transceivers (e.g., wireless transceivers).

[0182] At block 1702, process 1700 may include (e.g., by Figure 7 base station 753 of or Figure 10 gNB or base station 1016) transmitting a channel state information (CSI) reference signal to a user equipment (UE) on at least one of a first set of frequency units or a first set of antenna ports, wherein at least one of the first set of frequency units or the first set of antenna ports includes less than all available frequency units or less than all available antenna ports. At block 1704, process 1700 may include (e.g., by Figure 7 base station 753 of or Figure 10 gNB or base station 1016) receiving information associated with CSI from the UE on at least one of a second set of frequency units or a second set of antenna ports, wherein at least one of the second set of frequency units or the second set of antenna ports includes less than all available frequency units or less than all available antenna ports. At block 1706, the method may include (e.g., by Figure 7 base station 753 of or Figure 10 gNB or base station 1016) generating a reconstructed CSI for at least one of a third set of frequency units or a third set of antenna ports based on the information associated with CSI.

[0183] An apparatus for wireless communication (e.g., Figure 7 base station 753 of or Figure 10The gNB or base station 1016) may include: at least one memory; and at least one processor coupled to the at least one memory and configured to: transmit a channel state information (CSI) reference signal to a user equipment (UE) on at least one of a first set of frequency units or a first set of antenna ports, wherein at least one of the first set of frequency units or the first set of antenna ports includes less than all available frequency units or less than all available antenna ports; receive information associated with CSI from the UE on at least one of a second set of frequency units or a second set of antenna ports, wherein at least one of the second set of frequency units or the second set of antenna ports includes less than all available frequency units or less than all available antenna ports; and generate a reconstructed CSI for at least one of a third set of frequency units or a third set of antenna ports based on the information associated with CSI.

[0184] In some aspects, the techniques described herein relate to a non-transitory computer-readable storage medium (e.g., Figure 24 the memories 2415, 2420, 2425), the non-transitory computer-readable storage medium including instructions stored thereon that, when executed by at least one processor, cause the at least one processor to: transmit a channel state information (CSI) reference signal to a user equipment (UE) on at least one of a first set of frequency units or a first set of antenna ports, wherein at least one of the first set of frequency units or the first set of antenna ports includes less than all available frequency units or less than all available antenna ports; receive information associated with CSI from the UE on at least one of a second set of frequency units or a second set of antenna ports, wherein at least one of the second set of frequency units or the second set of antenna ports includes less than all available frequency units or less than all available antenna ports; and generate a reconstructed CSI for at least one of a third set of frequency units or a third set of antenna ports based on the information associated with CSI.

[0185] In some aspects, the techniques described herein relate to an apparatus for (e.g., by Figure 7 the base station 753 or Figure 10Apparatus for wireless communication of a gNB or base station 1016), the apparatus including one or more components for performing operations including: transmitting a channel state information (CSI) reference signal to a user equipment (UE) on at least one of a first set of frequency units or a first set of antenna ports, wherein at least one of the first set of frequency units or the first set of antenna ports includes less than all available frequency units or less than all available antenna ports; receiving information associated with CSI from the UE on at least one of a second set of frequency units or a second set of antenna ports, wherein at least one of the second set of frequency units or the second set of antenna ports includes less than all available frequency units or less than all available antenna ports; and generating a reconstructed CSI for at least one of a third set of frequency units or a third set of antenna ports based on the information associated with CSI.

[0186] In some examples, the processes described herein (e.g., process 1600, 1700, and / or other processes described herein) may be performed by a computing device or apparatus (e.g., a UE user equipment or a BS or base station). For example, process 1700 may be performed by Figure 24 configured to implement Figure 10 system 2400 of components of UE 1002 or gNB or base station 1016.

[0187] In some aspects, a deep learning-based joint channel estimation and CSI feedback system with low-density pilot signals for OFDM-MIMO systems is disclosed. Downlink channel state information (CSI) plays an important role in improving throughput in large-scale MIMO systems. Downlink CSI is measured by a UE via a channel state information reference signal (CSI-RS) and reported back to a BS via a feedback link. In current systems, CSI is represented by a standardized codebook to reduce feedback overhead. With the advancement of machine learning (ML), the idea of using ML-based algorithms to outperform codebook-based CSF in improving CSI feedback (CSF) performance has been explored. However, most studies mainly consider CSF with ideal or high-quality CSI, which is challenging to obtain in practical systems because the method typically requires high-density CSI-RS or high CSI-RS transmission power. The following figures and examples introduce a framework for CSF with low-density pilots. The framework consists of two enhancements. First, separate channel estimation (CE) and CSF functions may suffer from error propagation of low-quality CE, so the concept includes jointly implementing CE and CSF. Second, the CE quality is different for different parts of CSI. This disclosure introduces partial CSI reporting and leaves the interpolation task to the BS. Simulation results show that joint CE and CSF are better in some cases and partial CSI reporting is beneficial for low-quality channel estimation cases.

[0188] In an actual system, the UE estimates the downlink CSI by measuring the channel state information reference signal (CSI-RS) sent by the BS. To obtain high-accuracy CSI, denser CSI-RS can be used but at the cost of higher resource consumption, which may be plausible in a system where the BS deploys hundreds or thousands of antennas (e.g., 6G system). Therefore, obtaining high-quality CSI feedback (CSF) performance with a lower CSI-RS overhead can provide benefits. A joint design of CSI estimation and CSI feedback under low-density CSI-RS is introduced.

[0189] Consider a single-user downlink MIMO system with N t transmitting antennas at the BS and N r receiving antennas at the UE. The system employs an OFDM waveform and operates on N c subcarriers. The received signal on the nth subcarrier is represented by Equation (1):

[0190]

[0191] where is the signal received from N r antennas, is the channel on the nth subcarrier for all N r receiving antennas, represents the channel on the nth subcarrier of the ith receiving antenna, is the multiplexing weight for multiplexing N t antenna elements on the nth subcarrier, x is the transmitted pilot, and is the received additive noise.

[0192] Vectorizing Equation (1) results in:

[0193]

[0194] where is the identity matrix, and

[0195] The method includes splitting N c subcarriers into N f subcarrier blocks, each block containing P subcarriers, and assuming that the channels within each block are frequency-flat. For example, for the ith group, the result is:

[0196] h i,1 = h i,2 = … = h i,P ,

[0197] where is the channel on the j-th subcarrier in the i-th block. Thus, only the block-level channel needs to be considered. For simplicity of notation, this method uses to represent the vectorized channel of the i-th block. Assume that the pilots occupy L ≤ P subcarriers in each block, and the received signal of the i-th block is:

[0198] y i = W i h i + z i

[0199] where where

[0200]

[0201] and is the received signal on the j-th subcarrier in the block, is the multiplication weight for the L subcarriers of block i and is the additive noise. Let the channels on all N f blocks be:

[0202]

[0203] and assume that pilots are transmitted on N Y ≤ Nf blocks, and then the channels on N Y blocks are

[0204] H y = SH, (4)

