Phase alignment of predecoder

Abstract

Aspects of the present disclosure generally relate to wireless communications. In some aspects, a user equipment (UE) may perform measurements on a reference signal. Accordingly, the UE may transmit the meta indicator. The meta indicator may represent one or more attributes associated with processing of the reference signal at the UE. Numerous other aspects are described.

Description

[0001] Citation of Related Applications

[0002] This patent application claims priority to Patent Cooperation Treaty (PCT) Application No. PCT / CN2022 / 131420, entitled "PHASE ALIGNMENT FOR PRECODERS", filed on November 11, 2022, and is assigned to the assignee of this application. The disclosure of the prior application is considered to be a part of this patent application and is incorporated herein by reference. Background Art

[0003] Aspects of the present disclosure generally relate to wireless communication and relate to techniques and apparatuses for determining a precoder.

[0004] Wireless communication systems are widely deployed to provide various telecommunication services such as telephony, video, data, messaging, and broadcasting. A typical wireless communication system may employ multiple access techniques capable of supporting communication with multiple users by sharing available system resources (e.g., bandwidth, transmit power, etc.). Examples of such multiple access techniques include Code Division Multiple Access (CDMA) systems, Time Division Multiple Access (TDMA) systems, Frequency Division Multiple Access (FDMA) systems, Orthogonal Frequency Division Multiple Access (OFDMA) systems, Single Carrier Frequency Division Multiple Access (SC-FDMA) systems, Time Division Synchronous Code Division Multiple Access (TD-SCDMA) systems, and Long Term Evolution (LTE). LTE / Advanced LTE is an enhanced set of the Universal Mobile Telecommunications System (UMTS) mobile standards promulgated by the 3rd Generation Partnership Project (3GPP).

[0005] A wireless network may include one or more network nodes that support communication for wireless communication devices such as user equipment (UE) or multiple UEs. The UE may communicate with the network node via downlink communication and uplink communication. "Downlink" (or "DL") refers to the communication link from the network node to the UE, and "uplink" (or "UL") refers to the communication link from the UE to the network node. Some wireless networks may support device-to-device communication, such as via a local link (e.g., sidelink (SL), Wireless Local Area Network (WLAN) link, and / or Wireless Personal Area Network (WPAN) link, etc.).

[0006] The above-mentioned multiple access technologies have been adopted in various telecommunication standards to provide a common protocol that enables different UEs to communicate at the urban, national, regional, and / or global levels. New Radio (NR) (which may be referred to as 5G) is an enhanced set of the LTE mobile standard promulgated by 3GPP. NR is designed to improve spectral efficiency, reduce costs, improve services, utilize new spectra, and better integrate with other open standards by using Orthogonal Frequency Division Multiplexing (OFDM) with Cyclic Prefix (CP) (CP-OFDM) on the downlink, CP-OFDM and / or Single Carrier Frequency Division Multiplexing (SC-FDM) (also known as Discrete Fourier Transform Spread OFDM (DFT-s-OFDM)) on the uplink, and supporting beamforming, Multiple-Input Multiple-Output (MIMO) antenna technology, and carrier aggregation, so as to better support mobile broadband Internet access. With the continuous increase in the demand for mobile broadband access, further improvements to LTE, NR, and other radio access technologies are still useful. SUMMARY OF THE INVENTION

[0007] Some aspects described herein relate to an apparatus for wireless communication at a User Equipment (UE). The apparatus may include: one or more memories; and one or more processors coupled to the one or more memories. The one or more processors may be configured to cause the UE to perform measurements on reference signals. The one or more processors may be configured to cause the UE to determine a precoding matrix based on the measurements. The one or more processors may be configured to cause the UE to apply a phase rotation to the precoding matrix to generate a rotated precoding matrix. The one or more processors may be configured to cause the UE to transmit a report that is at least partially based on the rotated precoding matrix.

[0008] Some aspects described herein relate to an apparatus for wireless communication at a UE. The apparatus may include: one or more memories; and one or more processors coupled to the one or more memories. The one or more processors may be configured to cause the UE to perform measurements on reference signals. The one or more processors may be configured to cause the UE to transmit a meta-indicator representing one or more attributes associated with the processing of reference signals at the UE.

[0009] Some aspects described herein relate to an apparatus for wireless communication at a network node. The apparatus may include: one or more memories; and one or more processors coupled to the one or more memories. The one or more processors may be configured to cause the network node to transmit a reference signal. The one or more processors may be configured to cause the network node to receive a report that is at least partially based on a rotated precoding matrix, based on a first singular value decomposition (SVD) algorithm and measurements of the reference signal. The one or more processors may be configured to cause the network node to receive an output from a decoder that is trained on an output from a second SVD algorithm and receives an input from the report.

[0010] Some aspects described herein relate to an apparatus for wireless communication at a network node. The apparatus may include: one or more memories; and one or more processors coupled to the one or more memories. The one or more processors may be configured to cause the network node to transmit a reference signal. The one or more processors may be configured to cause the network node to receive a meta-indicator representing one or more attributes associated with processing of the reference signal at a UE.

[0011] Some aspects described herein relate to a method of wireless communication performed at a UE. The method may include performing measurements on a reference signal. The method may include determining a precoding matrix based on the measurements. The method may include applying a phase rotation to the precoding matrix to generate a rotated precoding matrix. The method may include transmitting a report that is at least partially based on the rotated precoding matrix.

[0012] Some aspects described herein relate to a method of wireless communication performed at a UE. The method may include performing measurements on a reference signal. The method may include transmitting a meta-indicator representing one or more attributes associated with processing of the reference signal at a UE.

[0013] Some aspects described herein relate to a method of wireless communication performed at a network node. The method may include transmitting a reference signal. The method may include receiving a report that is at least partially based on a rotated precoding matrix, based on a first SVD algorithm and measurements of the reference signal. The method may include receiving an output from a decoder that is trained on an output from a second SVD algorithm and receives an input from the report.

[0014] Some aspects described herein relate to a method of wireless communication performed at a network node. The method may include transmitting a reference signal. The method may include receiving a meta-indicator representing one or more attributes associated with processing of the reference signal at a UE.

[0015] Some aspects described herein relate to a non-transitory computer-readable medium storing an instruction set for wireless communication by a UE. The instruction set, when executed by one or more processors of the UE, may cause the UE to perform measurements on reference signals. The instruction set, when executed by one or more processors of the UE, may cause the UE to determine a precoding matrix based on the measurements. The instruction set, when executed by one or more processors of the UE, may cause the UE to apply a phase rotation to the precoding matrix to generate a rotated precoding matrix. The instruction set, when executed by one or more processors of the UE, may cause the UE to send a report based at least in part on the rotated precoding matrix.

[0016] Some aspects described herein relate to a non-transitory computer-readable medium storing an instruction set for wireless communication by a UE. The instruction set, when executed by one or more processors of the UE, may cause the UE to perform measurements on reference signals. The instruction set, when executed by one or more processors of the UE, may cause the UE to send a meta-indicator representing one or more attributes associated with the processing of the reference signals at the UE.

[0017] Some aspects described herein relate to a non-transitory computer-readable medium storing an instruction set for wireless communication by a network node. The instruction set, when executed by one or more processors of the network node, may cause the network node to send reference signals. The instruction set, when executed by one or more processors of the network node, may cause the network node to receive a report based at least in part on a rotated precoding matrix based on a first SVD algorithm and measurements of the reference signals. The instruction set, when executed by one or more processors of the network node, may cause the network node to receive an output from a decoder trained on the output from a second SVD algorithm and receiving an input from the report.

[0018] Some aspects described herein relate to a non-transitory computer-readable medium storing an instruction set for wireless communication by a network node. The instruction set, when executed by one or more processors of the network node, may cause the network node to send reference signals. The instruction set, when executed by one or more processors of the network node, may cause the network node to receive a meta-indicator representing one or more attributes associated with the processing of the reference signals at the UE.

[0019] Some aspects described herein relate to an apparatus for wireless communication. The apparatus may include means for performing measurements on reference signals. The apparatus may include means for determining a precoding matrix based on the measurements. The apparatus may include means for applying a phase rotation to the precoding matrix to generate a rotated precoding matrix. The apparatus may include means for sending a report based at least in part on the rotated precoding matrix.

[0020] Some aspects described herein relate to an apparatus for wireless communication. The apparatus may include components for performing measurements on reference signals. The apparatus may include components for transmitting a meta-indicator representing one or more attributes associated with processing of a reference signal at the apparatus.

[0021] Some aspects described herein relate to an apparatus for wireless communication. The apparatus may include components for transmitting a reference signal. The apparatus may include components for receiving a report that is at least partially based on a rotation precoding matrix based on a first SVD algorithm and measurements of the reference signal. The apparatus may include components for receiving an output from a decoder that is trained on an output from a second SVD algorithm and receives an input from the report.

[0022] Some aspects described herein relate to an apparatus for wireless communication. The apparatus may include components for transmitting a reference signal. The apparatus may include components for receiving a meta-indicator representing one or more attributes associated with processing of a reference signal at a UE.

[0023] Aspects generally include methods, apparatuses, systems, computer program products, non-transitory computer-readable media, user equipment, base stations, network entities, network nodes, wireless communication devices, and / or processing systems as fully described with reference to the accompanying drawings and the specification and as illustrated in the drawings and the specification.

[0024] The features and technical advantages of examples in accordance with the present disclosure have been outlined rather broadly above so that the detailed description that follows may be better understood. Additional features and advantages will be described below. The disclosed concepts and specific examples may be readily utilized as a basis for modifying or designing other structures for carrying out the same purposes of the present disclosure. Such equivalent constructions do not depart from the scope of the appended claims. The characteristics of the concepts disclosed herein (both their organization and method of operation) as well as the associated advantages will be better understood when considered in conjunction with the accompanying drawings. Each of the drawings provided is for the purpose of illustration and description and is not a definition of the limits of the claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] To enable a more particular understanding of the above-described features of the present disclosure, a more specific description may be obtained by reference to the aspects, some of which are illustrated in the accompanying drawings. It should be noted, however, that the drawings only illustrate certain typical aspects of the present disclosure and are not to be considered limiting of its scope, as the specification may admit other equally effective aspects. Like reference numerals in different drawings may identify the same or similar elements.

[0026] Figure 1 is a diagram illustrating an example of a wireless network in accordance with the present disclosure.

[0027] Figure 2 is a diagram illustrating an example of a network node communicating with a user equipment in a wireless network according to the present disclosure.

[0028] Figure 3 is a diagram illustrating an example of a decomposed base station architecture according to the present disclosure.

[0029] Figure 4 is a diagram illustrating an example of reporting a precoding matrix indicator according to the present disclosure.

[0030] Figure 5A is a diagram illustrating an example of artificial intelligence / machine learning-based beam management according to the present disclosure.

[0031] Figure 5B is a diagram illustrating an example of channel feedback using an encoder and a decoder according to the present disclosure.

[0032] Figure 6A is a diagram illustrating an example of a data collection phase and a training phase for an encoder and a decoder according to the present disclosure.

[0033] Figure 6B is a diagram illustrating an example of inference for an encoder and a decoder according to the present disclosure.

[0034] Figure 7 and Figure 8A is a diagram illustrating an example associated with applying phase alignment to a precoder according to the present disclosure.

[0035] Figure 8B is a diagram illustrating an example associated with reporting using a meta-indicator.

[0036] Figure 9 is a diagram illustrating an example process associated with applying phase alignment to a precoder according to the present disclosure.

[0037] Figure 10 is a diagram illustrating an example process associated with decoding a phase-aligned precoder according to the present disclosure.

[0038] Figure 11 and Figure 12 is a diagram illustrating an example process associated with reporting using a meta-indicator according to the present disclosure.

[0039] Figure 13 is a diagram of an example apparatus for wireless communication according to the present disclosure.

[0040] Figure 14 is a diagram illustrating an example of a hardware implementation of an apparatus using a processing system according to the present disclosure.

[0041] Figure 15 FIG. is an illustration of an example implementation of code and circuitry for an apparatus in accordance with the present disclosure.

[0042] Figure 16 FIG. is an illustration of an example apparatus for wireless communication in accordance with the present disclosure.

[0043] Figure 17 FIG. is an illustration of an example implementation of hardware for an apparatus employing a processing system in accordance with the present disclosure.

[0044] Figure 18 FIG. is an illustration of an example implementation of code and circuitry for an apparatus in accordance with the present disclosure. DETAILED DESCRIPTION

[0045] To improve the quality and reliability of transmissions from a network to a user equipment (UE), the network may request that the UE measure reference signals (e.g., channel state information (CSI) reference signals (CSI-RS) or another type of reference signal) and provide a report (e.g., a CSI report) based on the measurements of the reference signals. For example, the UE may determine a channel matrix representing the measurements (e.g., denoted by H). Based on the channel matrix, the UE may use a codebook (e.g., previously indicated by the network and / or programmed into the UE's memory) to identify one or more best codewords for decoding the reference signal. The UE transmits a bit sequence encoding the report and thus encodes a precoding matrix indicator (PMI) indicating the best codeword.

[0046] One technique for capturing more channel information in the bit sequence encoding the report is to apply an encoder (e.g., a machine learning model) at the UE instead of a codebook. The encoder may correspond to a decoder at the network (e.g., a machine learning model trained in parallel with the encoder). For example, the encoder may accept a precoder (e.g., denoted by V) based on the channel matrix H as input and may produce as output a compressed representation of the precoder V that the UE may encode in the report. A corresponding decoder may accept the compressed representation of the precoder V as input and produce a reconstructed precoder (e.g., denoted by V*) as output. The UE may calculate the precoder V by applying a singular value decomposition (SVD) to the channel matrix H. As used herein, “singular value decomposition” or “SVD” refers to factoring a real or complex matrix (in this example, the channel matrix H) into two complex unitary matrices (in this example, one of which is the precoder V) and a rectangular diagonal matrix. By performing SVD, the UE may estimate the precoder that the network applies to the reference signal before transmission. Applying different SVD algorithms may result in unitary matrices with different phases.

[0047] To train the encoder and decoder, the network can send reference signals to multiple UEs during the data collection phase and receive both the channel matrix and the reference signal-based precoder from the UEs. In one training example, during the training phase, the network (or a training entity at the network) can use the channel matrix and the precoder to train the encoder and decoder in parallel. The network (or the training entity) can refine the encoder and decoder during the refinement phase. For example, during the refinement phase, the network can send reference signals to multiple UEs again and receive both the reference signal-based precoder from the UEs and the output from the encoder. Thus, the network (or the training entity) can use the output and the precoder to refine the encoder and decoder in parallel. Thus, the refined encoder and decoder can be used to improve communication between the UE and the network. For example, during the inference phase, the UE can apply the refined encoder and encode the output from the refined encoder into a report to the network. Thus, the UE reports compressed information (i.e., the output from the encoder), and the network can recover more information about the channel between the UE and the network (e.g., by applying the decoder) to better schedule downlink transmissions to the UE based on the information about the channel. This example is generally referred to as "centralized" training because the training entity at the network performs all training and refinement.

[0048] In another training example, during the same training session, the encoder at the UE and the decoder at the network are trained separately on the UE side and the network side, respectively. That is, during each training session, the training entity at the UE provides the output from the encoder as an activation to the decoder at the network. The training entity at the network uses the activation as an input to the decoder and calculates a loss value associated with the current iteration. This loss value can be used to generate gradients (e.g., for backpropagation), and the network can provide the gradients to the training entity on the UE side for the training entity at the UE to update the encoder. The same process can be repeated until a loss threshold or condition is met. In this example, the UE can provide data to the training entity at the UE, and the training entity at the network also obtains the ground truth for loss calculation from the UE (or the training entity at the UE). Thus, the training entity at the UE can use newly collected data to update the encoder by requesting the activation (for backpropagation) from the training entity at the network. Alternatively, the training entity at the network can use newly collected data to update the decoder by requesting the activation (for backpropagation) from the training entity at the UE.

[0049] In another training example, the encoder at the UE and the decoder at the network are trained sequentially. For network-first training, the training entity at the network trains the encoder-decoder pair. The network provides the input and the encoder output to the training entity at the UE. The training entity at the UE can use the input and the encoder output to train its own encoder to ensure interoperability with the decoder at the network. Finally, the decoder trained by the training entity at the network and the encoder trained by the training entity at the UE can be used together. Thus, the UE (or the training entity at the UE) can provide data to the training entity at the network, and the network (or the training entity at the network) can provide the trained encoder output to the training entity at the UE. For UE-first training, the training entity at the UE trains the encoder-decoder pair and provides the encoder output and the decoder output to the training entity at the network. The training entity at the network can use the encoder output and the decoder output to train its own decoder to ensure interoperability with the encoder at the UE. Finally, the decoder trained by the training entity at the network and the encoder trained by the training entity at the UE can be used together.

[0050] Some of the techniques and apparatuses described herein provide a phase rotation applied to a pre-coder at the UE before the UE uses the pre-coder as an input to the encoder (e.g., during the inference phase) or before the UE reports the pre-coder to the network (e.g., during the data collection phase). Applying the phase rotation reduces the difference across pre-coders computed using different SVD algorithms by aligning the phases of the entries in the pre-coder. Thus, applying the phase rotation improves the accuracy of the training (and refinement) of the encoder and decoder during the training phase (or refinement phase). Because the decoder is more accurate, the accuracy of the output from the decoder during the inference phase (which can be the reconstructed pre-coder determined by the network based on the compressed pre-coder reported by the UE) is improved. The improved accuracy results in an improved quality and reliability of the communication between the UE and the network because the network configures the channel between the UE and the network based on the more accurate report.

[0051] Alternatively, the UE can apply the phase rotation to the pre-coder before reporting the PMI to the network using the pre-coder. Applying the phase rotation reduces the overhead when the UE performs frequency compression on the pre-coder to select a codeword (and thus select the PMI). Thus, applying the phase rotation saves power, processing resources, and memory usage at the UE.

[0052] In some aspects, a UE may report measurements with a meta - indicator during a data collection phase. As used herein, a "meta - indicator" refers to an indicator that is associated with information about the UE without explicitly indicating that information. For example, the meta - indicator may be associated with a cluster that includes the UE among multiple clusters. A cluster may represent a group of UEs that share an attribute (e.g., exhibit an attribute within a range associated with the cluster and / or meet a threshold). Thus, the network can infer attributes associated with the UE (e.g., a pre - decoder applied by the UE, an antenna configuration associated with the UE, a beamforming configuration used by the UE, a phase rotation algorithm applied by the UE, and / or an SVD algorithm applied by the UE, etc.) from the meta - indicator without the UE explicitly reporting these attributes. Thus, the network can use the meta - indicator to improve the accuracy of training (and refinement) of the encoder and decoder during a training phase (or refinement phase). Additionally, since the UE suppresses reporting detailed attributes about itself to the network, privacy is protected.

[0053] Aspects of the present disclosure are described more fully hereinafter with reference to the accompanying drawings. However, the present disclosure may be embodied in many different forms and should not be construed as limited to any specific structure or function presented throughout this disclosure. Rather, these aspects are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the present disclosure to those skilled in the art. Those skilled in the art should understand that the scope of the present disclosure is intended to cover any aspect of the present disclosure disclosed herein, whether implemented independently of or in combination with any other aspect of the present disclosure. For example, any number of the aspects described herein may be used to implement an apparatus or practice a method. In addition, the scope of the present disclosure is intended to cover such an apparatus or method practiced using other structures, functionality, or a combination of structures and functionality in addition to or different from the aspects of the present disclosure described herein. It should be understood that any aspect of the disclosure disclosed herein may be embodied by one or more elements of the present invention.

[0054] Several aspects of a telecommunications system will now be presented with reference to various apparatuses and techniques. These apparatuses and techniques will be described in the following detailed description and illustrated in the drawings by various blocks, modules, components, circuits, steps, processes, algorithms, etc. (collectively referred to as "elements"). These elements may be implemented using hardware, software, or a combination thereof. Whether such elements are implemented as hardware or software depends on the particular application and design constraints imposed on the overall system.

[0055] Although terms generally associated with 5G or New Radio (NR) radio access technology (RAT) may be used herein to describe aspects, aspects of the present disclosure may be applied to other RATs, such as 3G RAT, 4G RAT, and / or post - 5G RAT (e.g., 6G).

[0056] Figure 1 is a diagram illustrating an example of a wireless network 100 according to the present disclosure. The wireless network 100 may be a 5G (e.g., NR) network and / or a 4G (e.g., Long Term Evolution (LTE)) network, or may include elements of a 5G (e.g., NR) network and / or elements of a 4G (e.g., Long Term Evolution (LTE)) network, etc. The wireless network 100 may include one or more network nodes 110 (shown as network node 110a, network node 110b, network node 110c, and network node 110d), one UE 120 or multiple UEs 120 (shown as UE 120a, UE 120b, UE 120c, UE 120d, and UE 120e), and / or other entities. The network node 110 is a network node that communicates with the UE 120. As shown, the network node 110 may include one or more network nodes. For example, the network node 110 may be an aggregated network node, which means that the aggregated network node is configured to utilize a radio protocol stack that is physically or logically integrated within a single radio access network (RAN) node (e.g., within a single device or unit). As another example, the network node 110 may be a disaggregated network node (sometimes referred to as a disaggregated base station), which means that the network node 110 is configured to utilize a protocol stack that is physically or logically distributed between two or more nodes, such as one or more central units (CUs), one or more distributed units (DUs), or one or more radio units (RUs).

[0057] In some examples, network node 110 is or includes a network node that communicates with UE 120 via a radio access link, such as an RU. In some examples, network node 110 is or includes a network node that communicates with other network nodes 110 via a fronthaul link or a midhaul link, such as a DU. In some examples, network node 110 is or includes a network node that communicates with other network nodes 110 via a midhaul link or communicates with a core network via a backhaul link, such as a CU. In some examples, network node 110 (such as an aggregated network node 110 or a disaggregated network node 110) may include multiple network nodes, such as one or more RUs, one or more CUs, and / or one or more DUs. Network node 110 may include, for example, an NR base station, an LTE base station, a Node B, an eNB (e.g., in 4G), a gNB (e.g., in 5G), an access point, a transmit receive point (TRP), a DU, an RU, a CU, a mobility element of the network, a core network node, a network element, network equipment, a RAN node, or a combination thereof. In some examples, network nodes 110 may be interconnected with each other or with one or more other network nodes 110 in wireless network 100 using any suitable transport network via various types of fronthaul, midhaul, and / or backhaul interfaces, such as direct physical connections, air interfaces, or virtual networks.

[0058] In some examples, network node 110 may provide communication coverage for a specific geographical area. In the 3rd Generation Partnership Project (3GPP), depending on the context in which the term is used, the term "cell" may refer to the coverage area of network node 110 and / or the network node subsystem serving that coverage area. Network node 110 may provide communication coverage for a macrocell, a picocell, a femtocell, and / or another type of cell. A macrocell may cover a relatively large geographical area (e.g., with a radius of several kilometers) and may allow unrestricted access by UE 120 having a service subscription. A picocell may cover a relatively small geographical area and may allow unrestricted access by UE 120 having a service subscription. A femtocell may cover a relatively small geographical area (e.g., a home) and may allow restricted access by UE 120 associated with the femtocell (e.g., UE 120 in a Closed Subscriber Group (CSG)). The network node 110 for a macrocell may be referred to as a macro network node. The network node 110 for a picocell may be referred to as a pico network node. The network node 110 for a femtocell may be referred to as a femto network node or a home network node. In Figure 1In the example shown, network node 110a may be a macro network node for macro cell 102a, network node 110b may be a pico network node for pico cell 102b, and network node 110c may be a femto network node for femto cell 102c. A network node may support one or more (e.g., three) cells. In some examples, a cell may not necessarily be stationary, and the geographical area of a cell may move according to the location of a moving network node 110 (e.g., a mobile network node).

[0059] In some aspects, the term "base station" or "network node" may refer to an aggregated base station, a disaggregated base station, an integrated access and backhaul (IAB) node, a relay node, or one or more of their components. For example, in some aspects, the "base station" or "network node" may refer to a CU, a DU, an RU, a near real-time (near RT) RAN intelligent controller (RIC), or a non-real-time (non RT) RIC, or a combination thereof. In some aspects, the term "base station" or "network node" may refer to a single device configured to perform one or more functions, such as those described herein in connection with network node 110. In some aspects, the term "base station" or "network node" may refer to multiple devices configured to perform one or more functions. For example, in some distributed systems, each of multiple different devices (which may be located at the same geographical location or different geographical locations) may be configured to perform at least a portion of a function, or to repeat at least a portion of the function, and the term "base station" or "network node" may refer to any one or more of these different devices. In some aspects, the term "base station" or "network node" may refer to one or more virtual base stations or one or more virtual base station functions. For example, in some aspects, two or more base station functions may be instantiated on a single device. In some aspects, the term "base station" or "network node" may refer to one base station function among base station functions, rather than another base station function. In this way, a single device may include more than one base station.

[0060] Wireless network 100 may include one or more relay stations. A relay station is a network node that can receive a transmission of data from an upstream node (e.g., network node 110 or UE 120) and transmit the data to a downstream node (e.g., UE 120 or network node 110). A relay station may be a UE 120 capable of relaying transmissions for other UEs 120. In Figure 1 the example shown, network node 110d (e.g., a relay network node) may communicate with network node 110a (e.g., a macro network node) and UE 120d to facilitate communication between network node 110a and UE 120d. A network node that relays communication may be referred to as a relay station, a relay base station, a relay network node, a relay node, a relay, etc.

[0061] The wireless network 100 may be a heterogeneous network that includes different types of network nodes 110, such as macro network nodes, pico network nodes, femto network nodes, relay network nodes, etc. These different types of network nodes 110 may have different transmission power levels, different coverage areas, and / or different impacts on interference in the wireless network 100. For example, a macro network node may have a high transmission power level (e.g., 5 watts to 40 watts), while pico network nodes, femto network nodes, and relay network nodes may have lower transmission power levels (e.g., 0.1 watt to 2 watts).

[0062] The network controller 130 may be coupled to or communicate with a set of network nodes 110 and may provide coordination and control for these network nodes 110. The network controller 130 may communicate with the network nodes 110 via a backhaul communication link or a midhaul communication link. The network nodes 110 may also communicate directly with each other or indirectly via a wireless or wired backhaul communication link. In some aspects, the network controller 130 may be a CU or a core network device, or may include a CU or a core network device.

[0063] UEs 120 may be dispersed throughout the wireless network 100, and each UE 120 may be stationary or mobile. The UE 120 may include, for example, an access terminal, a terminal, a mobile station, and / or a subscriber unit. The UE 120 may be a cellular phone (e.g., a smart phone), a personal digital assistant (PDA), a wireless modem, a wireless communication device, a handheld device, a laptop computer, a cordless phone, a wireless local loop (WLL) station, a tablet computer, a camera, a gaming device, a netbook, a smartbook, a superbook, a medical device, a biometric device, a wearable device (e.g., a smart watch, smart clothing, smart glasses, a smart wristband, smart jewelry (e.g., a smart ring or a smart bracelet)), an entertainment device (e.g., a music device, a video device, and / or a satellite radio), a vehicle component or sensor, a smart meter / sensor, industrial manufacturing equipment, a global positioning system device, UE functionality of a network node, and / or any other suitable device configured to communicate via a wireless or wired medium.

[0064] Some UEs 120 may be considered machine type communication (MTC) or evolved or enhanced machine type communication (eMTC) UEs. The MTC UEs and / or eMTC UEs may include, for example, robots, drones, remote devices, sensors, meters, monitors, and / or location tags, which may communicate with network nodes, another device (e.g., a remote device), or some other entity. Some UEs 120 may be considered Internet of Things (IoT) devices and / or may be implemented as narrowband IoT (NB-IoT) devices. Some UEs 120 may be considered customer premises equipment. The UE 120 may be included inside a housing that houses components of the UE 120, such as processor components and / or memory components. In some examples, the processor components and the memory components may be coupled together. For example, the processor components (e.g., one or more processors) and the memory components (e.g., memory) may be operatively coupled, communicatively coupled, electronically coupled, and / or electrically coupled.

[0065] In general, any number of radio networks 100 may be deployed in a given geographical area. Each radio network 100 may support a specific RAT and may operate on one or more frequencies. The RAT may be referred to as a radio technology, an air interface, etc. The frequency may be referred to as a carrier, a frequency channel, etc. Each frequency in a given geographical area may support a single RAT to avoid interference between radio networks of different RATs. In some cases, an NR or 5G RAT network may be deployed.

[0066] In some examples, two or more UEs 120 (e.g., shown as UE 120a and UE 120e) may communicate directly using one or more sidelink channels (e.g., communicate with each other without using the network node 110 as an intermediate device). For example, the UE 120 may use peer-to-peer (P2P) communication, device-to-device (D2D) communication, vehicle-to-everything (V2X) protocols (e.g., which may include vehicle-to-vehicle (V2V) protocols, vehicle-to-infrastructure (V2I) protocols, or vehicle-to-pedestrian (V2P) protocols), and / or mesh networks to communicate. In such examples, the UE 120 may perform scheduling operations, resource selection operations, and / or other operations described elsewhere herein as being performed by the network node 110.

[0067] The electromagnetic spectrum is typically subdivided into various categories, bands, channels, etc. by frequency / wavelength. In 5G NR, two initial operating bands have been identified as Frequency Range Designation FR1 (410 MHz – 7.125 GHz) and FR2 (24.25 GHz – 52.6 GHz). It should be understood that although a portion of FR1 is greater than 6 GHz, in various documents and articles, FR1 is typically (interchangeably) referred to as the “sub-6 GHz” band. Regarding FR2, a similar naming issue sometimes occurs, which is typically (interchangeably) referred to as the “millimeter wave” band in documents and articles, although it is different from the extremely high frequency (EHF) band (30 GHz – 300 GHz) identified by the International Telecommunication Union (ITU) as the “millimeter wave” band.

[0068] The frequencies between FR1 and FR2 are generally referred to as mid-band frequencies. Recent 5G NR research has identified operating bands for these mid-band frequencies as Frequency Range Designation FR3 (7.125 GHz – 24.25 GHz). Bands falling within FR3 can inherit FR1 characteristics and / or FR2 characteristics, and thus can effectively extend the features of FR1 and / or FR2 to mid-band frequencies. Additionally, higher bands are currently being explored to extend 5G NR operation beyond 52.6 GHz. For example, three higher operating bands have been identified as Frequency Range Designation FR4a or FR4-1 (52.6 GHz - 71 GHz), FR4 (52.6 GHz - 114.25 GHz), and FR5 (114.25 GHz - 300 GHz). Each of these higher bands falls within the EHF band.

[0069] Considering the above examples, unless otherwise specifically stated, it should be understood that if the term “sub-6 GHz” etc. is used in this document, the term can broadly represent frequencies that can be below 6 GHz, can be within FR1, or can include mid-band frequencies. Additionally, unless otherwise specifically stated, it should be understood that if the term “millimeter wave” etc. is used in this document, the term can broadly represent frequencies that can include mid-band frequencies, can be within FR2, FR4, FR4-a or FR4-1 and / or FR5, or can be within the EHF band. Considering that the frequencies included in these operating bands (e.g., FR1, FR2, FR3, FR4, FR4-a, FR4-1 and / or FR5) can be modified, and the techniques described herein apply to those modified frequency ranges.

[0070] In some aspects, UE 120 may include a communication manager 140. As Figure 1As shown and described in more detail elsewhere herein, communication manager 140 may perform measurements on a reference signal (RS), may determine a precoding matrix based on the measurements and apply a phase rotation to the precoding matrix to generate a rotated precoding matrix, and may send a report (e.g., to network node 110) that is at least partially based on the rotated precoding matrix. Additionally or alternatively, and as described in more detail elsewhere herein, communication manager 140 may perform measurements on the RS and may send a meta-indicator, where the meta-indicator represents one or more attributes associated with the processing of the RS at UE 120. Additionally or alternatively, communication manager 140 may perform one or more other operations described herein.