[0205] where is a selection matrix consisting of only 1s and 0s. The selection matrix S has only one 1 in each row, which selects N Y rows of H, and thus Then the received signal on N Y blocks is:

[0206] y = Wh Y x + z (5)

[0207] where where

[0208]

[0209] In one aspect, is the multiplexing weight for N Y blocks and is written as

[0210]

[0211] And The channel estimation task can be written as:

[0212]

[0213] Subject to y = Wh Y x + z (6)

[0214] When replacing h with equation (4) Y And the result is: when

[0215]

[0216] Subject to y = WS I hx + z (7)

[0217] Where

[0218]

[0219] In one aspect, the method may include defining the pilot overhead ratio as:

[0220]

[0221] Then low-density pilots mean ∝ << 1, e.g., ∝ = 0.125. Consider where pilot overhead reduction is achieved by using N Y << N f sub-carrier blocks, and keeping L = N t , i.e., only the case of frequency reduction. Without loss of generality, the method may use And problem (7) can be written as:

[0222]

[0223] Subject to y = S I hx + z (9)

[0224] In some aspects, improvements are made with respect to how CSI feedback is accomplished. Figure 18 Illustrations include a block diagram of a UE / BS system 1800 of UE 1802 that implements a first operation fen(·)1804 on the received input V to generate z q and BS1806 that implements a second operation fen(·)1808 on z q to generate V BS Consider implicit CSI feedback where the pre-coder is fed back to BS1806. Before introducing the calculation of the pre-coder, the method first splits the channel of (3) into N B groups, where each group contains S sub-carrier blocks, and rewrites the channel of (3) as

[0225]

[0226] where is the channel on the i-th subcarrier block and is the channel on the j-th subcarrier block of the i-th group. The pre-coder is calculated group by group through the following process:

[0227] (1) Calculate the average of the spatial correlations between the transmit antennas over S subcarrier blocks for each group. For the i-th group, the average Tx spatial correlation is calculated as

[0228]

[0229] (2) Second, calculate the left subspace of R denoted as i There can be at most N r layers, where is the pre-coder of the r-th layer.

[0230] (3) Finally, aggregate the pre-coders of different layers for all N B groups.

[0231] In some aspects, the method only considers the first layer. For simplicity of notation, can be used to represent the layer-1 pre-coder for the i-th group, and the resulting pre-coder for all N B groups is:

[0232]

[0233] Denoting the operation of pre-coder calculation by p(·), the above process can be summarized as:

[0234] V = p(H).

[0235] In practice, the UE can only obtain the pre-coder as:

[0236]

[0237] where is the estimated channel obtained by solving (7).

[0238] For CSF, the UE encodes en by using the operation f :

[0239]

[0240] where z q is the bit stream fed back to the BS. The BS encodes z by f de (·)q Decode and obtain

[0241]

[0242] wherein is the pre - decoder recovered by BS1806.

[0243] If BS1806 uses low density, the channel estimation may be inaccurate and thus cause error propagation when the feedback is inaccurate. In some aspects, the problem of CSF with low - density pilots can be shown first, and then the disclosed solution can be presented.

[0244] Next, CSF under low - density pilots is discussed. First, the properties of the estimated pre - decoder V under low - density CSI - RS are discussed together with the problem of CSF with V and the disclosed solution.

[0245] By first solving problem (9) using a linear minimum mean - square error (LMMSE) channel estimator, the properties of the estimated pre - decoder for V under low - density pilots can be shown. Using the notation in (9), the LMMSE weights are derived as:

[0246]

[0247] where is the channel covariance matrix across all transmit antennas, receive antennas, and sub - carrier blocks, and cr 2 is the variance of the additive Gaussian noise. Then the channel is estimated as:

[0248]

[0249] And further, the method obtains:

[0250]

[0251] To show how well it is estimated, the method uses the squared generalized cosine similarity (SGCS) as a metric, which is calculated as:

[0252]

[0253] Since makes it such that if then and

[0254] Figure 19 shows having (∝, N f , N BChart 1900 of the SGCS performance of an estimated precoder = (0.125, 48, 12). Pilots are transmitted on every 1 / ∝ = 8 subcarrier blocks, and since there are S = 4 subcarrier blocks in each group, in one aspect, the method has observations only on 6 out of 12 groups. Let G be the set of groups on which pilots are transmitted and G' be the set of groups on which pilots are not transmitted, and then for Figure 19 the evaluation setting, one can have G = {1, 3, 5, 7, 9, 11} and G' = {2, 4, 6, 8, 10, 12}. By denote the estimated precoders for the groups in G and by denote the estimated precoders for the groups in G'. It can be observed from Figure 19 that the SGCS performance of is generally better than that of The performance gap between

[0255] and Figure 18 is very large for some groups. For example, the SGCS loss of group 12 relative to group 1 is 32.7% at SNR = 0 dB and 33.6% at SNR = 30 dB. The method indicates that interpolating / extrapolating the precoders for the groups in G' is more challenging.

[0255] There may also be additional problems and solutions. To show how inaccurate estimation of the precoder affects the CSF performance, one method evaluates the CSF performance by using the autoencoder structure in Figure 18 , where the transformer (TF) structure can be selected as f en (·)1804 and f de (·)1808. The performance metric for the CSF is the average SGCS calculated as follows:

[0256]

[0257] Example results are shown in Figure 20 of chart 2000 showing the average SGCS performance of the CSF. From Figure 20 , it can be seen that the performance degradation compared to V is clear, being 26.8% at SNR = 0 dB and 11.1% at SNR = 30 dB. Based on the observations discussed above, the method can improve the CSF performance in two aspects.

[0258] The first example improvement can relate to the channel estimation performance. Figure 19The channel estimation results shown are obtained by an LMMSE estimator that can be improved by deep learning-based techniques. Different from the work that only focuses on improving CE performance, the method disclosed in this paper optimizes both CE and CSF performance by training a joint CE and CSF neural network.

[0259] Figure 21 Illustrate the improved UE / BS system 2100. Another example improvement is that UE 2102 only feeds back a partial pre-decoder. Specifically, let Ω be the set of N groups that contain the pre-decoders selected by UE 2102 to be fed back under P ≤ N B and the result can be:

[0260] And where represents the operation to be estimated from y . When receiving z q , BS2108 performs two operations:

[0261] And where is decoded on the BS side and f de-ce (·)2112 represents the operation of estimating all N B pre-decoders on the BS side. Based on the observations in Figure 18 , the CE performance of the groups in G' is worse than that of the groups in G, and in one aspect, UE 2102 can select Ω = G and only feed back and leave the interpolation / extrapolation of the pre-decoders in G' to BS2108. In one way, the error propagation caused by inaccurate can be reduced.

[0262] Therefore, a joint CE and CSF framework or UE / BS system 2100 for joint CE and CSF with low-density pilots as shown in Figure 21 is proposed. As described above, UE 2102 receives the input y and the first UE operation f em-ce (y)2104 to generate The second UE operation 2106 processes to generate z q , which is transmitted to the BS2108. BS2108 includes the first BS operation f de (z q 02110 to obtain from z qGenerate which is then operated on by a second BS operation and processed by 2112 to generate

[0263] Figure 22 An example neural network (NN) structure is illustrated that has two cases 2200 for different decoders. A first BS-side decoder 2202 and a second BS-side decoder 2230 are illustrated for implementing the proposed framework. Figure 23 An NN structure for a UE-side encoder 2300 is illustrated. The UE-side encoder 2300 takes the received signal y as input and then compresses the signal y into z q . There are two subnets on the UE side, namely, as Figure 23 shown f en (·) and f en-ce . The NN structures for these two subnets are described. The structures for the two subnets are adapted from a vision transformer (ViT).

[0264] The UE-side encoder 2300 includes subnet-1 2316: The function of subnet-1 2316 is to map to E with size Np x d 1 . The concept of a CLS token is used as E 1 . The CLS token is concatenated to the input image tokens and sent to the transformer for attention calculation. The CLS token is considered a learned representation of the image and is used to calculate the classification score. In the design, the CLS token is used to be learned to represent Y 2322. In particular, the method first reshapes y into and splits into NyN r chips 2324, where each chip has size 1x 2N t . The method then obtains NyN r tokens by projecting each chip into a d-dimensional latent vector via a linear layer 2320. Finally, N P d-dimensional CLS tokens are concatenated to the NyN r tokens and sent to L 1 transformers 2318. The L 1 transformers 2318 can be represented by a transformer module 2326 that includes one or more of a first normalization component, a multi-head attention module, an addition component, a second normalization component, and a multi-layer perceptron with an additional addition component. The attention of the multi-head attention component in the transformer module 2326 can be calculated across all (N P )+N Y N r tokens, but only corresponding to NP N CLS tokens P A number of latent vectors are maintained at the output of subnet-1 2316. The output can also be provided to a linear projection 2314, whose output is converted to a complex number via a component 2312 that converts the data to a complex value.

[0265] The UE-side encoder 2300 includes subnet-2 2302. The function of subnet-2 2302 is to compress E 1 into an M-dimensional 1D vector z, which is then quantized to z q The data from subnet-1 2316 can be provided to a transformer 2310, whose output data is further processed by a flattening component 2308, and the output of this flattening component is processed by a linear projection component 2306 that produces z. In some aspects, vector quantization (VQ) 2304 can be used. VQ 2304 maps z to a codebook consisting of K vectors ; and it can be obtained that:

[0266]

[0267] The codebook C is learned together with the encoder and decoder.

[0268] Figure 22 Illustrate two example BS-side NN structures for two cases 2200. In the first case, the first BS-side decoder 2202 is applicable when Np < nB. The first BS-side decoder 2202 takes z q as input and recovers the NB pre-decoder The first BS-side decoder 2202 consists of two subnets, namely the first subnet shown as subnet-1 2214f Figure 22 (·) and the second subnet called subnet-22206f de . The first subnet maps the 1D vector z to de-ce and subnet-2 takes D1 and recovers the NB pre-decoder These two subnets also use a transformer structure, such as the first transformer 2216 in subnet-1 2214 and the second transformer 2210 in subnet-2 2206. Subnet-1 2214 includes a flattening layer 2218, a linear layer 1820, and an L3 transformer as the first transformer 2216, and it has a structure similar to that of subnet-2 2302 of the encoder in

[0269] . Figure 23 Subnet-2 2206 may include an L4 transformer as the second transformer 2210 and a linear layer 2208.

[0270] ​

[0271] As pointed out above, for N P <N B in case 1, this means that the column dimension of D1 is less than the column dimension of. In one aspect, the method is to concatenate (N P —N B ) d-dimensional CLS tokens to D1 and transmit them to the L4 transformer serving as the second transformer 2210. The output of the transformer is then projected to and the recovered pre-decoder is obtained by organizing the values in D2 into complex values using the linear projector 2222 and the component 2224 for conversion to complex numbers.

[0272] The second BS-side decoder 2230 is applicable to N P = N B in case 2, which means that the column dimension of D1 is the same as the column dimension of. In one aspect, the method is to not use any CLS tokens and directly transmit D1 into subnet-2 2234. The second BS-side decoder 2230 includes subnet 1 2340, linear projection 2346, reshaping flattening component 2344, and transformer 2342. The second BS-side decoder 2230 also includes subnet-2 2334, which has a transformer 2338, a linear layer 2336, and a component 2332 for converting values to complex numbers.

[0273] For Figure 23 in case 1, a method can be applied to jointly train the encoder and decoder by using the following loss function:

[0274]

[0275] where Θ represents all the parameters to be learned in the encoder and decoder, ∝≥0 and β≥0 are hyperparameters, is the MSE loss between V^ and V calculated as follows:

[0276]

[0277] Here, represents the pre-decoder over N P groups, is obtained by first projecting to and then organizing the values therein into complex values, and is obtained in the same way as . VQ loss is calculated as:

[0278]

[0279] where \(sg[\cdot]\) represents the stop-gradient operator that applies only the forward computation to its input but applies zero partial derivatives in backpropagation, represents the codebook vectors to be learned, and \(\Upsilon\) is a hyperparameter.

[0280] For Case 2, the method is to jointly train the encoder and decoder by using the following loss function:

[0281]

[0282] Figure 24 is a diagram illustrating an example of a system for implementing certain aspects of the present technology. Specifically, Figure 24 illustrates an example of a computing system 2400, which can be any computing device that constitutes an internal computing system, a remote computing system, a camera, or any layer thereof, where the components of the system communicate with each other using a connection 2405. The connection 2405 can be a physical connection using a bus or a direct connection into a processor 2410, such as in a chipset architecture. The connection 2405 can also be a virtual connection, a networking connection, or a logical connection.

[0283] In some aspects, the computing system 2400 is a distributed system, where the functions described in the present disclosure can be distributed within one data center, multiple data centers, a peer-to-peer network, etc. In some aspects, one or more of the described system components represent many such components that each perform some or all of the functions that the component is described for. In some aspects, the components can be physical or virtual devices.

[0284] The example system 2400 includes at least one processing unit (CPU or processor) 2410 and a connection 2405 that communicatively couples various system components including a system memory 2415 (such as a read-only memory (ROM) 2420 and a random access memory (RAM) 2425) to the processor 2410. The computing system 2400 can include a cache 2412 that is directly connected to, in close proximity to, or integrated as part of the processor 2410 for high-speed memory.

[0285] The processor 2410 may include any general-purpose processor and hardware services or software services (such as services 2432, 2434, and 2436 stored in the storage device 2430 and configured to control the processor 2410), as well as a dedicated processor in which software instructions are incorporated into the actual processor design. The processor 2410 can be substantially a completely independent computing system that includes multiple cores or processors, buses, memory controllers, caches, etc. The multi-core processor can be symmetric or asymmetric.

[0286] To enable user interaction, the computing system 2400 includes an input device 2445 that can represent any number of input mechanisms, such as a microphone for voice, a touch-sensitive screen for gesture or graphical input, a keyboard, a mouse, motion input, voice, etc. The computing system 2400 may also include an output device 2435 that can be one or more of a plurality of output mechanisms. In some cases, a multimode system may enable the user to provide multiple types of input / output to communicate with the computing system 2400.