[0071] In some aspects, network node 110 may include communication manager 150. As Figure 1 shown and described in more detail elsewhere herein, communication manager 150 may send the RS, may receive a report that is at least partially based on a rotated precoding matrix based on a first SVD algorithm and measurements of the reference signal, and may receive an output from a decoder that is trained on the output from a second SVD algorithm and receives an input from the report. Additionally or alternatively, and as described in more detail elsewhere herein, communication manager 150 may send the RS and may receive a meta-indicator, where the meta-indicator represents one or more attributes associated with the processing of the RS at a UE (e.g., UE 120). Additionally or alternatively, communication manager 150 may perform one or more other operations described herein.

[0072] As indicated above, Figure 1 is provided as an example. Other examples may be different from the example Figure 1 described.

[0073] Figure 2 FIG. 200 is a diagram illustrating an example 200 of communication between network node 110 and UE 120 in a wireless network 100 in accordance with the present disclosure. Network node 110 may be equipped with a set of antennas 234a through 234t, such as T antennas (T≥1). UE 120 may be equipped with a set of antennas 252a through 252r, such as R antennas (R≥1). Network node 110 of example 200 includes one or more radio frequency components, such as antennas 234 and modem 232. In some examples, network node 110 may include an interface, communication component, or another component that facilitates communication with UE 120 or another network node. Some network nodes 110 may not include radio frequency components that facilitate direct communication with UE 120, such as one or more CUs or one or more DUs.

[0074] At network node 110, a transmit processor 220 may receive data destined for UE 120 (or a set of UEs 120) from a data source 212. The transmit processor 220 may select one or more modulation and coding schemes (MCSs) for the UE 120 based at least in part on one or more channel quality indicators (CQIs) received from the UE 120. The network node 110 may process (e.g., encode and modulate) the data for the UE 120 based at least in part on the MCS selected for the UE 120 and may provide data symbols for the UE 120. The transmit processor 220 may process system information (e.g., for semi-static resource allocation information (SRPI)) and control information (e.g., CQI requests, grants, and / or upper layer signaling) and may provide overhead symbols and control symbols. The transmit processor 220 may generate reference symbols for reference signals (e.g., cell-specific reference signal (CRS) or demodulation reference signal (DMRS)) and synchronization signals (e.g., primary synchronization signal (PSS) or secondary synchronization signal (SSS)). A 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 a set of output symbol streams (e.g., T output symbol streams) to a corresponding set of modems 232 (e.g., T modems) (shown as modems 232a through 232t). For example, each output symbol stream may be provided to a modulator component (shown as MOD) of a modem 232. Each modem 232 may process the corresponding output symbol stream (e.g., for OFDM) using the corresponding modulator component to obtain an output sample stream. Each modem 232 may also process the output sample stream (e.g., convert to analog, amplify, filter, and / or up-convert) using the corresponding modulator component to obtain a downlink signal. Modems 232a through 232t may transmit a set of downlink signals (e.g., T downlink signals) via a corresponding set of antennas 234 (e.g., T antennas) (shown as antennas 234a through 234t).

[0075] At the UE 120, a set of antennas 252 (shown as antennas 252a through 252r) may receive downlink signals from the network node 110 and / or other network nodes 110 and may provide a set of received signals (e.g., R received signals) to a set of modems 254 (e.g., R modems) (shown as modems 254a through 254r). For example, each received signal may be provided to a demodulator component (shown as DEMOD) of the modem 254. Each modem 254 may use the corresponding demodulator component to condition (e.g., filter, amplify, down-convert, and / or digitize) the received signal to obtain input samples. Each modem 254 may use the demodulator component to further process the input samples (e.g., for OFDM) to obtain the received symbols. The MIMO detector 256 may obtain the received symbols from the modems 254, may perform MIMO detection on the received symbols when applicable, and may provide the detected symbols. The receive processor 258 may process (e.g., demodulate and decode) the detected symbols, may provide the decoded data for the UE 120 to the data sink 260, and may provide the decoded control information and system information to the controller / processor 280. The term "controller / processor" may refer to one or more controllers, one or more processors, or a combination thereof. The channel processor may determine reference signal received power (RSRP) parameters, received signal strength indicator (RSSI) parameters, reference signal received quality (RSRQ) parameters, and / or CQI parameters, etc. In some examples, one or more components of the UE 120 may be included in the housing 284.

[0076] The network controller 130 may include a communication unit 294, a controller / processor 290, and a memory 292. The network controller 130 may include, for example, one or more devices in a core network. The network controller 130 may communicate with the network node 110 via the communication unit 294.

[0077] One or more antennas (e.g., antennas 234a through 234t and / or antennas 252a through 252r) may include one or more antenna panels, one or more antenna groups, one or more sets of antenna elements, and / or one or more antenna arrays, etc., or may be included within one or more antenna panels, one or more antenna groups, one or more sets of antenna elements, and / or one or more antenna arrays, etc. Antenna panels, antenna groups, a set of antenna elements, and / or antenna arrays may include one or more antenna elements (in a single housing or multiple housings), a set of coplanar antenna elements, a set of non-coplanar antenna elements, and / or one or more antenna elements coupled to one or more transmit and / or receive components (such as Figure 2 one or more components) of.

[0078] On the uplink, at the UE 120, the transmit processor 264 may receive and process data from the data source 262 and control information from the controller / processor 280 (e.g., for reports including RSRP, RSSI, RSRQ, and / or CQI). The transmit processor 264 may generate reference symbols for one or more reference signals. The symbols from the transmit processor 264 may be pre-coded by the TX MIMO processor 266 when applicable, further processed by the modem 254 (e.g., for DFT-s-OFDM or CP-OFDM), and sent to the network node 110. In some examples, the modem 254 of the UE 120 may include a modulator and a demodulator. In some examples, the UE 120 includes a transceiver. The transceiver may include any combination of the antenna 252, the modem 254, the MIMO detector 256, the receive processor 258, the transmit processor 264, and / or the TX MIMO processor 266. The transceiver may be used by a processor (e.g., the controller / processor 280) and the memory 282 to perform aspects of any of the methods described herein.

[0079] At the network node 110, the uplink signals from the UE 120 and / or other UEs may be received by the antenna 234, processed by the modem 232 (e.g., the demodulator component of the modem 232 (shown as DEMOD)), detected by the MIMO detector 236 when applicable, and further processed by the receive processor 238 to obtain the decoded data and control information transmitted by the UE 120. The receive processor 238 may provide the decoded data to the data sink 239 and the decoded control information to the controller / processor 240. The network node 110 may include a communication unit 244 and may communicate with the network controller 130 via the communication unit 244. The network node 110 may include a scheduler 246 to schedule one or more UEs 120 for downlink communication and / or uplink communication. In some examples, the modem 232 of the network node 110 may include a modulator and a demodulator. In some examples, the network node 110 includes a transceiver. The transceiver may include any combination of the antenna 234, the modem 232, the MIMO detector 236, the receive processor 238, the transmit processor 220, and / or the TX MIMO processor 230. The transceiver may be used by a processor (e.g., the controller / processor 240) and the memory 242 to perform aspects of any of the methods described herein.

[0080] The controller / processor 240 of the network node 110, the controller / processor 280 of the UE 120, and / or Figure 2Any other components in may perform one or more techniques associated with phase alignment for pre - decoder applications, as described in more detail elsewhere in this document. For example, the controller / processor 240 of network node 110, the controller / processor 280 of UE 120, and / or Figure 2 any other components of may execute or direct, for example, Figure 9 process 900 of, Figure 10 process 1000 of, Figure 11 process 1100 of, Figure 12 process 1200 of, and / or the operations of other processes as described herein. Memory 242 and memory 282 may store data and program code for network node 110 and UE 120, respectively. In some examples, memory 242 and / or memory 282 may include non - transitory computer - readable media storing one or more instructions for wireless communication (e.g., code and / or program code). For example, when one or more instructions are executed (e.g., directly executed, or after compilation, transformation, and / or interpretation) by one or more processors of network node 110 and / or UE 120, the one or more processors, UE 120, and / or network node 110 may execute or direct, for example, Figure 9 process 900 of, Figure 10 process 1000 of, Figure 11 process 1100 of, Figure 12 process 1200 of, and / or the operations of other processes as described herein. In some examples, executing the instructions may include running the instructions, transforming the instructions, compiling the instructions, and / or interpreting the instructions, etc.

[0081] In some aspects, a UE (e.g., UE 120 and / or Figure 13 device 1300 of) may include components for performing measurements on reference signals; components for determining a pre - coding matrix based on the measurements; components for applying a phase rotation to the pre - coding matrix to generate a rotated pre - coding matrix; and / or components for transmitting a report based at least in part on the rotated pre - coding matrix. Additionally or alternatively, a UE may include components for performing measurements on reference signals and / or components for transmitting a meta - indicator representing one or more attributes associated with the processing of reference signals at the UE. The components for a UE to perform the operations described herein may include, for example, one or more of the following: communication manager 140, antenna 252, modem 254, MIMO detector 256, receive processor 258, transmit processor 264, TX MIMO processor 266, controller / processor 280, or memory 282.

[0082] In some aspects, a network node (e.g., network node 110, RU 340, DU 330, CU 310, and / or Figure 16The apparatus 1600 may include components for transmitting reference signals; components for receiving a report that is at least partially based on a rotation precoding matrix based on measurements of the reference signals using a first SVD algorithm; and / or components for receiving an output from a decoder that is trained on the output from a second SVD algorithm and receives an input from the report. Additionally or alternatively, the network node may include components for transmitting reference signals and / or components for receiving a meta-indicator representing one or more attributes associated with the processing of the reference signals at a UE (e.g., UE 120 and / or Figure 13 of the apparatus 1300). The components for the network node to perform the operations described herein may include, for example, one or more of the following: communication manager 150, transmit processor 220, TX MIMO processor 230, modem 232, antenna 234, MIMO detector 236, receive processor 238, controller / processor 240, memory 242, or scheduler 246.

[0083] In some aspects, a single processor may perform all the functions described as being performed by the one or more processors. In some aspects, the one or more processors may perform a set of functions jointly. For example, a first set of processors (one or more processors) among the one or more processors may perform a first function described as being performed by the one or more processors, and a second set of processors (one or more processors) among the one or more processors may perform a second function described as being performed by the one or more processors. The first set of processors and the second set of processors may be the same set of processors or may be different sets of processors. References to "one or more processors" should be understood to refer to any one or more of the processors described in conjunction with Figure 2 References to "one or more memories" should be understood to refer to any one or more of the memories of the corresponding device, such as the memory described in conjunction with Figure 2 For example, functions described as being performed by one or more memories may be performed by the same subset or different subsets of the one or more memories.

[0084] Although Figure 2 the boxes in are illustrated as different components, the functions described above for these boxes may be implemented in a single hardware, software, or combined component or in various combinations of components. For example, the functions described for transmit processor 264, receive processor 258, and / or TX MIMO processor 266 may be performed by or under the control of controller / processor 280.

[0085] As indicated above, Figure 2 is provided as an example. Other examples may be associated with Figure 2Different from the described examples.

[0086] The deployment of a communication system (such as a 5G NR system) can be arranged with various components or constituent parts in various ways. In a 5G NR system or network, network nodes, network entities, mobility elements of the network, RAN nodes, core network nodes, network elements, base stations, or network equipment can be implemented in a converged or decomposed architecture. For example, a base station (such as a Node B (NB), evolved NB (eNB), NR base station, 5G NB, access point (AP), TRP, or cell, etc.) or one or more units (or one or more components) performing base station functionality can be implemented as a converged base station (also referred to as a stand-alone base station or monolithic base station) or a decomposed base station. A "network entity" or "network node" can refer to a decomposed base station or one or more units of a decomposed base station (such as one or more CUs, one or more DUs, one or more RUs, or a combination thereof).

[0087] A converged base station (e.g., a converged network node) can be configured to utilize a radio protocol stack physically or logically integrated within a single RAN node (e.g., within a single device or unit). A decomposed base station (e.g., a decomposed network node) can be configured to utilize a protocol stack physically or logically distributed among two or more units (such as one or more CUs, one or more DUs, or one or more RUs). In some examples, a CU can be implemented within a network node, and one or more DUs can be co-located with the CU, or alternatively, can be geographically or virtually spread across one or more other network 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, such as a virtual central unit (VCU), virtual distributed unit (VDU), or virtual radio unit (VRU), etc.

[0088] Base station type operations or network designs can consider the aggregation characteristics of base station functionality. For example, a decomposed base station can be utilized in an 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 known as a cloud radio access network (C-RAN)) to facilitate the scaling of a communication system by separating base station functionality into one or more units that can be deployed separately. A decomposed base station can include functionality implemented across two or more units at various physical locations, as well as functionality implemented virtually for at least one unit, which can achieve flexibility in network design. The individual units of a decomposed base station can be configured for wired or wireless communication with at least one other unit of the decomposed base station.

[0089] Figure 3FIG. is an illustration of an example disaggregated base station architecture 300 in accordance with the present disclosure. The disaggregated base station architecture 300 may include a CU 310 that may communicate directly with a core network 320 via a backhaul link, or indirectly with the core network 320 through one or more disaggregated control units (such as a near RT RIC 325 via an E2 link, or a non-RTRIC 315 associated with a service management and orchestration (SMO) framework 305, or both). The CU 310 may communicate with one or more DUs 330 via a respective midhaul link (such as via an F1 interface). Each DU in the DUs 330 may communicate with one or more RUs 340 via a respective fronthaul link. Each RU in the RUs 340 may communicate with one or more UEs 120 via a respective radio frequency (RF) access link. In some embodiments, a UE 120 may be served simultaneously by multiple RUs 340.

[0090] Each unit (including the CU 310, DU 330, RU 340) and 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 that are configured to receive or transmit signals, data, or information (collectively referred to as signals) via a wired or wireless transmission medium. Each unit in the units or an associated processor or controller that provides instructions to one or more communication interfaces of a respective unit may be configured to communicate with one or more of the other units via the transmission medium. In some examples, each unit in the units may include a wired interface and a wireless interface, the wired interface being configured to receive signals or transmit signals to one or more of the other units via a wired transmission medium, and the wireless interface may include a receiver, a transmitter, or a transceiver (such as an RF transceiver) that is configured to receive signals or transmit signals to one or more of the other units via a wireless transmission medium or both.

[0091] In some aspects, the CU 310 may host one or more higher layer control functions. Such control functions may include radio resource control (RRC) functions, packet data convergence protocol (PDCP) functions, or service data adaptation protocol (SDAP) functions, among others. Each control function may be implemented using an interface that is configured to communicate signals with other control functions hosted by the CU 310. The CU 310 may be configured to handle user plane functionality (e.g., central unit - user plane (CU-UP) functionality), control plane functionality (e.g., central unit - control plane (CU-CP) functionality), or a combination thereof. In some embodiments, the CU 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 an interface such as the E1 interface. As needed, the CU 310 may be implemented to communicate with the DU 330 for network control and signaling.

[0092] Each 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 at least part of the radio link control (RLC) layer, the media access control (MAC) layer, and one or more of the higher physical (PHY) layers, at least in part according to a functional split such as that defined by 3GPP. In some aspects, one or more of the higher PHY layers may be implemented by one or more modules for forward error correction (FEC) encoding and decoding, scrambling, and modulation and demodulation, among others. In some aspects, the DU 330 may further host one or more lower PHY layers, such as those implemented by one or more modules for fast Fourier transform (FFT), inverse FFT (iFFT), digital beamforming, or physical random access channel (PRACH) extraction and filtering, among others. Each layer (which may also be referred to as a 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.

[0093] Each RU 340 can implement lower layer functionality. In some deployments, the RU 340 controlled by the DU 330 can correspond to a logical node that hosts RF processing functions or low PHY layer functions, such as performing FFT, performing iFFT, digital beamforming, or PRACH extraction and filtering, etc., based on a functional split (e.g., the functional split defined by 3GPP), such as a lower layer functional split. In such an architecture, each RU 340 can be operated to handle over-the-air (OTA) communication with one or more UEs 120. In some embodiments, the real-time and non-real-time aspects of the control plane and user plane communication with the RU 340 can be controlled by the corresponding DU 330. In some scenarios, this configuration can enable each DU 330 and CU 310 to be implemented in a cloud-based RAN architecture, such as a vRAN architecture.