[0287] The computing system 2400 may include a communication interface 2440 that generally can govern and manage user input and system output. The communication interface can execute or facilitate receiving and / or sending wired or wireless communications using wired and / or wireless transceivers, including using audio jack / plug, microphone jack / plug, universal serial bus (USB) port / plug, Apple TM Lightning TM port / plug, Ethernet port / plug, fiber optic port / plug, dedicated wired port / plug, 3G, 4G, 5G, and / or other cellular data network wireless signal transfer, Bluetooth TM wireless signal transfer, Bluetooth TM low-power (BLE) wireless signal transfer, iBeacon TMThose communications of wireless signal transfer, radio frequency identification (RFID) wireless signal transfer, near field communication (NFC) wireless signal transfer, dedicated short range communication (DSRC) wireless signal transfer, 802.11 Wi-Fi wireless signal transfer, wireless local area network (WLAN) signal transfer, visible light communication (VLC), worldwide interoperability for microwave access (WiMAX), infrared (IR) communication wireless signal transfer, public switched telephone network (PSTN) signal transfer, integrated services digital network (ISDN) signal transfer, ad hoc network signal transfer, radio wave signal transfer, microwave signal transfer, infrared signal transfer, visible light signal transfer, ultraviolet light signal transfer, wireless signal transfer along the electromagnetic spectrum, or some combination thereof. The communication interface 2440 may also include one or more global navigation satellite system (GNSS) receivers or transceivers for determining the location of the computing system 2400 based on one or more signals received from one or more satellites associated with one or more GNSS systems. GNSS systems include, but are not limited to, the Global Positioning System (GPS) of the United States, the Global Navigation Satellite System (GLONASS) of Russia, the Beidou Navigation Satellite System (BDS) of China, and Galileo GNSS of Europe. There are no restrictions on operating on any particular hardware arrangement, and thus the underlying features here can be easily replaced to obtain improved hardware or firmware arrangements as they are developed.

[0288] The storage device 2430 can be a non-volatile and / or non-transitory and / or computer-readable memory device and can be a hard disk or other type of computer-readable medium that can store data accessible by a computer, such as cassette tapes, flash memory cards, solid state memory devices, digital versatile discs, cartridges, floppy disks, hard disks, magnetic tapes, magnetic strips / magnetic stripes, any other magnetic storage medium, flash memory, memristor memory, any other solid state memory, compact disc read-only memory (CD-ROM) optical discs, rewritable compact discs (CD) optical discs, digital video disc (DVD) optical discs, Blu-ray disc (BDD) optical discs, holographic optical discs, another optical medium, secure digital (SD) cards, micro secure digital (microSD) cards, Memory Cards, smart card chips, EMV chips, subscriber identity module (SIM) cards, mini / micro / nano / pico SIM cards, another integrated circuit (IC) chip / card, random access memory (RAM), static RAM (SRAM), dynamic RAM (DRAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash EPROM (FLASHEPROM), cache memory (e.g., level 1 (L1) cache, level 2 (L2) cache, level 3 (L3) cache, level 4 (L4) cache, level 5 (L5) cache, other (L#) cache), resistive random access memory (RRAM / ReRAM), phase change memory (PCM), spin transfer torque RAM (STT-RAM), another memory chip or cartridge and / or combinations thereof.

[0289] The storage device 2430 may include software services, servers, services, etc., which, when the code defining such software is executed by the processor 2410, cause the system to perform functions. In some aspects, the hardware services that perform specific functions may include software components stored in a computer-readable medium connected to the necessary hardware components (such as the processor 2410, connection 2405, output device 2435, etc.) for the functions. The term "computer-readable medium" includes, but is not limited to, portable or non-portable storage devices, optical storage devices, and various other media capable of storing, containing, or carrying instructions and / or data. The computer-readable medium may include non-transitory media in which data can be stored and which do not include carrier waves and / or transient electronic signals propagated wirelessly or via a wired connection. Examples of non-transitory media may include, but are not limited to, magnetic disks or tapes, optical storage media (such as compact discs (CDs) or digital versatile discs (DVDs)), flash memory, memory, or memory devices. The computer-readable medium may have code and / or machine-executable instructions stored thereon, which may represent procedures, functions, subroutines, programs, routines, subroutines, modules, software packages, classes, or any combination of instructions, data structures, or program statements. By passing and / or receiving information, data, arguments, parameters, or memory contents, a code segment may be coupled to another code segment or hardware circuit. The information, arguments, parameters, data, etc. may be passed, forwarded, or sent via any suitable means, including memory sharing, message passing, token passing, network sending, etc.

[0290] Figure 19 is a diagram illustrating an example of a neural network architecture of a base station for implementing certain aspects of the present technology; and

[0291] Figure 20 It is a diagram illustrating an example of a neural network architecture of a UE for implementing certain aspects of the present technology.

[0292] Specific details are provided in the above description to provide a thorough understanding of the aspects and examples provided herein, but those skilled in the art will recognize that this application is not limited thereto. Thus, although the exemplary aspects of this application have been described in detail herein, it is to be understood that the various inventive concepts can be implemented and adopted in other various ways, and the appended claims are not to be construed as including such variations unless limited by the prior art. The various features and aspects of the above applications can be used alone or in combination. In addition, without departing from the broader scope of the specification, the aspects can be utilized in any number of environments and applications beyond those described herein. Therefore, the specification and drawings should be regarded as illustrative rather than restrictive. For illustrative purposes, the methods are described in a particular order. It should be understood that in alternative aspects, the methods can be performed in a different order than that described.

[0293] For clarity of explanation, in some cases, the present technology may be presented as including separate functional blocks that include devices, device components, steps, or routines in a method embodied in software or a combination of hardware and software. Additional components other than those shown in the drawings and / or described herein may be used. For example, circuits, systems, networks, processes, and other components may be shown as components in block diagram form to avoid obscuring these aspects in unnecessary detail. In other cases, well-known circuits, processes, algorithms, structures, and techniques may be shown without unnecessary detail to avoid obscuring the aspects.

[0294] In addition, those skilled in the art should understand that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the aspects disclosed herein can be implemented as electronic hardware, computer software, or a combination of both. To clearly illustrate this interchangeability of hardware and software, the various illustrative components, blocks, modules, circuits, and steps have been described generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and the design constraints imposed on the overall system. Those skilled in the art can implement the described functionality in different ways for each particular application, but such specific implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

[0295] Each aspect described above may be described as a process or method that is depicted as a flowchart, process diagram, data flow diagram, structure diagram, or block diagram. Although a flowchart may describe operations as a sequential process, many of the operations in the operations may be performed in parallel or concurrently. In addition, the order of the operations may be rearranged. The process is terminated when the operations of the process are completed, but the process may have additional steps not included in the figures. The process may correspond to a method, function, procedure, subroutine, subprogram, etc. When the process corresponds to a function, the termination of the process may correspond to the function returning to the calling function or the main function.

[0296] The processes and methods according to the above examples may be implemented using computer-executable instructions stored or otherwise available from a computer-readable medium. Such instructions may include, for example, instructions and data that cause or otherwise configure a general-purpose computer, special-purpose computer, or processing device to perform a certain function or group of functions. Portions of the computer resources used may be accessed through a network. The computer-executable instructions may be, for example, binary, intermediate format instructions such as assembly language, firmware, source code. Examples of computer-readable media that may be used to store instructions, the information used, and / or the information created during the methods according to the described examples include magnetic or optical disks, flash memory, USB devices with non-volatile memory, networked storage devices, etc.

[0297] In some aspects, computer-readable storage devices, media, and memories may include wires or wireless signals containing bitstreams, etc. However, when mentioned, non-transitory computer-readable storage media expressly exclude media such as energy, carrier signals, electromagnetic waves, and signals themselves.

[0298] Those skilled in the art will understand that information and signals may be represented using any of a variety of different technologies and methods. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be referred to throughout the above description may in some cases be represented, in part depending on the specific application, in part depending on the desired design, in part depending on the corresponding technology, etc., by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or optical particles, or any combination thereof.

[0299] The various illustrative logical blocks, modules, and circuits described in connection with the aspects disclosed herein may be implemented or performed using hardware, software, firmware, middleware, microcode, hardware description languages, or any combination thereof, and may take on any of a variety of form factors. When implemented in software, firmware, middleware, or microcode, the program code or code segments (e.g., a computer program product) for performing the necessary tasks may be stored in a computer-readable or machine-readable medium. The processor may perform the necessary tasks. Examples of form factors include: laptop computers, smart phones, mobile phones, tablet devices, or other small form factor personal computers, personal digital assistants, rack-mounted devices, stand-alone devices, etc. The functionality described herein may also be embodied in a peripheral device or an add-in card. By further example, such functionality may also be implemented on a circuit board among different chips or different processes executing on a single device.

[0300] Instructions, the medium for conveying such instructions, the computing resources for executing them, and other structures for supporting such computing resources are example components for providing the functionality described in this disclosure.

[0301] The techniques described herein may also be implemented in electronic hardware, computer software, firmware, or any combination thereof. Such techniques may be implemented in any of a variety of devices, such as a general purpose computer, a wireless communication device handset, or an integrated circuit device with multiple uses, including applications in a wireless communication device handset and other devices. Any features described as modules or components may be implemented together in an integrated logic device or separately as discrete but interoperable logic devices. If implemented in software, the techniques may be at least partially implemented by a computer-readable data storage medium including program code that includes instructions that, when executed, perform one or more of the methods, algorithms, and / or operations described above. The computer-readable data storage medium may form part of a computer program product, which may include packaging material. The computer-readable medium may include a memory or data storage medium, such as random access memory (RAM) (such as synchronous dynamic random access memory (SDRAM)), read only memory (ROM), non-volatile random access memory (NVRAM), electrically erasable programmable read only memory (EEPROM), flash memory, magnetic or optical data storage media, etc. Additionally or alternatively, the techniques may be at least partially implemented by a computer-readable communication medium that carries or conveys program code in the form of instructions or data structures and that can be accessed, read, and / or executed by a computer, such as a propagated signal or wave.

[0302] The program code can be executed by a processor, which can include one or more processors, such as one or more digital signal processors (DSPs), general-purpose microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other equivalent integrated or discrete logic circuits. Such processors can be configured to perform any of the techniques described in this disclosure. A general-purpose processor can be a microprocessor; but in an alternative, the processor can be any conventional processor, controller, microcontroller, or state machine. The processor can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. Thus, the term "processor" as used herein can refer to any of the foregoing structures, any combination of the foregoing structures, or any other structure or device suitable for implementing the techniques described herein.

[0303] Those of ordinary skill in the art should understand that, without departing from the scope of this specification, the less-than ("<") and greater-than (">") symbols or terms used herein can be replaced with less-than-or-equal-to ("≤") and greater-than-or-equal-to ("≥") symbols, respectively.

[0304] In cases where a component is described as "configured to" perform certain operations, such configuration can be implemented, for example, by designing electronic circuits or other hardware to perform the operations, by programming programmable electronic circuits (e.g., a microprocessor or other suitable electronic circuit) to perform the operations, or any combination thereof.

[0305] The phrase "coupled to" or "communicatively coupled to" means that any component is directly or indirectly physically connected to another component, and / or any component is directly or indirectly in communication with another component (e.g., connected to the other component via a wired or wireless connection and / or other suitable communication interface).

[0306] Claim language that recites "at least one" of a set and / or "one or more" of a set, or other language that indicates that one member of the set or multiple members of the set (in any combination) satisfy the claim. For example, claim language that recites "at least one of A and B" or "at least one of A or B" means A, B, or A and B. In another example, claim language that recites "at least one of A, B, and C" or "at least one of A, B, or C" means A, B, C, or A and B, or A and C, or B and C, A and B and C, or any repetition is information or data (e.g., A and A, B and B, C and C, A and A and B, etc.), or any other ordering, repetition, or combination of A, B, and C. The language "at least one" of a set and / or "one or more" of a set does not limit the set to the items listed in the set. For example, claim language that recites "at least one of A and B" or "at least one of A or B" can mean A, B, or A and B, and can additionally include items not listed in the set of A and B. The phrases "at least one" and "one or more" are used interchangeably herein.

[0307] Claim language that recites "at least one processor, the at least one processor being configured to", "at least one processor being configured to", "one or more processors, the one or more processors being configured to", "one or more processors being configured to", etc., or other language that indicates that one processor or multiple processors (in any combination) can perform the associated operations. For example, claim language that recites "at least one processor, the at least one processor being configured to: X, Y, and Z" means that a single processor can be used to perform operations X, Y, and Z; or multiple processors are each assigned a task of a particular subset of operations X, Y, and Z such that the multiple processors together perform X, Y, and Z; or a group of multiple processors work together to perform operations X, Y, and Z. In another example, claim language that recites "at least one processor, the at least one processor being configured to: X, Y, and Z" can mean that any single processor can perform at least a subset of operations X, Y, and Z.

[0308] When referring to one or more elements that perform functions (e.g., the steps of a method), one element may perform all the functions, or more than one element may jointly perform these functions. When more than one element jointly performs these functions, each function does not need to be performed by each of these elements (e.g., different functions may be performed by different elements), and / or each function does not need to be fully performed by only one element (e.g., different elements may perform different sub-functions of a function). Similarly, when referring to one or more elements that are configured to cause another element (e.g., a device) to perform functions, one element may be configured to cause another element to perform all the functions, or more than one element may jointly be configured to cause another element to perform these functions.

[0309] When referring to an entity (e.g., any entity or device described herein) that performs functions or is configured to perform functions (e.g., the steps of a method), the entity may be configured to cause one or more elements (individually or jointly) to perform these functions. One or more components of the entity may include at least one memory, at least one processor, at least one communication interface, another component configured to perform one or more (or all) of these functions, and / or any combination thereof. When referring to an entity that performs functions, the entity may be configured to cause one component to perform all the functions, or to cause more than one component to jointly perform these functions. When the entity is configured to cause more than one component to jointly perform these functions, each function does not need to be performed by each of these components (e.g., different functions may be performed by different components), and / or each function does not need to be fully performed by only one component (e.g., different components may perform different sub-functions of a function).