[0094] As Figure 3 shown, the RU 340 can send RS, and the UE 120 can perform measurements on the RS. Thus, as described herein, the UE 120 can determine a precoding matrix based on the measurements and apply a phase rotation to the precoding matrix to generate a rotated precoding matrix. The precoding matrix and thus the rotated precoding matrix can be based on the first SVD algorithm. As Figure 3 shown, the UE 120 can send a report that is at least partially based on the rotated precoding matrix, and the RU 340 can receive the report. The RU 340 (or a device that controls the RU 340, such as the DU 330 and / or CU 310) can receive an output from a decoder that accepts the input from the report. The decoder can be trained on the output from the second SVD algorithm.

[0095] The SMO framework 305 can be configured to support the RAN deployment and orchestration of non-virtualized network elements and virtualized network elements. For non-virtualized network elements, the SMO framework 305 can be configured to support the deployment of dedicated physical resources for RAN coverage requirements, and these dedicated physical resources can be managed via operation and maintenance interfaces (such as the O1 interface). For virtualized network elements, the SMO framework 305 can be configured to interact with a cloud computing platform (such as the Open Cloud (O-Cloud) platform 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 can include, but are not limited to, CU 310, DU 330, RU 340, non-RT RIC 315, and near-RT RIC 325. In some specific implementations, the SMO framework 305 can communicate with the hardware aspect of the 4G RAN (such as the Open eNB (O-eNB) 311) via the O1 interface. Additionally, in some specific implementations, the SMO framework 305 can directly communicate with each RU in one or more RUs 340 via the corresponding O1 interface. The SMO framework 305 can also include a non-RT RIC 315 configured to support the functionality of the SMO framework 305.

[0096] The non-RT RIC 315 can be configured to include a logical 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 update, or policy-based guidance for 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 logical function that can achieve 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 this interface connects one or more CUs 310, one or more DUs 330, or both, and the O-eNB to the near-RT RIC 325.

[0097] In some specific implementations, to generate the AI / ML models to be deployed in the near-RT RIC 325, the non-RT RIC 315 may 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 at the SMO framework 305 or the non-RT RIC 315 from non-network data sources or from network functions. In some examples, the non-RT RIC 315 or the near-RT RIC 325 may be configured to tune the RAN behavior or performance. For example, the non-RT RIC 315 may monitor the long-term trends and patterns of the performance and employ an AI / ML model to perform corrective actions via the SMO framework 305 (such as reconfiguration via the O1 interface) or via the creation of RAN management policies (such as A1 interface policies).

[0098] As indicated above, Figure 3 is provided as an example. Other examples may be different from the examples described with respect to Figure 3 which are described.

[0099] Figure 4 is a diagram illustrating Example 400 of reporting PMI according to the present disclosure. As Figure 4 shown, Example 400 includes a UE 120 communicating with a network node 110. The network node 110 may indicate (e.g., in a CSI report configuration) a codebook 401 for use by the UE 120. As Figure 4 further shown, the network node 110 may transmit an RS (e.g., CSI-RS or another type of RS), and the UE 120 may measure the RS. Thus, using the codebook as a PMI dictionary, the UE 120 can select the best PMI codeword from the PMI dictionary. The codebook 401 serves as a PMI dictionary because the codebook can be used to look up PMI codewords based on measurements (e.g., channel matrix or precoder). As Figure 4 shown, the UE 120 may use a bit sequence to report the PMI 403 (based on the best PMI codeword). Thus, the bit sequence can encode the CSI report indicating the PMI 403. The network node 110 can use the codebook 401 to determine the best PMI codeword based on the reported PMI 403. The network node 110 can thus configure the channel between the UE 120 and the network node 110 based on the best PMI codeword.

[0100] As indicated above, Figure 4 is provided as an example. Other examples may be different from the examples described for Figure 4 which are described.

[0101] Figure 5A is a diagram illustrating Example 500 of AI / ML-based beam management according to the present disclosure. As Figure 5AAs shown, the AI / ML model 510 can be deployed at or on the UE 120. For example, a model inference host (such as a model inference host) can be deployed at or on the UE 120. The AI / ML model 510 can enable the UE 120 to determine one or more inferences or predictions based on the data input into the AI / ML model 510.

[0102] For example, as indicated by reference numeral 515, the input to the AI / ML model 510 can include measurements associated with a first beam set. For example, the network node 110 can transmit one or more signals using respective beams from the first beam set. The UE 120 can perform measurements on the first beam set (e.g., L1 RSRP measurements or other measurements) to obtain a first measurement set. For example, each beam from the first beam set can be associated with one or more measurements performed by the UE 120. The UE 120 can input the first measurement set (e.g., L1 RSRP measurement values) into the AI / ML model 510 together with information associated with the first beam set and / or the second beam set, such as beam direction (e.g., spatial direction), beam width, beam shape, and / or other characteristics of the respective beams from the first beam set and / or the second beam set.

[0103] As indicated by reference numeral 520, the AI / ML model 510 can output one or more predictions. The one or more predictions can include predicted measurement values (e.g., predicted L1 RSRP measurement values) associated with a second beam set. This can reduce the number of beam measurements performed by the UE 120, thereby conserving the power of the UE 120 and / or network resources that would otherwise be used to measure all the beams included in the first beam set and the second beam set. This type of prediction can be referred to as codebook-based spatial domain selection or prediction.

[0104] As another example, the output of the AI / ML model 510 can include the point direction, angle of departure (AoD), and / or angle of arrival (AoA) of the beams included in the second beam set. This type of prediction can be referred to as non-codebook-based spatial domain selection or prediction. As another example, multiple measurement reports or values collected at different time points can be input into the AI / ML model 510. This can enable the AI / ML model 510 to output codebook-based and / or non-codebook-based predictions for measurement values, AoD, and / or AoA, etc. of the beams at future times. As described herein, the output of the AI / ML model 510 can facilitate the initial access process, secondary cell group (SCG) setup process, beam refinement process (e.g., P2 beam management process or P3 beam management process), link quality or interference adaptation process, beam failure and / or beam blockage prediction, and / or radio link failure prediction, etc.

[0105] In some examples, the first beam set may be referred to as set B beams, and the second beam set may be referred to as set A beams. In some examples, the first beam set (e.g., set B beams) may be a subset of the second beam set (e.g., set A beams). In some other examples, the first beam set and the second beam set may be different beams and / or may be mutually exclusive sets. For example, the first beam set (e.g., set B beams) may include wide beams (e.g., unrefined beams or beams having a beam width that meets a first threshold), and the second beam set (e.g., set A beams) may include narrow beams (e.g., refined beams or beams having a beam width that meets a second threshold). In one example, the AI / ML model 510 may perform spatial domain downlink beam prediction for the beams included in set A beams based on the measurements of the beams included in set B beams. As another example, the AI / ML model 510 may perform temporal downlink beam prediction for the beams included in set A beams based on the historical measurements of the beams included in set B beams.

[0106] Figure 5B is a diagram illustrating example 550 of channel feedback using an encoder and a decoder according to the present disclosure. As Figure 5B shown, example 550 includes a UE 120 communicating with a network node 110. To improve reporting accuracy, the UE 120 and the network node 110 use AI (AI-based) CSI feedback, which includes an encoder (e.g., encoder 555) and a decoder (e.g., decoder 557) instead of a codebook (e.g., in combination with Figure 4 described).

[0107] Accordingly, the network node 110 may transmit an RS (e.g., CSI-RS or another type of RS), and the UE 120 may measure the RS to determine a downlink channel matrix 551 (e.g., represented by H). The UE 120 may further apply SVD (e.g., using SVD algorithm 553) to derive a downlink precoder (e.g., represented by V) from the downlink channel matrix 551. The UE 120 may apply the encoder 555 to generate a compressed representation of the downlink precoder V, and the UE 120 may use a bit sequence to report the compressed representation to the network node 110. Thus, the encoder is similar to a PMI search algorithm (e.g., for finding the best PMI codeword, as in combination with Figure 4 described).

[0108] A bit sequence can encode a CSI report indicating a compressed representation, and network node 110 can receive the CSI report. Thus, network node 110 can apply decoder 557 to generate a reconstructed precoder (e.g., denoted by V*) from the compressed representation. Thus, the decoder is similar to a PMI codebook (e.g., for converting CSI report bits into PMI codewords, as described in conjunction with Figure 4 ). In some aspects, decoder 557 can output a (reconstructed) downlink channel matrix 559 (corresponding to the original channel or a channel pre-whitened by UE 120's demodulation filter based on UE 120). Similarly, decoder 557 can output an interference covariance matrix (e.g., denoted by R nn ) or a transmit covariance matrix. In example 550, decoder 557 can output a (reconstructed) downlink precoder 559. Network node 110 can thus schedule downlink transmissions based on the reconstructed CSI (e.g., the reconstructed downlink channel matrix or downlink precoder 559).

[0109] As indicated above, Figure 5A and Figure 5B are provided as examples. Other examples may differ from the examples described for Figure 5A and Figure 5B .

[0110] Figure 6A is a diagram illustrating example 600 of a data collection phase and a training phase for an encoder and a decoder according to the present disclosure. To train an encoder (e.g., encoder 555 as described in conjunction with Figure 5B ) and a corresponding decoder (e.g., decoder 557 as described in conjunction with Figure 5B ), network node 110 can use multiple UEs (e.g., UEs 120-1,..., UEs 120-n in example 600, where n represents the number of UEs used for data collection) to perform data collection.

[0111] As Figure 6AAs shown, network node 110 may send RS to the UE for measurement. During the training phase, the UE may determine a pre - decoder based on the measurement of the RS (e.g., using the SVD algorithm) and may report the pre - decoder to network node 110. Additionally, in some aspects, the UE may report a channel matrix representing the measurement of the RS to network node 110. Thus, network node 110 (or training entity 601 associated with network node 110) may train the encoder and the corresponding decoder based on the pre - decoder (and in some aspects, the channel matrix). Example 600 is an example of centralized training at the network. Other examples may include UE 120 and network node 110 (or training entities associated with UE 120 and network node 110) training the encoder and decoder in the same training session, as described above. Alternatively, other examples may include UE 120 and network node 110 (or training entities associated with UE 120 and network node 110) training the encoder and decoder sequentially. As described above, UE - first training or network - first training may be used.

[0112] Based on this training, network node 110 may provide the trained encoder to multiple UEs for refinement of the trained encoder (e.g., during the refinement phase). The UEs may be the same set of UEs as those used during the training phase or may include at least one different UE. Network node 110 may send RS to the UEs again for measurement. During the refinement phase, the UEs may determine a pre - decoder based on the measurement of the RS (e.g., using the SVD algorithm) and may report a compressed representation of the pre - decoder output by the trained encoder to network node 110. Additionally, in some aspects, the UEs may report the pre - decoder to network node 110. Thus, network node 110 may refine the encoder and the corresponding decoder based on the compressed representation (and in some aspects, the pre - decoder).

[0113] Figure 6B is a diagram illustrating example 650 for inference of an encoder and a decoder according to the present disclosure. In example 650, UE 120 and network node 110 may use an encoder (e.g., encoder 555 as described in conjunction with Figure 5B and a corresponding decoder (e.g., decoder 557 as described in conjunction with Figure 5B for channel state feedback (CSF). In one example, network node 110 may indicate to UE 120 the encoder to be used, or UE 120 may be programmed (and / or otherwise pre - configured) with the encoder to be used. In another example, the training entity of UE 120 may train the encoder 707 used by UE 120. As Figure 6BAs shown, network node 110 may send RS to UE 120 for measurement. During the inference phase, UE 120 may apply an encoder (e.g., as described in conjunction with Figure 5B ) to the pre-coder determined based on the RS measurement. Thus, UE 120 may report the output from the encoder (e.g., the compressed representation of the pre-coder) to network node 110. Network node 110 may apply a decoder (e.g., as described in conjunction with Figure 5B ) and schedule downlink transmission based on the output from the decoder (e.g., the reconstructed channel matrix or pre-coder).

[0114] Training the encoder and the corresponding decoder may be hardware-dependent. In fact, data corresponding to different types of devices may have different characteristics. For example, such differences may be caused by device construction, RF aspects, or implementation differences across vendors, device models, and / or chip sets, etc. However, to save power, processing resources, and memory usage, training data may be obtained from one type of device (e.g., the encoder and decoder) to develop the model. Thus, when such a model is used for inference on another type of device, the difference in data distribution between training and inference may affect the performance of the model.

[0115] One example difference is associated with SVD. When calculating the input CSI or target CSI (e.g., during the data collection phase), the UE may calculate the SVD of the channel measurements on each sub-band. However, different UEs may use different SVD algorithms, and different SVD algorithms result in different phase rotations on the resulting pre-coders associated with each sub-band. For example, the pre-coder on sub-band k may be calculated by , where H k,n represents the channel measurement associated with the nth resource block (RB) of sub-band k. The size of H k,n may be N t ×N r , where N t represents the number of antenna ports, and N r represents the number of sub-carriers. The size of V k may be N t ×rank. The pre-coder calculated using the first SVD algorithm (represented by V k,alg1 ) may be different in phase from the pre-coder calculated using the second SVD algorithm (represented by V k,alg2 ), such that where θ k,lRepresents the phase rotation on layer l and sub-band k. Thus, when the UE applies an SVD algorithm different from the SVD algorithm used during the training of the encoder (and the corresponding decoder), the accuracy of the output from the decoder at the network is reduced, which reduces the quality and reliability of the communication between the UE and the network. The reduced quality and reliability waste power and processing resources because the network typically performs more retransmissions to the UE.

[0116] Some of the techniques and apparatuses described herein enable a UE (e.g., UE 120) to apply phase alignment to a pre-coder before reporting and / or using the pre-coder. For example, UE 120 may apply a phase alignment algorithm to the pre-coder represented by V k where k = 1,…,N SB such that the V k computed by different SVD algorithms has (at least approximately) the same phase rotation. Thus, the accuracy of the training (and refinement) using the pre-coder is improved. Similarly, based on the compressed representation of the pre-coder, the accuracy of the reconstructed pre-coder at the network is improved. The improved accuracy results in improved quality and reliability of the communication between UE 120 and the network, which saves power and processing resources because the network typically performs fewer retransmissions to UE 120. Alternatively, UE 120 may apply phase alignment to the pre-coder before performing frequency compression on the pre-coder to select a codeword (and thus select a PMI). Thus, UE 120 saves power, processing resources, and memory usage because phase alignment reduces the computational overhead associated with frequency compression.

[0117] As indicated above, Figure 6A and Figure 6B are provided as examples. Other examples may be different from the examples described for Figure 6A and Figure 6B

[0118] Figure 7 is a diagram illustrating Example 700 associated with applying phase alignment to a pre-coder according to the present disclosure. In Example 700, UE 120 and network node 110 may use an encoder (e.g., encoder 707) and a corresponding decoder (e.g., decoder 709) for CSF. In one example, network node 110 may indicate the encoder 707 to be used to UE 120, or UE 120 may be programmed (and / or otherwise pre-configured) with the encoder 707 to be used. In another example, a training entity of UE 120 may train the encoder 707 used by UE 120.

[0119] ​Network node 110 may send RS to UE 120 for measurement. Thus, UE 120 may perform measurements on the RS (e.g., channel matrix 701). To determine a precoding matrix (also referred to as a "precoder") based on the measurements, UE 120 may apply SVD (e.g., SVD algorithm 703).

[0120] As Figure 7 further shown, UE 120 may apply a phase rotation 705 to the precoding matrix to generate a rotated precoding matrix. In one example, the phase rotation 705 is applied per subband and per layer and is determined based on the phase of the first entry in the precoding matrix associated with the corresponding subband and layer. Mathematically, a part of the precoding matrix may be represented by V k,l (e.g., of size N t ×1), which thus represents the precoding vector for layer l on subband k. Thus, the phase rotation 705 is θ k,l = -angle(V k,l [1]), where V k,l [1] = a*exp(jψ) and represents the first entry in V k,l (e.g., the weight applied to the first antenna port on subband k and layer l), and the entries in V k,l are indexed as 1, 2, ..., N t . Thus, the phase rotation 705 is θ k,l = -ψ.