[0310] The various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the examples disclosed herein may be implemented as electronic hardware, computer software, firmware, or combinations thereof. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

[0311] The techniques described herein may also be implemented in electronic hardware, computer software, firmware, or any combination thereof. Such techniques may be implemented in any of a variety of devices, such as a general-purpose computer, a wireless communication device handheld, or an integrated circuit device with multiple uses, including applications in wireless communication device handhelds and other devices. Any features described as modules or components may be implemented together in an integrated logic device or separately as discrete but interoperable logic devices. If implemented in software, the techniques may be at least partially realized by a computer-readable data storage medium including program code that includes instructions that, when executed, perform one or more of the above-described methods, algorithms, and / or operations. The computer-readable data storage medium may form part of a computer program product, which may include packaging materials. The computer-readable medium may include a memory or data storage medium, such as random access memory (RAM) (such as synchronous dynamic random access memory (SDRAM)), read-only memory (ROM), non-volatile random access memory (NVRAM), electrically erasable programmable read-only memory (EEPROM), flash memory, magnetic or optical data storage media, and the like. Additionally or alternatively, the techniques may be at least partially realized by a computer-readable communication medium that carries or conveys program code in the form of instructions or data structures that can be accessed, read, and / or executed by a computer, such as a propagated signal or wave.

[0312] The program code may be executed by a processor, which may include one or more processors, such as one or more digital signal processors (DSPs), general-purpose microprocessors, application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other equivalent integrated or discrete logic circuits. Such processors may be configured to perform any of the techniques described in this disclosure. A general-purpose processor may be a microprocessor; but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. Thus, as used herein, the term "processor" may refer to any of the foregoing structures, any combination of the foregoing structures, or any other structure or apparatus suitable for implementing the techniques described herein.

[0313] Exemplary aspects of the present disclosure include:

[0314] Aspect 1. A method for wireless communication at a user equipment (UE), the method comprising: receiving a channel state information (CSI) reference signal from a base station on at least one of a first set of frequency units or a first set of antenna ports, wherein at least one of the first set of frequency units or the first set of antenna ports includes less than all available frequency units or less than all available antenna ports; generating CSI based on the CSI reference signal; and transmitting information associated with the CSI from the UE to the base station on at least one of a second set of frequency units or a second set of antenna ports for use in reconstructing the CSI on at least one of a third set of frequency units or a third set of antenna ports, wherein at least one of the second set of frequency units or the second set of antenna ports includes less than all available frequency units or less than all available antenna ports.

[0315] Aspect 2. The method according to aspect 1, wherein at least one of the second set of frequency units or the second set of antenna ports is determined at least in part based on at least one of the first set of frequency units or the first set of antenna ports, at least one of the third set of frequency units or the third set of antenna ports, received signal power, interference level, channel estimation accuracy of the CSI reference signal, or based on configuration information received from the base station.

[0316] Aspect 3. The method according to any one of aspects 1 or 2, wherein the third set of frequency units includes all available frequency units and the third set of antenna ports includes all available antenna ports.

[0317] Aspect 4. The method according to any one of aspects 1 to 3, wherein receiving the CSI reference signal further comprises receiving the CSI reference signal on the first set of frequency units and via the first set of antenna ports.

[0318] Aspect 5. The method according to aspect 4, wherein transmitting the information associated with the CSI comprises transmitting the information associated with the CSI on the second set of frequency units and using the second set of antenna ports.

[0319] Aspect 6. The method according to any one of aspects 1 to 5, wherein the first set of frequency units and the second set of frequency units are the same set of frequency units.

[0320] Aspect 7. The method according to any one of aspects 1 to 6, wherein the second set of frequency units includes a subband having at least one resource block containing the CSI reference signal.

[0321] Aspect 8. The method according to any one of Aspects 1 to 7, wherein the second set of frequency units includes the first set of frequency units and at least one additional frequency unit.

[0322] Aspect 9. The method according to the method of Aspect 8, wherein the at least one additional frequency unit can be configured by the network or is determined based on predefined rules.

[0323] Aspect 10. The method according to any one of Aspects 1 to 9, wherein the second set of frequency units is in a subband associated with high channel estimation quality in at least one of a set of resource blocks or a set of subbands.

[0324] Aspect 11. The method according to Aspect 10, wherein the high channel estimation quality is determined based on at least one of high reference signal received power, high interference, high noise measurement, or resources close to the CSI reference signal.

[0325] Aspect 12. The method according to any one of Aspects 1 to 11, wherein the first set of frequency units and the first set of antenna ports are the same as the second set of frequency units and the second set of antenna ports.

[0326] Aspect 13. The method according to any one of Aspects 1 to 12, wherein the second set of frequency units and the second set of antenna ports include the first set of frequency units and the first set of antenna ports and at least one additional antenna port.

[0327] Aspect 14. The method according to Aspect 13, wherein the at least one additional antenna port is at least one of the following: predefined, based on configuration information received from the base station, or reported by the user equipment.

[0328] Aspect 15. The method according to any one of Aspects 1 to 14, wherein the second set of antenna ports includes all available antenna ports or a selected set of antenna ports.

[0329] Aspect 16. The method according to Aspect 15, wherein the second set of antenna ports includes a selected set of antenna ports, and wherein the selected set of antenna ports is predefined or based on configuration information received from the base station.

[0330] Aspect 17. The method according to any one of Aspects 1 to 16, wherein the first set of frequency units, the second set of frequency units, and the third set of frequency units are different sets of frequency units.

[0331] Aspect 18. The method according to aspect 17, wherein the first set of antenna ports, the second set of antenna ports, and the third set of frequency units are different sets of antenna ports.

[0332] Aspect 19. The method according to aspect 17 or 18, wherein the third set of frequency units includes all available frequency units.

[0333] Aspect 20. The method according to any one of aspects 1 to 19, wherein at least the first set of frequency units or the first set of antenna ports is configured based on a resource pattern of the CSI reference signal.

[0334] Aspect 21. The method according to any one of aspects 1 to 20, wherein at least the third set of frequency units or the third set of antenna ports is at least one of the following: configured based on a CSI reporting subband configuration or dependent on at least one of the second set of frequency units or the second set of antenna ports.

[0335] Aspect 22. The method according to any one of aspects 1 to 21, wherein at least the second set of frequency units or the second set of antenna ports is at least one of the following: predefined based on configuration information received from the base station or sent in a CSI report including the information associated with the CSI.

[0336] Aspect 23. The method according to any one of aspects 1 to 22, wherein the information associated with the CSI includes a latent representation of the CSI generated using a machine learning encoder.