[0121] In another example, the phase rotation 705 is applied per layer and is determined based on the frequency correlation aggregated across the weights applied to the antenna ports. Mathematically, UE 120 may formulate the precoding matrix (e.g., of size N t ×N SB ) by aggregating the precoder vectors for all subbands for layer l. UE 120 may further calculate where represents 's i-th row (e.g., including the weights applied to antenna port i across all subbands), and R f represents the frequency correlation for layer l. Thus, UE 120 may calculate the right singular matrix U l = SVD(R f,l ), such that the phase rotation 705 applied to subband k is given by the phase of the k-th entry in the first column of U l , i.e., U l [k,1], and θ k,l = angle(U l [k,1]).

[0122] In another example, the phase rotation 705 is determined such that the rotated precoding matrix across sub - bands results in a reduced latency (e.g., delay spread and / or average delay). Mathematically, (e.g., of size N t ×N SB ) that aggregates the precoding vectors across all sub - bands of layer l after applying the phase rotation 705 on each sub - band. Additionally, the UE 120 may apply an inverse fast Fourier transform (IFFT) such that W l,t (θ l ) = IFFT(W l (θ l )) = W l (θ l )×F H represents the rotated precoding matrix in the transform domain (e.g., delay domain), where F represents the discrete Fourier transform (DFT) matrix, and F H represents the inverse discrete Fourier transform (IDFT) matrix. The size of W l,t (θ l ) can be N t ×N SB . Thus, the UE 120 can determine the phase rotation 705 (e.g., represented by ) such that Thus, the UE 120 can apply a minimization function to the latency such that the phase rotation 705 results in at least a locally minimum latency.

[0123] As described above, the UE 120 can select between different phase alignment algorithms based on pre - configured settings stored in the memory of the UE 120 (and / or otherwise programmed therein). Alternatively, the network node 110 can configure the UE 120 to apply one of the above - described phase alignment algorithms. Alternatively, the UE 120 can select one of the above - described phase alignment algorithms and report the selected phase alignment algorithm to the network node 110 (e.g., during the data collection phase, as described in conjunction with Figure 6A ).

[0124] As Figure 7 further shown, the UE 120 can apply an encoder 707 to the rotated precoding matrix. Thus, the UE 120 can report the output from the encoder (e.g., a compressed representation of the rotated precoding matrix) to the network node 110. The network node 110 can apply a decoder 709 and configure the channel between the UE 120 and the network node 110 based on the output from the decoder 709 (e.g., the reconstructed channel matrix or the precoder 711).

[0125] By using as described in conjunction with Figure 7The described technology improves the accuracy of training (and refinement) using a pre-coder. Similarly, based on the compressed representation of the pre-coder, the accuracy of the reconstructed pre-coder at network node 110 is improved. The improved accuracy results in improved quality and reliability of communication between UE 120 and network node 110, which saves power and processing resources as network node 110 typically performs fewer re-transmissions to UE 120. Alternatively, UE 120 may apply phase rotation 705 to the pre-coder before performing frequency compression on the pre-coder to select a codeword (and thus select a PMI). Thus, UE 120 saves power, processing resources, and memory usage as phase rotation 705 reduces the computational overhead associated with frequency compression.

[0126] As indicated above, Figure 7 is provided as an example. Other examples may be different from the examples described for Figure 7 the example.

[0127] Figure 8A is a diagram illustrating example 800 associated with applying phase alignment for a pre-coder according to the present disclosure. As Figure 8A shown, network node 110 (e.g., RU 340 and / or a device controlling RU 340 such as DU 330 and / or CU 310) and UE 120 may communicate with each other (e.g., on a wireless network such as Figure 1 wireless network 100).

[0128] As indicated by reference numeral 805, network node 110 may transmit an RS (e.g., directly or via RU 340), and UE 120 may receive the RS. For example, the RS may include CSI-RS for channel measurement, CSI interference measurement (CSI-IM), or non-zero power (NZP) CSI-RS for interference measurement, or a combination of two or more of CSI-RS for channel measurement, CSI-IM, and NZP CSI-RS for interference measurement.

[0129] As indicated by reference numeral 810, UE 120 may perform measurements on the RS. For example, UE 120 may calculate a channel matrix based on the RS.

[0130] As indicated by reference numeral 815, UE 120 may determine a transmit pre-coding matrix based on the measurements. The transmit pre-coding matrix may include sub-matrices (or vectors) for each sub-band. UE 120 may apply a first SVD algorithm to determine the transmit pre-coding matrix.

[0131] As shown by reference numeral 820, the UE 120 may apply a phase rotation to a transmit precoding matrix. Thus, the UE 120 may generate a rotated precoding matrix. In some aspects, a portion of the rotated precoding matrix associated with a first subband is associated with a first phase rotation, and a portion of the rotated precoding matrix associated with a second subband is associated with a second phase rotation. Thus, the phase rotation may be different across subbands. Additionally or alternatively, a portion of the rotated precoding matrix associated with a first layer is associated with a first phase rotation, and a portion of the rotated precoding matrix associated with a second layer is associated with a second phase rotation. Thus, the phase rotation may be different across layers.

[0132] In some aspects, as described in connection with Figure 7 the UE 120 may select the phase of the first entry in the precoding matrix (e.g., per layer and / or per subband) as a phase multiplier and apply the phase multiplier to the remaining entries in the precoding matrix (e.g., per layer and / or per subband). Alternatively, as described in connection with Figure 7 the UE 120 may determine a frequency correlation matrix across weights aggregated associated with one or more antenna ports (e.g., per layer), apply SVD to the frequency correlation matrix to generate eigenvectors (e.g., per layer), and apply the associated phase multiplier indicated in the eigenvectors (e.g., per subband) to the entries in the precoding matrix (e.g., per layer and / or per subband). Alternatively, as described in connection with Figure 7 the UE 120 may use IFFT to determine a delay associated with the precoding matrix and apply a set of phase multipliers to the precoding matrix based on applying a minimization function to the delay.

[0133] As shown by reference numeral 825, UE 120 may send a report that is at least partially based on a rotated precoding matrix, and network node 110 may receive the report (e.g., directly or via RU 340). In some aspects, the report may indicate the rotated precoding matrix. Thus, UE 120 may report the rotated precoding matrix as target CSI or input CSI (e.g., during a data collection phase). Thus, as shown by reference numeral 830a, network node 110 may use the rotated precoding matrix to perform training of an encoder (and corresponding decoder) (e.g., during a training phase). Additionally or alternatively, as further shown by reference numeral 830a, network node 110 may use the rotated precoding matrix to perform refinement of the encoder (and corresponding decoder) (e.g., during a refinement phase). Although example 800 includes network node 110 (or a training entity at network node 110) performing training and / or refinement, other examples may include UE 120 (or a training entity at UE 120) performing training and / or refinement, as described above. Thus, UE 120 may report the rotated precoding matrix as target CSI or input CSI to a training entity at UE 120. Using the rotated precoding matrix instead of the precoding matrix improves the accuracy of training and / or refinement.

[0134] Alternatively, UE 120 may use the rotated precoding matrix as an input to an encoder (e.g., during an inference phase). Thus, the report may indicate an output from the encoder (e.g., a machine learning model that receives the rotated precoding matrix as an input). Thus, as shown by reference numeral 830b, based on the rotated precoding matrix, network node 110 may send downlink scheduling information (e.g., directly or via RU 340), and UE 120 may receive the downlink scheduling information. Even when network node 110 uses a decoder trained with data from a second SVD algorithm, the scheduling information results in improved quality and reliability of communication when UE 120 sends an output based on the rotated precoding matrix instead of an output based on the precoding matrix.

[0135] Alternatively, UE 120 may report CSI based on the rotated precoding matrix. Thus, the report may indicate a PMI selected using the rotated precoding matrix (e.g., based on a legacy non-AI codebook as described above). Thus, as shown by reference numeral 830b, based on the PMI, network node 110 may send downlink scheduling information (e.g., directly or via RU 340), and UE 120 may receive the downlink scheduling information.

[0136] Figure 8B is a diagram illustrating example 850 associated with reporting using a meta-indicator according to the present disclosure. AsFigure 8B As shown, network node 110 (e.g., RU 340 and / or a device controlling RU 340 such as DU 330 and / or CU 310) and UE 120 can communicate with each other (e.g., over a wireless network such as Figure 1 wireless network 100).

[0137] As shown by reference numeral 855, network node 110 can transmit an RS (e.g., directly or via RU 340), and UE 120 can receive the RS. For example, the RS can include CSI-RS, CSI-IM for channel measurement, or NZP CSI-RS for interference measurement, or a combination of two or more of CSI-RS, CSI-IM for channel measurement, and NZP CSI-RS for interference measurement.

[0138] Thus, UE 120 can perform measurements on the RS. For example, UE 120 can calculate a channel matrix based on the RS. UE 120 can perform the measurements as part of a data collection phase (e.g., as described in conjunction with Figure 6A ).

[0139] As shown by reference numeral 860, UE 120 can determine a cluster associated with UE 120. For example, UE 120 can determine the cluster from a plurality of possible clusters. Each cluster can be associated with a set of reception attributes of the UEs included in the cluster. For example, a cluster can be associated with a set of precoders, a set of antenna configurations (e.g., a range of antenna elements and / or a set of shapes of antenna elements), a set of beamforming configurations, a set of phase rotation algorithms, and / or a set of SVD algorithms. Thus, UE 120 can determine the cluster by mapping the reception attributes associated with UE 120 to the set of reception attributes associated with the cluster.

[0140] In some aspects, network node 110 can transmit an indication of a plurality of possible clusters and the set of reception attributes associated with each possible cluster. Additionally or alternatively, the indication of the plurality of possible clusters and the set of reception attributes associated with each possible cluster can be stored in the memory of UE 120 (and / or otherwise programmed therein). Thus, UE 120 can determine which cluster UE 120 belongs to.

[0141] As shown by reference numeral 865, the UE 120 may encode a meta - indicator (also referred to as a "meta - ID") in an indication to be sent to the network node 110. For example, each cluster may be associated with a corresponding meta - indicator. Thus, the UE 120 may use the meta - indicator associated with the cluster that includes the UE 120. The meta - indicator may include an alphanumeric indicator, and the UE 120 may select the meta - indicator from a plurality of possible indicators. For example, the plurality of possible indicators may correspond to a plurality of possible clusters such that the UE 120 selects the meta - indicator based on the reception attributes associated with the UE 120.

[0142] In some aspects, the network node 110 may send an indication of the plurality of possible indicators and the set of reception attributes associated with each possible indicator. Additionally or alternatively, the indication of the plurality of possible indicators and the set of reception attributes associated with each possible indicator may be stored in the memory of the UE 120 (and / or otherwise programmed therein). Thus, the UE 120 may encode the meta - indicator corresponding to the cluster to which the UE 120 belongs.

[0143] As shown by reference numeral 870, the UE 120 may send an indication of the measurement of a reference signal having a meta - indicator, and the network node 110 may receive the indication (e.g., directly or via the RU 340). This measurement serves as the target CSI or input CSI (e.g., during the data collection phase). Additionally, the meta - indicator allows the UE 120 to notify the network node 110 about the reception attributes of the UE 120 without explicitly indicating the reception attributes. For example, the network node 110 may infer an estimate of the reception attributes based on the cluster corresponding to the meta - indicator without inferring the exact value of the reception attributes. Thus, the privacy of the UE 120 is preserved.

[0144] In some embodiments, as shown by reference numeral 875a, the network node 110 may use the measurement and the meta - indicator to perform training of an encoder (and the corresponding decoder) (e.g., during the training phase). Additionally or alternatively, as further shown by reference numeral 875a, the network node 110 may use the measurement and the meta - indicator to perform refinement of an encoder (and the corresponding decoder) (e.g., during the refinement phase). Although Example 850 includes the network node 110 (or a training entity at the network node 110) performing training and / or refinement, other examples may include the UE 120 (or a training entity at the UE 120) performing training and / or refinement, as described above. Thus, the UE 120 may report the measurement as the target CSI or input CSI to a training entity at the UE 120.

[0145] In some specific implementations, the UE 120 may proceed from the data collection phase to the inference phase. Thus, as indicated by reference numeral 875b, in response to the meta-indicator, the network node 110 may send a model indicator (e.g., directly or via the RU 340), and the UE 120 may receive the model indicator. For example, the network node 110 may map the meta-indicator to a model indicator associated with an encoder-decoder pair (from among multiple possible encoder-decoder pairs). Thus, the network node 110 may indicate the encoder-decoder pair for the UE 120 to use that is most suitable for the reception attributes of the UE 120, as represented by the meta-indicator. Thus, the network node 110 and the UE 120 improve the accuracy of the output from the encoder-decoder pair without the UE 120 reporting the exact values of the reception attributes of the UE 120. Thus, the privacy of the UE 120 is preserved.

[0146] As indicated above, Figures 8A to 8B is provided as an example. Other examples may be different from those described with respect to Figures 8A to 8B which are described.

[0147] Figure 9 is a diagram illustrating an example process 900 performed, for example, by a UE in accordance with the present disclosure. The example process 900 is an example in which a UE (e.g., the UE 120 and / or Figure 13 the apparatus 1300) performs operations associated with applying phase alignment for a pre-coder.

[0148] As Figure 9 shown, in some aspects, process 900 may include performing measurements on a reference signal (block 910). For example, the UE (e.g., using the communication manager 140 and / or the measurement component 1308 depicted in Figure 13 ) may perform measurements on the reference signal as described herein.

[0149] As Figure 9 further shown, in some aspects, process 900 may include determining a pre-coding matrix based on the measurements (block 920). For example, the UE (e.g., using the communication manager 140 and / or the determination component 1310 depicted in Figure 13 ) may determine the pre-coding matrix based on the measurements as described herein.

[0150] As Figure 9 further shown, in some aspects, process 900 may include applying a phase rotation to the pre-coding matrix to generate a rotated pre-coding matrix (block 930). For example, the UE (e.g., using the communication manager 140 and / or the determination component 1310) may apply a phase rotation to the pre-coding matrix to generate a rotated pre-coding matrix as described herein.

[0151] AsFigure 9 As further shown, in some aspects, process 900 may include transmitting a report that is at least partially based on a rotated precoding matrix (block 940). For example, a UE (e.g., Figure 13 depicted in the use of communication manager 140 and / or transmission component 1304) may transmit a report that is at least partially based on a rotated precoding matrix, as described herein.

[0152] Process 900 may include additional aspects, such as any single aspect or any combination of aspects described below and / or in combination with one or more other processes described elsewhere herein.

[0153] In a first aspect, the reference signal includes CSI-RS.

[0154] In a second aspect, separately or in combination with the first aspect, the measurement includes a channel matrix.

[0155] In a third aspect, separately or in combination with one or more of the first and second aspects, determining the precoding matrix includes applying SVD to a matrix representing the measurement to determine the precoding matrix.

[0156] In a fourth aspect, separately or in combination with one or more of the first to third aspects, applying phase rotation includes selecting the phase of the first entry associated with the first layer and the first subband in the precoding matrix as a first phase multiplier, and applying the first phase multiplier to the remaining entries associated with the first layer and the first subband in the precoding matrix.

[0157] In a fifth aspect, separately or in combination with one or more of the first to fourth aspects, applying phase rotation further includes selecting the phase of the first entry associated with the first layer and the second subband in the precoding matrix as a second phase multiplier, and applying the second phase multiplier to the remaining entries associated with the first layer and the second subband in the precoding matrix.

[0158] In a sixth aspect, separately or in combination with one or more of the first to fifth aspects, applying phase rotation further includes selecting the phase of the first entry associated with the second layer and the first subband in the precoding matrix as a second phase multiplier, and applying the second phase multiplier to the remaining entries associated with the second layer and the first subband in the precoding matrix.

[0159] In a seventh aspect, either alone or in combination with one or more of the first to sixth aspects, applying phase rotation includes determining a frequency correlation matrix associated with a first layer across weight aggregations associated with one or more antenna ports; applying SVD to the frequency correlation matrix to generate eigenvectors associated with the first layer; and applying a phase multiplier associated with a first subband and indicated in the eigenvectors to an entry in a pre-coding matrix associated with the first layer and the first subband.

[0160] In an eighth aspect, either alone or in combination with one or more of the first to seventh aspects, applying phase rotation further includes applying a phase multiplier associated with a second subband and indicated in the eigenvectors to an entry in a pre-coding matrix associated with the first layer and the second subband.

[0161] In a ninth aspect, either alone or in combination with one or more of the first to eighth aspects, applying phase rotation further includes determining an additional frequency correlation matrix associated with a second layer across additional weight aggregations associated with one or more antenna ports; applying SVD to the additional frequency correlation matrix to generate additional eigenvectors associated with the second layer; and applying a phase multiplier indicated in the additional eigenvectors to an entry in a pre-coding matrix associated with the second layer and the first subband.

[0162] In a tenth aspect, either alone or in combination with one or more of the first to ninth aspects, applying phase rotation includes determining a delay associated with a pre-coding matrix using IFFT and applying a set of phase multipliers to the pre-coding matrix based on applying a minimization function to the delay.

[0163] In an eleventh aspect, either alone or in combination with one or more of the first to tenth aspects, reporting indicates a rotated pre-coding matrix.

[0164] In a twelfth aspect, either alone or in combination with one or more of the first to eleventh aspects, reporting indicates an output from a machine learning model that receives a rotated pre-coding matrix as an input.

[0165] In a thirteenth aspect, either alone or in combination with one or more of the first to twelfth aspects, reporting indicates at least one PMI selected using a rotated pre-coding matrix.

[0166] Although Figure 9 example boxes of process 900 are shown, in some aspects, process 900 may include additional boxes, fewer boxes, different boxes, or boxes arranged in a different manner compared to those depicted in Figure 9 Two or more boxes of process 900 may alternatively be executed in parallel.

[0167] Figure 10 FIG. is an illustration of an example process 1000 performed, for example, by a network node in accordance with the present disclosure. The example process 1000 is one in which a network node (e.g., network node 110 and / or Figure 16 device 1600) performs operations associated with decoding a phase-aligned pre-decoder.

[0168] As Figure 10 shown, in some aspects, process 1000 may include transmitting a reference signal (block 1010). For example, a network entity (e.g., using the Figure 16 communication manager 150 and / or transmission component 1604 depicted in ) may transmit a reference signal as described herein.

[0169] As Figure 10 further shown, in some aspects, process 1000 may include receiving a report at least partially based on a rotated pre-decoding matrix based on a first SVD algorithm and measurements of the reference signal (block 1020). For example, a network node (e.g., using the Figure 16 communication manager 150 and / or receiving component 1602 depicted in ) may receive a report at least partially based on a rotated pre-decoding matrix based on a first SVD algorithm and measurements of the reference signal as described herein.

[0170] As Figure 10 further shown, in some aspects, process 1000 may include receiving an output from a decoder trained on an output from a second SVD algorithm and receiving an input from the report (block 1030). For example, a network node (e.g., using communication manager 150 and / or receiving component 1602) may receive an output from a decoder trained on an output from a second SVD algorithm and receiving an input from the report as described herein.

[0171] Process 1000 may include additional aspects, such as any single aspect or any combination of aspects described below and / or in combination with one or more other processes described elsewhere herein.

[0172] In a first aspect, the reference signal includes CSI-RS.

[0173] In a second aspect, alone or in combination with the first aspect, the measurement includes a channel matrix.

[0174] In a third aspect, alone or in combination with one or more of the first and second aspects, the phase of the first entry in the rotated pre-decoding matrix is zero.

[0175] In a fourth aspect, either alone or in combination with one or more of the first to third aspects, a portion of the rotation precoding matrix associated with the first subband is associated with a first phase rotation, and a portion of the rotation precoding matrix associated with the second subband is associated with a second phase rotation.

[0176] In a fifth aspect, either alone or in combination with one or more of the first to fourth aspects, a portion of the rotation precoding matrix associated with the first layer is associated with a first phase rotation, and a portion of the rotation precoding matrix associated with the second layer is associated with a second phase rotation.

[0177] In a sixth aspect, either alone or in combination with one or more of the first to fifth aspects, a report indicates the rotation precoding matrix.

[0178] In a seventh aspect, either alone or in combination with one or more of the first to sixth aspects, process 1000 includes training (e.g., using Figure 16 the communication manager 150 and / or the training component 1608 depicted therein) a machine learning model at least in part based on the rotation precoding matrix.

[0179] In an eighth aspect, either alone or in combination with one or more of the first to seventh aspects, a report indicates an output from a machine learning model that receives the rotation precoding matrix as an input.

[0180] In a ninth aspect, either alone or in combination with one or more of the first to eighth aspects, process 1000 includes refining (e.g., using Figure 16 the communication manager 150 and / or the refinement component 1610 depicted therein) the machine learning model at least in part based on the output.

[0181] In a tenth aspect, either alone or in combination with one or more of the first to ninth aspects, process 1000 includes applying a decoder (e.g., using Figure 16 the communication manager 150 and / or the decoder component 1612 depicted therein) to the output to determine a reconstructed precoding matrix, and transmitting (e.g., using the communication manager 150 and / or the transmission component 1604) downlink scheduling information based on the reconstructed precoding matrix.

[0182] In an eleventh aspect, either alone or in combination with one or more of the first to tenth aspects, a report indicates at least one PMI based on the rotation precoding matrix.

[0183] In a twelfth aspect, alone or in combination with one or more of the first to eleventh aspects, process 1000 includes sending (e.g., using communication manager 150 and / or sending component 1604) downlink scheduling information based on at least one PMI.

[0184] Although Figure 10 example boxes of process 1000 are shown, in some aspects, process 1000 may include additional boxes, fewer boxes, different boxes, or boxes arranged in a different manner compared to those depicted Figure 10 herein. Additionally or alternatively, two or more boxes of process 1000 may be executed in parallel.

[0185] Figure 11 is a diagram illustrating an example process 1100 performed, for example, by a UE in accordance with the present disclosure. Example process 1100 is an example in which a UE (e.g., UE 120 and / or Figure 13 apparatus 1300 thereof) performs operations associated with reporting using a meta-indicator.

[0186] As Figure 11 shown, in some aspects, process 1100 may include performing measurements on a reference signal (block 1110). For example, a UE (e.g., using Figure 13 communication manager 140 and / or measurement component 1308 depicted herein) may perform measurements on a reference signal as described herein.

[0187] As Figure 11 further shown, in some aspects, process 1100 may include sending a meta-indicator representing one or more attributes associated with processing of a reference signal at the UE (block 1120). For example, a UE (e.g., using Figure 13 communication manager 140 and / or sending component 1304 depicted herein) may send a meta-indicator representing one or more attributes associated with processing of a reference signal at the UE as described herein.

[0188] Process 1100 may include additional aspects, such as any single aspect or any combination of aspects described below and / or in combination with one or more other processes described elsewhere herein.

[0189] In a first aspect, the meta-indicator includes an alphanumeric indicator selected from a plurality of possible indicators using one or more attributes.

[0190] In a second aspect, alone or in combination with the first aspect, the meta-indicator is associated with a UE cluster including the UE from a plurality of possible clusters.

[0191] In a third aspect, alone or in combination with one or more of the first and second aspects, measurements are performed as part of a data collection phase.

[0192] In a fourth aspect, alone or in combination with one or more of the first to third aspects, one or more attributes include a pre - decoder applied by the UE, an antenna configuration associated with the UE, a beamforming configuration used by the UE, a phase rotation algorithm applied by the UE, or a singular value decomposition algorithm applied by the UE.

[0193] In a fifth aspect, alone or in combination with one or more of the first to fourth aspects, process 1100 includes receiving (e.g., using Figure 13 the communication manager 140 and / or the receiving component 1302 depicted in

[0194] Although Figure 11 illustrates example boxes of process 1100, in some aspects, process 1100 may include additional boxes, fewer boxes, different boxes, or boxes arranged in a different manner compared to those depicted in Figure 11 . Additionally or alternatively, two or more boxes of process 1100 may be executed in parallel.

[0195] Figure 12 FIG. is an illustration of an example process 1200 performed, for example, by a network node in accordance with the present disclosure. Example process 1000 is an example in which a network node (e.g., network node 110 and / or Figure 16 the apparatus 1600 of

[0196] As Figure 12 shown, in some aspects, process 1200 may include transmitting a reference signal (block 1210). For example, a network entity (e.g., using Figure 16 the communication manager 150 and / or the transmitting component 1604 depicted in

[0197] As Figure 12 further shown, in some aspects, process 1200 may include receiving a meta - indicator representing one or more attributes associated with the processing of the reference signal at a UE (e.g., UE 120 and / or Figure 13 the apparatus 1300 of Figure 16 ). For example, a network node (e.g., using

[0198] Process 1200 may include additional aspects, such as any individual aspect or any combination of aspects described below and / or in combination with one or more other process descriptions described elsewhere herein.

[0199] In a first aspect, a meta - indicator includes an alphanumeric indicator selected from a plurality of possible indicators using one or more attributes.

[0200] In a second aspect, either alone or in combination with the first aspect, the meta - indicator is associated with a UE cluster including the UE from a plurality of possible clusters.

[0201] In a third aspect, either alone or in combination with one or more of the first and second aspects, a reference signal is sent as part of a data collection phase.

[0202] In a fourth aspect, either alone or in combination with one or more of the first through third aspects, the one or more attributes include a pre - decoder applied by the UE, an antenna configuration associated with the UE, a beamforming configuration used by the UE, a phase rotation algorithm applied by the UE, or a singular value decomposition algorithm applied by the UE.

[0203] In a fifth aspect, either alone or in combination with one or more of the first through fourth aspects, process 1200 includes sending (e.g., using communication manager 150 and / or sending component 1604) a model indicator in response to receipt of the meta - indicator.

[0204] Although Figure 12 example boxes of process 1200 are shown, in some aspects, process 1200 may include additional boxes, fewer boxes, different boxes, or boxes arranged in a different manner compared to those depicted in Figure 12 Additionally or alternatively, two or more boxes of process 1200 may be executed in parallel.

[0205] Figure 13 is a diagram of an example apparatus 1300 for wireless communication in accordance with the present disclosure. Apparatus 1300 may be a UE, or the UE may include apparatus 1300. In some aspects, apparatus 1300 includes a receiving component 1302 and a sending component 1304 that may communicate with each other (e.g., via one or more buses and / or one or more other components). As shown, apparatus 1300 may use receiving component 1302 and sending component 1304 to communicate with another apparatus 1306 (such as a UE, RU, or another wireless communication device). As further shown, apparatus 1300 may include a communication manager 140. Communication manager 140 may include one or more of a measurement component 1308 and / or a determination component 1310, etc.

[0206] In some aspects, apparatus 1300 may be configured to perform one or more operations described herein in connection with Figure 7 , Figure 8A and / or Figure 8B the one or more operations described. Additionally or alternatively, apparatus 1300 may be configured to perform one or more processes described herein, such as Figure 9 process 900 of Figure 11 process 1100 of or a combination thereof. In some aspects, Figure 13 apparatus 1300 shown in Figure 2 and / or one or more components may include one or more components of the UE described in connection with Figure 13 . Additionally or alternatively, Figure 2 one or more components shown in

[0207] Receiving component 1302 may receive communications from apparatus 1306, such as reference signals, control information, data communications, or a combination thereof. Receiving component 1302 may provide the received communications to one or more other components of apparatus 1300. In some aspects, receiving component 1302 may perform signal processing on the received communications (such as filtering, amplification, demodulation, analog-to-digital conversion, demultiplexing, deinterleaving, demapping, equalization, interference cancellation, or decoding, etc.), and may provide the processed signals to one or more other components of apparatus 1300. In some aspects, receiving component 1302 may include one or more antennas, modems, demodulators, MIMO detectors, receiving processors, controller / processors, memories, or a combination thereof of the UE described in connection with Figure 2 .

[0208] Transmitting component 1304 may transmit communications to apparatus 1306, such as reference signals, control information, data communications, or a combination thereof. In some aspects, one or more other components of apparatus 1300 may generate communications and may provide the generated communications to transmitting component 1304 for transmission to apparatus 1306. In some aspects, transmitting component 1304 may perform signal processing on the generated communications (such as filtering, amplification, modulation, digital-to-analog conversion, multiplexing, interleaving, mapping, or encoding, etc.), and may transmit the processed signals to apparatus 1306. In some aspects, transmitting component 1304 may include one or more components of the UE described in connection with Figure 2One or more antennas, a modem, a modulator, a transmit MIMO processor, a transmit processor, a controller / processor, a memory, or a combination thereof of the UE described. In some aspects, the transmit component 1304 may be co-located with the receive component 1302 in a transceiver.

[0209] In some aspects, the measurement component 1308 may perform measurements on reference signals. Accordingly, the determination component 1310 may determine a precoding matrix based on the measurements. The determination component 1310 may further apply a phase rotation to the precoding matrix to generate a rotated precoding matrix. Accordingly, the transmit component 1304 may transmit a report that is at least partially based on the rotated precoding matrix.

[0210] Additionally or alternatively, the measurement component 1308 may perform measurements on reference signals. Accordingly, the transmit component 1304 may transmit a meta-indicator that represents one or more attributes associated with the receive component 1302 (e.g., associated with the processing of reference signals at the device 1300).

[0211] Figure 13 The number and arrangement of the components shown are provided as an example. In fact, there may be additional components, fewer components, different components, or components arranged in a different manner compared to Figure 13 the components shown. Additionally, Figure 13 two or more of the components shown may be implemented within a single component, or Figure 13 a single component shown may be implemented as multiple distributed components. Additionally or alternatively, Figure 13 a set of the (one or more) components shown may perform one or more functions described as being performed by Figure 13 another set of the components shown.

[0212] Figure 14 is a diagram illustrating an example 1400 of a hardware implementation of a device 1405 for employing a processing system 1410 according to the present disclosure. The device 1405 may be a UE.

[0213] The processing system 1410 may be implemented using a bus architecture generally represented by a bus 1415. The bus 1415 may include any number of interconnecting buses and bridges, depending on the specific application of the processing system 1410 and overall design constraints. The bus 1415 links together various circuits including one or more processors and / or hardware components (represented by the processor 1420, the illustrated components, and the computer-readable medium / memory 1425). The processor 1420 may include multiple processors, and / or the memory 1425 may include multiple memories. The bus 1415 may also link various other circuits such as a timing source, peripherals, voltage regulators, and / or power management circuits.

[0214] The processing system 1410 may be coupled to a transceiver 1430. The transceiver 1430 is coupled to one or more antennas 1435. The transceiver 1430 provides components for communicating with various other devices over a transmission medium. The transceiver 1430 receives signals from the one or more antennas 1435, extracts information from the received signals, and provides the extracted information to the processing system 1410 (specifically, the receiving component 1302). Additionally, the transceiver 1430 receives information from the processing system 1410 (specifically, the transmitting component 1304) and generates signals to be applied to the one or more antennas 1435 based at least in part on the received information.

[0215] The processing system 1410 includes a processor 1420 coupled to a computer-readable medium / memory 1425. The processor 1420 is responsible for general processing, including executing software stored on the computer-readable medium / memory 1425. The software, when executed by the processor 1420, causes the processing system 1410 to perform the various functions described herein for any particular device. The computer-readable medium / memory 1425 may also be used to store data manipulated by the processor 1420 when executing the software. The processing system also includes at least one of the illustrated components. These components may be software modules running in the processor 1420, residing / stored in the computer-readable medium / memory 1425, one or more hardware modules coupled to the processor 1420, or some combination thereof.

[0216] In some aspects, the processing system 1410 can be a component of the UE 120 and can include the memory 282 and / or at least one of the TX MIMO processor 266, the receive (RX) processor 258, and / or the controller / processor 280. In some aspects, the apparatus 1405 for wireless communication includes components for performing measurements on reference signals; components for determining a precoding matrix based on the measurements; components for applying a phase rotation to the precoding matrix to generate a rotated precoding matrix; and / or components for transmitting a report based at least in part on the rotated precoding matrix. Additionally or alternatively, the apparatus 1405 for wireless communication includes components for performing measurements on reference signals and / or components for transmitting a meta-indicator representing one or more attributes associated with the processing of reference signals at the apparatus 1405. The foregoing components can be one or more of the foregoing components of the processing system 1410 of the apparatus 1300 and / or the apparatus 1405 configured to perform the functions stated by the foregoing components. As described elsewhere herein, the processing system 1410 can include the TX MIMO processor 266, the RX processor 258, and / or the controller / processor 280. In one configuration, the foregoing components can be the TX MIMO processor 266, the RX processor 258, and / or the controller / processor 280 configured to perform the functions and / or operations stated herein.