[0337] Aspect 24. An apparatus for wireless communication, the apparatus comprising: at least one memory; and at least one processor, the at least one processor coupled to the at least one memory and configured to: receive a channel state information (CSI) reference signal from a base station on at least one of a first set of frequency units or a first set of antenna ports, wherein at least one of the first set of frequency units or the first set of antenna ports includes less than all available frequency units or less than all available antenna ports; generate CSI based on the CSI reference signal; and transmit information associated with the CSI to the base station on at least one of a second set of frequency units or a second set of antenna ports for use in reconstructing the CSI on at least one of a third set of frequency units or a third set of antenna ports, wherein at least one of the second set of frequency units or the second set of antenna ports includes less than all available frequency units or less than all available antenna ports.

[0338] Aspect 25. The apparatus according to aspect 24, wherein at least one of the second set of frequency units or the second set of antenna ports is determined at least in part based on at least one of the first set of frequency units or the first set of antenna ports, at least one of the third set of frequency units or the third set of antenna ports, received signal power, interference level, channel estimation accuracy of the CSI reference signal, or based on configuration information received from the base station.

[0339] Aspect 26. The apparatus according to any one of aspects 24 or 25, wherein the third set of frequency units includes all available frequency units and the third set of antenna ports includes all available antenna ports.

[0340] Aspect 27. The apparatus according to any one of aspects 24 to 26, wherein receiving the CSI reference signal further includes receiving the CSI reference signal on the first set of frequency units and via the first set of antenna ports.

[0341] Aspect 28. The apparatus according to any one of aspects 24 to 27, wherein transmitting the information associated with the CSI includes transmitting the information associated with the CSI on the second set of frequency units and using the second set of antenna ports.

[0342] Aspect 29. The apparatus according to any one of aspects 24 to 28, wherein the first set of frequency units and the second set of frequency units are the same set of frequency units.

[0343] Aspect 30. The apparatus according to any one of aspects 24 to 29, wherein the second set of frequency units includes a subband having at least one resource block containing the CSI reference signal.

[0344] Aspect 31. The apparatus according to any one of aspects 24 to 30, wherein the second set of frequency units includes the first set of frequency units and at least one additional frequency unit.

[0345] Aspect 32. The apparatus according to aspect 31, wherein the at least one additional frequency unit can be configured by the network or is determined based on predefined rules.

[0346] Aspect 33. The apparatus according to any one of aspects 24 to 32, wherein the second set of frequency units is in a subband associated with high channel estimation quality in at least one of a set of resource blocks or a set of subbands.

[0347] Aspect 34. The apparatus according to aspect 33, wherein the high channel estimation quality is determined based on at least one of high reference signal received power, high interference, high noise measurement, or resources close to the CSI reference signal.

[0348] Aspect 35. The apparatus according to any one of aspects 24 to 34, wherein the first set of frequency units and the first set of antenna ports are the same as the second set of frequency units and the second set of antenna ports.

[0349] Aspect 36. The apparatus according to any one of aspects 24 to 35, wherein the second set of frequency units and the second set of antenna ports include the first set of frequency units and the first set of antenna ports and at least one additional antenna port.

[0350] Aspect 37. The apparatus according to aspect 36, wherein the at least one additional antenna port is at least one of the following: predefined, based on configuration information received from the base station, or reported by the user equipment.

[0351] Aspect 38. The apparatus according to any one of aspects 24 to 37, wherein the second set of antenna ports includes all available antenna ports or a selected set of antenna ports.

[0352] Aspect 39. The apparatus according to aspect 38, wherein the second set of antenna ports includes a selected set of antenna ports, and wherein the selected set of antenna ports is predefined or based on configuration information received from the base station.

[0353] Aspect 40. The apparatus according to any one of aspects 24 to 39, wherein the first set of frequency units, the second set of frequency units, and the third set of frequency units are different sets of frequency units.

[0354] Aspect 41. The apparatus according to any one of aspects 24 to 40, wherein the first set of antenna ports, the second set of antenna ports, and the third set of frequency units are different sets of antenna ports.

[0355] Aspect 42. The apparatus according to any one of aspects 24 to 41, wherein the third set of frequency units includes all available frequency units.

[0356] Aspect 43. The apparatus according to any one of aspects 24 to 42, wherein at least the first set of frequency units or the first set of antenna ports is configured based on the resource pattern of the CSI reference signal.

[0357] Aspect 44. The apparatus according to any one of aspects 24 to 43, wherein at least the third set of frequency units or the third set of antenna ports is at least one of the following: configured based on a CSI reporting subband configuration or depending on at least one of the second set of frequency units or the second set of antenna ports.

[0358] Aspect 45. The apparatus according to any one of aspects 24 to 44, wherein at least the second set of frequency units or the second set of antenna ports is at least one of the following: predefined based on configuration information received from the base station or sent in a CSI report including the information associated with the CSI.

[0359] Aspect 46. The apparatus according to any one of aspects 24 to 45, wherein the information associated with the CSI includes a latent representation of the CSI generated using a machine learning encoder.

[0360] Aspect 47. A method for wireless communication at a base station, the method comprising: transmitting a channel state information (CSI) reference signal to a user equipment (UE) on at least one of a first set of frequency units or a first set of antenna ports, wherein at least one of the first set of frequency units or the first set of antenna ports includes less than all available frequency units or less than all available antenna ports; receiving information associated with the CSI from the UE on at least one of a second set of frequency units or a second set of antenna ports, wherein at least one of the second set of frequency units or the second set of antenna ports includes less than all available frequency units or less than all available antenna ports; and generating a reconstructed CSI for at least one of a third set of frequency units or a third set of antenna ports based on the information associated with the CSI.

[0361] Aspect 48. A device for wireless communication, the device comprising: at least one memory; and at least one processor, the at least one processor coupled to the at least one memory and configured to: transmit a channel state information (CSI) reference signal to a user equipment (UE) on at least one of a first set of frequency units or a first set of antenna ports, wherein at least one of the first set of frequency units or the first set of antenna ports comprises less than all available frequency units or less than all available antenna ports; receive information associated with CSI from the UE on at least one of a second set of frequency units or a second set of antenna ports, wherein at least one of the second set of frequency units or the second set of antenna ports comprises less than all available frequency units or less than all available antenna ports; and generate a reconstructed CSI for at least one of a third set of frequency units or a third set of antenna ports based on the information associated with the CSI.

[0362] Aspect 49. A non-transitory computer-readable storage medium, the non-transitory computer-readable storage medium comprising instructions stored thereon that, when executed by at least one processor, cause the at least one processor to perform the operations according to any one of Aspects 1 to 23 and 47.

[0363] Aspect 50. A device for wireless communication, the device comprising one or more components for performing the operations according to any one of Aspects 1 to 23 and 47.

[0364] Aspect 49. A non-transitory computer-readable storage medium, the non-transitory computer-readable storage medium comprising instructions stored thereon that, when executed by at least one processor, cause the at least one processor to perform the operations according to any one of Aspects 1 to 23 and 47.

[0365] Aspect 50. A device for wireless communication, the device comprising one or more components for performing the operations according to any one of Aspects 1 to 23 and 47.