[0217] Figure 14 are provided as examples. Other examples may be different from the examples Figure 14 described.

[0218] Figure 15 is a diagram illustrating Example 1500 that exemplifies a specific implementation of code and circuitry for apparatus 1505 according to the present disclosure. The circuitry can include processing circuitry and memory circuitry. The apparatus 1505 can be a UE, or the UE can include the apparatus 1505.

[0219] As Figure 15 shown, the apparatus 1505 can include circuitry (circuitry 1520) for performing measurements on reference signals. For example, the circuitry 1520 can enable the apparatus 1505 to perform measurements on reference signals.

[0220] As Figure 15 shown, the apparatus 1505 can include code (code 1525) for performing measurements on reference signals stored in a computer-readable medium 1425. For example, when executed by the processor 1420, the code 1525 can cause the processor 1420 to cause the transceiver 1430 to perform measurements on reference signals.

[0221] As Figure 15As shown, the apparatus 1505 may include circuitry (circuitry 1530) for determining a precoding matrix based on measurements. For example, the circuitry 1530 may enable the apparatus 1505 to determine a precoding matrix based on measurements.

[0222] As Figure 15 shown, the apparatus 1505 may include code (code 1535) stored in a computer-readable medium 1425 for determining a precoding matrix based on measurements. For example, when executed by the processor 1420, the code 1535 may cause the processor 1420 to determine a precoding matrix based on measurements.

[0223] As Figure 15 shown, the apparatus 1505 may include circuitry (circuitry 1540) for applying a phase rotation to the precoding matrix to generate a rotated precoding matrix. For example, the circuitry 1540 may enable the apparatus 1505 to apply a phase rotation to the precoding matrix to generate a rotated precoding matrix.

[0224] As Figure 15 shown, the apparatus 1505 may include code (code 1545) stored in a computer-readable medium 1425 for applying a phase rotation to the precoding matrix to generate a rotated precoding matrix. For example, when executed by the processor 1420, the code 1545 may cause the processor 1420 to apply a phase rotation to the precoding matrix to generate a rotated precoding matrix.

[0225] As Figure 15 shown, the apparatus 1505 may include circuitry (circuitry 1550) for transmitting a report that is at least partially based on the rotated precoding matrix. For example, the circuitry 1550 may enable the apparatus 1505 to transmit a report that is at least partially based on the rotated precoding matrix. Additionally or alternatively, the report may include an indication of measurements of a reference signal and a meta-indicator representing one or more attributes associated with reception at the apparatus 1505. For example, the circuitry 1550 may enable the apparatus 1505 to transmit an indication of measurements of a reference signal and a meta-indicator representing one or more attributes associated with reception at the transceiver 1430.

[0226] As Figure 15As shown, the apparatus 1505 may include code (code 1555) stored in a computer-readable medium 1425 for sending a report that is at least partially based on a rotation precoding matrix. For example, when executed by the processor 1420, the code 1555 may cause the processor 1420 to cause the transceiver 1430 to send a report that is at least partially based on a rotation precoding matrix. Additionally or alternatively, the report may include an indication of measurements of a reference signal and a meta-indicator representing one or more attributes associated with reception at the apparatus 1505. For example, when executed by the processor 1420, the code 1555 may cause the processor 1420 to cause the transceiver 1430 to send an indication of measurements of a reference signal and a meta-indicator representing one or more attributes associated with reception at the transceiver 1430.

[0227] Figure 15 is provided as an example. Other examples may be different from the examples Figure 15 described.

[0228] Figure 16 is a diagram of an example apparatus 1600 for wireless communication in accordance with the present disclosure. The apparatus 1600 may be a network node, or a network node may include the apparatus 1600. In some aspects, the apparatus 1600 includes a receiving component 1602 and a transmitting component 1604 that may communicate with each other (e.g., via one or more buses and / or one or more other components). As shown, the apparatus 1600 may use the receiving component 1602 and the transmitting component 1604 to communicate with another apparatus 1606 (such as a UE, RU, or another wireless communication device). As further shown, the apparatus 1600 may include a communication manager 150. The communication manager 150 may include one or more of a training component 1608, a refinement component 1610, and / or a decoder component 1612, among others.

[0229] In some aspects, the apparatus 1600 may be configured to perform one or more operations described herein in connection with Figure 7 , Figure 8A and / or Figure 8B described. Additionally or alternatively, the apparatus 1600 may be configured to perform one or more processes described herein, such as Figure 10 process 1000 of Figure 12 process 1200 of Figure 15 or a combination thereof. In some aspects, Figure 2 the apparatus 1600 and / or one or more components shown may include one or more components of the network node described in connection with Figure 16 Additionally or alternatively, Figure 2implemented within the one or more components described. Additionally or alternatively, one or more components in a set of components may be at least partially implemented as software stored in a memory. For example, a component (or a portion of a component) may be implemented as instructions or code stored in a non-transitory computer-readable medium and executable by a controller or processor to perform the functions or operations of the component.

[0230] The receiving component 1602 may receive communications from the device 1606, such as reference signals, control information, data communications, or combinations thereof. The receiving component 1602 may provide the received communications to one or more other components of the device 1600. In some aspects, the receiving component 1602 may perform signal processing on the received communications (such as filtering, amplifying, demodulating, analog-to-digital conversion, demultiplexing, deinterleaving, demapping, equalizing, interference cancellation, or decoding, etc.), and may provide the processed signals to one or more other components of the device 1600. In some aspects, the receiving component 1602 may include one or more antennas, modems, demodulators, MIMO detectors, receiving processors, controllers / processors, memories, or combinations thereof associated with Figure 2 the network node described.

[0231] The transmitting component 1604 may transmit communications to the device 1606, such as reference signals, control information, data communications, or combinations thereof. In some aspects, one or more other components of the device 1600 may generate communications and may provide the generated communications to the transmitting component 1604 for transmission to the device 1606. In some aspects, the transmitting component 1604 may perform signal processing on the generated communications (such as filtering, amplifying, modulating, digital-to-analog conversion, multiplexing, interleaving, mapping, or encoding, etc.), and may transmit the processed signals to the device 1606. In some aspects, the transmitting component 1604 may include one or more antennas, modems, modulators, transmit MIMO processors, transmit processors, controllers / processors, memories, or combinations thereof associated with Figure 2 the network node described. In some aspects, the transmitting component 1604 may be co-located with the receiving component 1602 in a transceiver.

[0232] In some aspects, the transmitting component 1604 may transmit a reference signal. The receiving component 1602 may receive a report that is at least partially based on a rotated precoding matrix based on the first SVD algorithm and measurements of the reference signal. The receiving component 1602 may further receive an output from a decoder that is trained on the output from the second SVD algorithm and receives the input from the report.

[0233] In some aspects, the training component 1608 may train a machine learning model at least in part based on a rotation pre - decoding matrix. Alternatively, the refinement component 1610 may refine the machine learning model at least in part based on the output. Alternatively, the decoder component 1612 may apply a decoder to the output to determine a reconstructed pre - decoding matrix. Accordingly, the transmitting component 1604 may transmit downlink scheduling information based on the reconstructed pre - decoding matrix.

[0234] Additionally or alternatively, the transmitting component 1604 may transmit a reference signal. Accordingly, the receiving component 1602 may receive a meta - indicator representing one or more attributes associated with processing at the device 1606 (e.g., associated with processing of the reference signal at the device 1606). Accordingly, the training component 1608 may train a machine learning model at least in part based on the measurements and the meta - indicator. Alternatively, the refinement component 1610 may refine the machine learning model at least in part based on the measurements and the meta - indicator. Additionally or alternatively, the transmitting component 1604 may transmit a model indicator in response to the meta - indicator.

[0235] Figure 16 The number and arrangement of the components shown are provided as an example. In fact, there may be additional components, fewer components, different components, or components arranged in a different manner compared to Figure 16 those shown. Additionally, Figure 16 two or more of the components shown may be implemented within a single component, or Figure 16 a single component shown may be implemented as multiple distributed components. Additionally or alternatively, Figure 16 a set of the (one or more) components shown may perform one or more functions described as being performed by Figure 16 another set of the components shown.

[0236] Figure 17 FIG. 1700 is a diagram illustrating an example 1700 of a hardware implementation of a device 1705 for employing a processing system 1710 according to the present disclosure. The device 1705 may be a network node.

[0237] The processing system 1710 may be implemented using a bus architecture generally represented by a bus 1715. The bus 1715 may include any number of interconnecting buses and bridges depending on the specific application and overall design constraints of the processing system 1710. The bus 1715 links together various circuits including one or more processors and / or hardware components (represented by the processor 1720, the illustrated components, and the computer - readable medium / memory 1725). The processor 1720 may include multiple processors, and / or the memory 1725 may include multiple memories. The bus 1715 may also link various other circuits such as a timing source, peripherals, voltage regulators, and / or power management circuits.

[0238] The processing system 1710 can be coupled to the transceiver 1730. The transceiver 1730 is coupled to one or more antennas 1735. The transceiver 1730 provides components for communicating with various other devices via a transmission medium. The transceiver 1730 receives signals from one or more antennas 1735, extracts information from the received signals, and provides the extracted information to the processing system 1710 (specifically, the receiving component 1602). Additionally, the transceiver 1730 receives information from the processing system 1710 (specifically, the transmitting component 1604) and generates signals to be applied to one or more antennas 1735 based at least in part on the received information.

[0239] The processing system 1710 includes a processor 1720 coupled to a computer-readable medium / memory 1725. The processor 1720 is responsible for general processing, including executing software stored on the computer-readable medium / memory 1725. The software, when executed by the processor 1720, causes the processing system 1710 to perform the various functions described herein for any particular device. The computer-readable medium / memory 1725 can also be used to store data manipulated by the processor 1720 when executing the software. The processing system also includes at least one of the illustrated components. These components can be software modules running in the processor 1720, residing / stored in the computer-readable medium / memory 1725, one or more hardware modules coupled to the processor 1720, or some combination thereof.

[0240] In some aspects, the processing system 1710 can be a component of the network node 110 and can include the memory 242 and / or at least one of the TX MIMO processor 230, the RX processor 238, and / or the controller / processor 240. In some aspects, the apparatus 1505 for wireless communication includes components for transmitting reference signals; components for receiving a report that is at least partially based on a rotated precoding matrix based on measurements of the reference signals using a first SVD algorithm; and / or components for receiving an output from a decoder that is trained on an output from a second SVD algorithm and receives an input from the report. Additionally or alternatively, the apparatus 1505 for wireless communication includes components for transmitting reference signals and / or components for receiving a meta-indicator representing one or more attributes associated with processing of the reference signals at the UE. The foregoing components can be one or more of the foregoing components of the processing system 1710 of the apparatus 1600 and / or the apparatus 1705 that are configured to perform the functions stated by the foregoing components. As described elsewhere herein, the processing system 1710 can include the TX MIMO processor 230, the receiving processor 238, and / or the controller / processor 240. In one configuration, the foregoing components can be the TX MIMO processor 230, the receiving processor 238, and / or the controller / processor 240 that are configured to perform the functions and / or operations stated herein.

[0241] Figure 17 are provided as examples. Other examples may be different from the examples Figure 17 described.

[0242] Figure 18 is a diagram illustrating Example 1800 that exemplifies a specific implementation of code and circuitry for an apparatus 1805 according to the present disclosure. The circuitry can include processing circuitry and memory circuitry. The apparatus 1805 can be a network node, or the network node can include the apparatus 1805.

[0243] As Figure 18 shown, the apparatus 1805 can include circuitry (circuitry 1820) for transmitting reference signals. For example, the circuitry 1820 can enable the apparatus 1805 to transmit reference signals.

[0244] As Figure 18 shown, the apparatus 1805 can include code (code 1825) for transmitting reference signals stored in a computer-readable medium 1725. For example, when executed by the processor 1720, the code 1825 can cause the processor 1720 to cause the transceiver 1730 to transmit reference signals.

[0245] As Figure 18As shown, apparatus 1805 may include circuitry (circuitry 1830) for receiving a report that is at least partially based on a rotated precoding matrix based on measurements of a first SVD algorithm and reference signals. For example, circuitry 1830 may enable apparatus 1805 to receive a report that is at least partially based on a rotated precoding matrix based on measurements of a first SVD algorithm and reference signals. Additionally or alternatively, the report may include an indication of measurements of the reference signals and a meta-indicator representing one or more attributes associated with reception at the UE. For example, circuitry 1830 may enable apparatus 1805 to receive a meta-indicator representing one or more attributes associated with processing of the reference signals at the UE.

[0246] As Figure 18 As shown, apparatus 1805 may include code (code 1835) stored in a computer-readable medium 1725 for receiving a report that is at least partially based on a rotated precoding matrix based on measurements of a first SVD algorithm and reference signals. For example, when executed by processor 1720, code 1835 may cause processor 1720 to cause transceiver 1730 to receive a report that is at least partially based on a rotated precoding matrix based on measurements of a first SVD algorithm and reference signals. Additionally or alternatively, the report may include an indication of measurements of the reference signals and a meta-indicator representing one or more attributes associated with reception at the UE. For example, when executed by processor 1720, code 1835 may cause processor 1720 to cause transceiver 1730 to receive a meta-indicator representing one or more attributes associated with processing of the reference signals at the UE.

[0247] As Figure 18 As shown, apparatus 1805 may include circuitry (circuitry 1840) for receiving an output from a decoder that is trained on an output from a second SVD algorithm and receives an input from the report. For example, circuitry 1840 may enable apparatus 1805 to receive an output from a decoder that is trained on an output from a second SVD algorithm and receives an input from the report.

[0248] As Figure 18 As shown, apparatus 1805 may include code (code 1845) stored in a computer-readable medium 1725 for receiving an output from a decoder that is trained on an output from a second SVD algorithm and receives an input from the report. For example, when executed by processor 1720, code 1845 may cause processor 1720 to receive an output from a decoder that is trained on an output from a second SVD algorithm and receives an input from the report.

[0249] Figure 18 is provided as an example. Other examples may be different from the example(s) described in conjunction with Figure 18 the example(s) described.

[0250] An overview of some aspects of the present disclosure is provided below:

[0251] Aspect 1: A method of wireless communication performed at a user equipment (UE), the method comprising: performing measurements on a reference signal; determining a precoding matrix based on the measurements; applying a phase rotation to the precoding matrix to generate a rotated precoding matrix; and transmitting a report based at least in part on the rotated precoding matrix.

[0252] Aspect 2: The method according to Aspect 1, wherein the reference signal comprises a channel state information reference signal.

[0253] Aspect 3: The method according to any one of Aspects 1 to 2, wherein the measurements comprise a channel matrix.

[0254] Aspect 4: The method according to any one of Aspects 1 to 3, wherein determining the precoding matrix comprises: applying a singular value decomposition to a matrix representing the measurements to determine the precoding matrix.

[0255] Aspect 5: The method according to any one of Aspects 1 to 4, wherein applying the phase rotation comprises: selecting a first phase of a first entry of the precoding matrix associated with a first layer and a first subband as a first phase multiplier; and applying the first phase multiplier to remaining entries of the precoding matrix associated with the first layer and the first subband.

[0256] Aspect 6: The method according to Aspect 5, wherein applying the phase rotation further comprises: selecting a first phase of a first entry of the precoding matrix associated with the first layer and a second subband as a second phase multiplier; and applying the second phase multiplier to remaining entries of the precoding matrix associated with the first layer and the second subband.

[0257] Aspect 7: The method according to any one of Aspects 5 to 6, wherein applying the phase rotation further comprises: selecting a first phase of a first entry of the precoding matrix associated with a second layer and the first subband as a second phase multiplier; and applying the second phase multiplier to remaining entries of the precoding matrix associated with the second layer and the first subband.