Claims

1. An apparatus for wireless communication, the apparatus comprising: at least one memory; and at least one processor, the at least one processor coupled to the at least one memory and configured to: receive a channel state information (CSI) reference signal from a base station on at least one of a first set of frequency units or a first set of antenna ports, wherein at least one of the first set of frequency units or the first set of antenna ports includes less than all available frequency units or less than all available antenna ports; generate CSI based on the CSI reference signal; and transmit information associated with the CSI to the base station on at least one of a second set of frequency units or a second set of antenna ports for use in reconstructing the CSI on at least one of a third set of frequency units or a third set of antenna ports, wherein at least one of the second set of frequency units or the second set of antenna ports includes less than all available frequency units or less than all available antenna ports.

2. The apparatus according to claim 1, wherein the at least one processor is configured to determine at least one of the second set of frequency units or the second set of antenna ports at least in part based on at least one of the first set of frequency units or the first set of antenna ports, at least one of the third set of frequency units or the third set of antenna ports, received signal power, interference level, channel estimation accuracy of the CSI reference signal, or configuration information received from the base station.

3. The apparatus according to claim 1, wherein the third set of frequency units includes all available frequency units and the third set of antenna ports includes all available antenna ports.

4. The apparatus according to claim 1, wherein the at least one processor is configured to receive the CSI reference signal on the first set of frequency units and via the first set of antenna ports.

5. The apparatus according to claim 1, wherein the at least one processor is configured to transmit the information associated with the CSI on the second set of frequency units and using the second set of antenna ports.

6. The apparatus according to claim 1, wherein the first set of frequency units and the second set of frequency units are the same set of frequency units, wherein the second set of frequency units includes a subband having at least one resource block containing the CSI reference signal, and wherein the second set of frequency units includes the first set of frequency units and at least one additional frequency unit.

7. The apparatus according to claim 6, wherein the at least one additional frequency unit is network-configured or determined based on predefined rules, and wherein the second set of frequency units is in a subband associated with high channel estimation quality in at least one of a set of resource blocks or a set of subbands.

8. The apparatus according to claim 7, wherein the at least one processor is configured to determine the high channel estimation quality based on at least one of high reference signal received power, high interference, high noise measurement, or a resource close to the CSI reference signal.

9. The apparatus according to claim 1, wherein the first set of frequency units and the first set of antenna ports are the same as the second set of frequency units and the second set of antenna ports.

10. The apparatus according to claim 1, wherein the second set of frequency units and the second set of antenna ports include the first set of frequency units and the first set of antenna ports and at least one additional antenna port.

11. The apparatus according to claim 10, wherein the at least one additional antenna port is at least one of the following: predefined, based on configuration information received from the base station, or reported by the user equipment.

12. The apparatus according to claim 1, wherein the second set of antenna ports includes all available antenna ports or a selected set of antenna ports.

13. The apparatus according to claim 12, wherein the second set of antenna ports includes a selected set of antenna ports, and wherein the selected set of antenna ports is predefined or based on configuration information received from the base station.

14. The apparatus according to claim 1, wherein the first set of frequency units, the second set of frequency units, and the third set of frequency units are different sets of frequency units.

15. The apparatus according to claim 1, wherein the first set of antenna ports, the second set of antenna ports, and the third set of frequency units are different sets of antenna ports.

16. The apparatus according to claim 1, wherein the third set of frequency units includes all available frequency units.

17. The apparatus according to claim 1, wherein at least the first set of frequency units or the first set of antenna ports is configured based on the resource pattern of the CSI reference signal, and wherein at least the third set of frequency units or the third set of antenna ports is at least one of the following: configured based on the CSI reporting subband configuration or dependent on at least one of the second set of frequency units or the second set of antenna ports.

18. The apparatus according to claim 1, wherein at least the second set of frequency units or the second set of antenna ports is at least one of the following: predefined based on configuration information received from the base station or sent in a CSI report including the information associated with the CSI.

19. The apparatus according to claim 1, wherein the information associated with the CSI includes a compressed representation of the CSI generated using a machine learning model.

20. The apparatus according to claim 19, wherein the compressed representation of the CSI includes a latent representation of the CSI generated using a machine learning encoder.

21. A method for wireless communication at a user equipment (UE), the method comprises: receiving a channel state information (CSI) reference signal on at least one of a first set of frequency units or a first set of antenna ports, wherein at least one of the first set of frequency units or the first set of antenna ports comprises less than all available frequency units or less than all available antenna ports; generating CSI based on the CSI reference signal; and transmitting information associated with the CSI on at least one of a second set of frequency units or a second set of antenna ports for use in reconstructing the CSI on at least one of a third set of frequency units or a third set of antenna ports, wherein at least one of the second set of frequency units or the second set of antenna ports comprises less than all available frequency units or less than all available antenna ports.

22. The method according to claim 21, wherein at least one of the second set of frequency units or the second set of antenna ports is determined at least in part based on at least one of the first set of frequency units or the first set of antenna ports, at least one of the third set of frequency units or the third set of antenna ports, received signal power, interference level, channel estimation accuracy of the CSI reference signal, or configuration information received by the UE.

23. The method according to claim 21, wherein the third set of frequency units comprises all available frequency units and the third set of antenna ports comprises all available antenna ports.

24. The method according to claim 21, wherein receiving the CSI reference signal further comprises receiving the CSI reference signal on the first set of frequency units and via the first set of antenna ports.

25. The method according to claim 24, wherein transmitting the information associated with the CSI comprises transmitting the information associated with the CSI on the second set of frequency units and using the second set of antenna ports.

26. A method for wireless communication at a network entity, the method comprises: transmitting a channel state information (CSI) reference signal to a user equipment (UE) on at least one of a first set of frequency units or a first set of antenna ports, wherein at least one of the first set of frequency units or the first set of antenna ports comprises less than all available frequency units or less than all available antenna ports; receiving information associated with CSI from the UE on at least one of a second set of frequency units or a second set of antenna ports, wherein at least one of the second set of frequency units or the second set of antenna ports comprises less than all available frequency units or less than all available antenna ports; and generating a reconstructed CSI for at least one of a third set of frequency units or a third set of antenna ports based on the information associated with the CSI.

27. The method according to claim 26, wherein the reconstructed CSI is generated using a machine learning model.

28. The method according to claim 26, wherein the third set of frequency units or the third set of antenna ports includes a superset of the second set of frequency units or the second set of antenna ports.

29. An apparatus for wireless communication, the apparatus comprising: at least one memory; and at least one processor, the at least one processor coupled to the at least one memory and configured to: transmit a channel state information (CSI) reference signal to a user equipment (UE) on at least one of a first set of frequency units or a first set of antenna ports, wherein at least one of the first set of frequency units or the first set of antenna ports includes less than all available frequency units or less than all available antenna ports; receive information associated with CSI from the UE on at least one of a second set of frequency units or a second set of antenna ports, wherein at least one of the second set of frequency units or the second set of antenna ports includes less than all available frequency units or less than all available antenna ports; and generate a reconstructed CSI for at least one of a third set of frequency units or a third set of antenna ports based on the information associated with the CSI.

30. The apparatus according to claim 29, wherein the at least one processor is configured to generate the reconstructed CSI using a machine learning model.

Images