[0258] Aspect 8: The method according to any one of Aspects 1 to 4, wherein applying the phase rotation comprises: determining a frequency correlation matrix associated with a first layer across weight aggregations associated with one or more antenna ports; applying a singular value decomposition to the frequency correlation matrix to generate eigenvectors associated with the first layer; and applying a phase multiplier associated with a first subband and indicated in the eigenvectors to entries of the precoding matrix associated with the first layer and the first subband.

[0259] Aspect 9: The method according to aspect 8, wherein applying the phase rotation further comprises: applying a phase multiplier associated with the second subband and indicated in the eigenvector to an entry in the pre-coding matrix associated with the first layer and the second subband.

[0260] Aspect 10: The method according to any one of aspects 8 to 9, wherein applying the phase rotation further comprises: determining an additional frequency correlation matrix associated with a second layer across additional weight aggregations associated with the one or more antenna ports; applying singular value decomposition to the additional frequency correlation matrix to generate additional eigenvectors associated with the second layer; and applying a phase multiplier indicated in the additional eigenvectors to an entry in the pre-coding matrix associated with the second layer and the first subband.

[0261] Aspect 11: The method according to any one of aspects 1 to 4, wherein applying the phase rotation comprises: using an inverse fast Fourier transform to determine a delay associated with the pre-coding matrix; and applying a set of phase multipliers to the pre-coding matrix based on applying a minimization function to the delay.

[0262] Aspect 12: The method according to any one of aspects 1 to 11, wherein the report indicates the rotated pre-coding matrix.

[0263] Aspect 13: The method according to any one of aspects 1 to 11, wherein the report indicates an output from a machine learning model that receives the rotated pre-coding matrix as an input.

[0264] Aspect 14: The method according to any one of aspects 1 to 11, wherein the report indicates at least one pre-coding matrix indicator selected using the rotated pre-coding matrix.

[0265] Aspect 15: A method of wireless communication performed at a network node, the method comprising: transmitting a reference signal; receiving a report based at least in part on a rotated pre-coding matrix based on a first singular value decomposition (SVD) algorithm and measurements of the reference signal; and receiving an output from a decoder trained on an output from a second SVD algorithm and receiving an input from the report.

[0266] Aspect 16: The method according to aspect 15, wherein the reference signal comprises a channel state information reference signal.

[0267] Aspect 17: The method according to any one of aspects 15 to 16, wherein the measurements comprise a channel matrix.

[0268] Aspect 18: The method according to any one of Aspects 15 to 17, wherein the phase of the first entry in the rotation precoding matrix is zero.

[0269] Aspect 19: The method according to any one of Aspects 15 to 18, wherein a portion of the rotation precoding matrix associated with a first subband is associated with a first phase rotation, and a portion of the rotation precoding matrix associated with a second subband is associated with a second phase rotation.

[0270] Aspect 20: The method according to any one of Aspects 15 to 19, wherein a portion of the rotation precoding matrix associated with a first layer is associated with a first phase rotation, and a portion of the rotation precoding matrix associated with a second layer is associated with a second phase rotation.

[0271] Aspect 21: The method according to any one of Aspects 15 to 20, wherein the report indicates the rotation precoding matrix.

[0272] Aspect 22: The method according to Aspect 21, further comprising training a machine learning model at least in part based on the rotation precoding matrix.

[0273] Aspect 23: The method according to any one of Aspects 15 to 20, wherein the report indicates an output from a machine learning model that receives the rotation precoding matrix as an input.

[0274] Aspect 24: The method according to Aspect 23, the method further comprising refining the machine learning model at least in part based on the output.

[0275] Aspect 25: The method according to Aspect 23, further comprising: applying a decoder to the output to determine a reconstructed precoding matrix; and transmitting downlink scheduling information based on the reconstructed precoding matrix.

[0276] Aspect 26: The method according to any one of Aspects 15 to 20, wherein the report indicates at least one precoding matrix indicator (PMI) based on the rotation precoding matrix.

[0277] Aspect 27: The method according to Aspect 26, further comprising: transmitting downlink scheduling information based on the at least one PMI.

[0278] Aspect 28: A method of wireless communication performed at a user equipment (UE), the method comprising: performing measurements on a reference signal; and transmitting a meta-indicator representing one or more attributes associated with processing of the reference signal at the UE.

[0279] Aspect 29: The method according to aspect 28, wherein the meta-indicator comprises an alphanumeric indicator selected from a plurality of possible indicators using the one or more attributes.

[0280] Aspect 30: The method according to any one of aspects 28 to 29, wherein the meta-indicator is associated with a UE cluster including the UE from a plurality of possible clusters.

[0281] Aspect 31: The method according to any one of aspects 28 to 30, wherein the measurement is performed as part of a data collection phase.

[0282] Aspect 32: The method according to any one of aspects 28 to 31, wherein the one or more attributes include: a precoder applied by the UE; an antenna configuration associated with the UE; a beamforming configuration used by the UE; a phase rotation algorithm applied by the UE; or a singular value decomposition algorithm applied by the UE.

[0283] Aspect 33: The method according to any one of aspects 28 to 32, further comprising: receiving a model indicator in response to the transmission of the meta-indicator.

[0284] Aspect 34: A method of wireless communication performed at a network node, the method comprising: transmitting a reference signal; and receiving a meta-indicator representing one or more attributes associated with the processing of the reference signal at a user equipment (UE).

[0285] Aspect 35: The method according to aspect 34, wherein the meta-indicator comprises an alphanumeric indicator selected from a plurality of possible indicators using the one or more attributes.

[0286] Aspect 36: The method according to any one of aspects 34 to 35, wherein the meta-indicator is associated with a UE cluster including the UE from a plurality of possible clusters.

[0287] Aspect 37: The method according to any one of aspects 34 to 36, wherein the reference signal is transmitted as part of a data collection phase.

[0288] Aspect 38: The method according to any one of aspects 34 to 37, wherein the one or more attributes include: a precoder applied by the UE; an antenna configuration associated with the UE; a beamforming configuration used by the UE; a phase rotation algorithm applied by the UE; or a singular value decomposition algorithm applied by the UE.

[0289] Aspect 39: The method according to any one of aspects 34 to 38, further comprising: transmitting a model indicator in response to the reception of the meta-indicator.

[0290] Aspect 40: An apparatus for wireless communication at a device, the apparatus comprising one or more processors; one or more memories coupled to the processors; and instructions stored in the one or more memories and executable by the one or more processors to cause the apparatus to perform the method according to one or more of Aspects 1 to 39.

[0291] Aspect 41: A device for wireless communication, the device comprising one or more memories; and one or more processors coupled to the one or more memories, the one or more processors configured to cause the device to perform the method according to one or more of Aspects 1 to 39.

[0292] Aspect 42: An apparatus for wireless communication, the apparatus comprising at least one component for performing the method according to one or more of Aspects 1 to 39.

[0293] Aspect 43: A non-transitory computer-readable medium storing code for wireless communication, the code comprising instructions executable by a processor to perform the method according to one or more of Aspects 1 to 39.

[0294] Aspect 44: A non-transitory computer-readable medium storing an instruction set for wireless communication, the instruction set comprising one or more instructions that, when executed by one or more processors of a device, cause the device to perform the method according to one or more of Aspects 1 to 39.

[0295] The foregoing disclosure provides illustration and description, but is not intended to be exhaustive or to limit the aspects to the precise forms disclosed. Modifications and variations may be made in light of the above disclosure, or may be obtained from practice of the aspects.

[0296] As used herein, the term "component" is intended to be broadly construed as hardware and / or a combination of hardware and software. "Software" shall be broadly construed to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executables, execution threads, processes, and / or functions, etc., regardless of whether it is referred to as software, firmware, middleware, microcode, hardware description language, or other names. As used herein, a "processor" is implemented by hardware and / or a combination of hardware and software. It will be apparent that the systems and / or methods described herein can be implemented by different forms of hardware and / or a combination of hardware and software. The actual specific control hardware or software code used to implement these systems and / or methods does not limit the various aspects. Accordingly, the operation and behavior of the systems and / or methods are not described herein with reference to specific software code, as those skilled in the art will understand that the software and hardware can be designed at least in part based on the description herein to implement the systems and / or methods.

[0297] As used herein, depending on the context, "meeting a threshold" can mean that a value is greater than a threshold, greater than or equal to a threshold, less than a threshold, less than or equal to a threshold, equal to a threshold, not equal to a threshold, etc.

[0298] Although specific combinations of features are recited in the claims and / or disclosed in the specification, these combinations are not intended to limit the disclosure of the various aspects. Many of these features can be combined in ways that are not specifically recited in the claims and / or not disclosed in the specification. The disclosure of the various aspects includes each dependent claim in combination with every other claim in the set of claims. As used herein, the phrase referring to "at least one of" a list of items refers to any combination of those items (which includes a single member). As an example, "at least one of a, b, or c" is intended to cover a, b, c, a + b, a + c, b + c, and a + b + c, as well as any combination with multiple identical elements (e.g., a + a, a + a + a, a + a + b, a + a + c, a + b + b, a + c + c, b + b, b + b + b, b + b + c, c + c, and c + c + c, or any other ordering of a, b, and c).

[0299] No element, act, or instruction used herein should be construed as critical or essential unless explicitly described as such. Additionally, as used herein, the article "a" is intended to include one or more items and may be used interchangeably with "one or more." Further, as used herein, the article "the" is intended to include one or more items mentioned in connection with the article "the" and may be used interchangeably with "one or more." Additionally, as used herein, the terms "set" and "group" are intended to include one or more items and may be used interchangeably with "one or more." If only one item is intended, the phrase "only one" or similar will be used. Further, as used herein, the terms "having," "possessing," "with," etc. are intended to be open-ended terms that do not limit the elements they modify (e.g., an element "with" A may also have B). Additionally, the phrase "based on" is intended to mean "at least partially based on" unless otherwise explicitly stated. Additionally, as used herein, the term "or" when used in a series is intended to be open-ended and may be used interchangeably with "and / or" unless otherwise clearly stated (e.g., if used in conjunction with "either" or "only one").

Claims

1. An apparatus for wireless communication at a user equipment (UE), the apparatus comprises: one or more memories; and one or more processors, the one or more processors being coupled to the one or more memories, and the one or more processors being configured to cause the UE to: perform measurements on reference signals; determine a precoding matrix based on the measurements; apply a phase rotation to the precoding matrix to generate a rotated precoding matrix; and send a report that is at least partially based on the rotated precoding matrix.

2. The apparatus according to claim 1, wherein in order to determine the precoding matrix, the one or more processors are configured to cause the UE to: apply singular value decomposition to a matrix representing the measurements to determine the precoding matrix.

3. The apparatus according to claim 1, wherein in order to apply the phase rotation, the one or more processors are configured to cause the UE to: select a phase of a first entry associated with a first layer and a first subband in the precoding matrix as a first phase multiplier; and apply the first phase multiplier to remaining entries associated with the first layer and the first subband in the precoding matrix.

4. The apparatus according to claim 3, wherein in order to apply the phase rotation, the one or more processors are further configured to cause the UE to: select a phase of a first entry associated with the first layer and a second subband in the precoding matrix as a second phase multiplier; and apply the second phase multiplier to remaining entries associated with the first layer and the second subband in the precoding matrix.

5. The apparatus according to claim 3, wherein in order to apply the phase rotation, the one or more processors are further configured to cause the UE to: select a phase of a first entry associated with a second layer and the first subband in the precoding matrix as a second phase multiplier; and apply the second phase multiplier to remaining entries associated with the second layer and the first subband in the precoding matrix.

6. The apparatus according to claim 1, wherein in order to apply the phase rotation, the one or more processors are configured to cause the UE to: determine a frequency correlation matrix associated with a first layer across weight aggregations associated with one or more antenna ports; apply singular value decomposition to the frequency correlation matrix to generate eigenvectors associated with the first layer; and apply a phase multiplier associated with a first subband and indicated in the eigenvectors to entries associated with the first layer and the first subband in the precoding matrix.

7. The apparatus according to claim 6, wherein in order to apply the phase rotation, the one or more processors are further configured to cause the UE to: apply a phase multiplier associated with a second subband and indicated in the eigenvectors to entries associated with the first layer and the second subband in the precoding matrix.

8. The apparatus according to claim 6, wherein in order to apply the phase rotation, the one or more processors are further configured to cause the UE to: Determine an additional frequency correlation matrix associated with a second layer for aggregating additional weights associated with the one or more antenna ports; Apply singular value decomposition to the additional frequency correlation matrix to generate additional eigenvectors associated with the second layer; and Apply the phase multipliers indicated in the additional eigenvectors to the entries in the precoding matrix associated with the second layer and the first subband.

9. The apparatus according to claim 1, wherein in order to apply the phase rotation, the one or more processors are configured to cause the UE to: Use an inverse fast Fourier transform to determine a delay associated with the precoding matrix; and Apply a set of phase multipliers to the precoding matrix based on applying a minimization function to the delay.

10. The apparatus according to claim 1, wherein the report indicates an output from a machine learning model that accepts the rotated precoding matrix as an input.

11. An apparatus for wireless communication at a network node, the apparatus comprises: One or more memories; and One or more processors, the one or more processors being coupled to the one or more memories, the one or more processors being configured to cause the network node to perform the following operations: Transmit a reference signal; Receive a report that is at least partially based on a rotated precoding matrix based on a first singular value decomposition (SVD) algorithm and measurements of the reference signal; and Receive an output from a decoder that is trained on an output from a second SVD algorithm and accepts an input from the report.

12. The apparatus according to claim 11, wherein a portion of the rotated precoding matrix associated with a first subband is associated with a first phase rotation, and a portion of the rotated precoding matrix associated with a second subband is associated with a second phase rotation.

13. The apparatus according to claim 11, wherein a portion of the rotated precoding matrix associated with a first layer is associated with a first phase rotation, and a portion of the rotated precoding matrix associated with a second layer is associated with a second phase rotation.

14. The apparatus according to claim 11, wherein the report indicates the rotated precoding matrix.

15. The apparatus according to claim 14, wherein the one or more processors are further configured to cause the network node to: Train a machine learning model at least partially based on the rotated precoding matrix.

16. The apparatus according to claim 11, wherein the report indicates an output from a machine learning model that accepts the rotated precoding matrix as an input.

17. The apparatus according to claim 16, wherein the one or more processors are further configured to cause the network node to: Refine the machine learning model at least partially based on the output.

18. The apparatus according to claim 16, wherein the one or more processors are further configured to cause the network node to: Apply a decoder to the output to determine a reconstructed precoding matrix; and Transmit downlink scheduling information based on the reconstructed precoding matrix.

19. An apparatus for wireless communication at a user equipment (UE), the apparatus comprises: one or more memories; and one or more processors, the one or more processors being coupled to the one or more memories, and the one or more processors being configured to cause the UE to: perform measurements on a reference signal; and send a meta-indicator representing one or more attributes associated with the processing of the reference signal at the UE.

20. The apparatus according to claim 19, wherein the meta-indicator comprises an alphanumeric indicator selected from a plurality of possible indicators using the one or more attributes.

21. The apparatus according to claim 19, wherein the meta-indicator is associated with a UE cluster including the UE from a plurality of possible clusters.

22. The apparatus according to claim 19, wherein the measurements are performed as part of a data collection phase.

23. The apparatus according to claim 19, wherein the one or more attributes comprise: a pre-coder applied by the UE; an antenna configuration associated with the UE; a beamforming configuration used by the UE; a phase rotation algorithm applied by the UE; or a singular value decomposition algorithm applied by the UE.

24. The apparatus according to claim 19, wherein the one or more processors are configured to cause the UE to: receive a model indicator in response to the transmission of the meta-indicator.

25. An apparatus for wireless communication at a network node, the apparatus comprises: one or more memories; and one or more processors, the one or more processors being coupled to the one or more memories, the one or more processors being configured to cause the network node to: send a reference signal; and receive a meta-indicator representing one or more attributes associated with the processing of the reference signal at a user equipment (UE).

26. The apparatus according to claim 25, wherein the meta-indicator comprises an alphanumeric indicator selected from a plurality of possible indicators using the one or more attributes.

27. The apparatus according to claim 25, wherein the meta-indicator is associated with a UE cluster including the UE from a plurality of possible clusters.

28. The apparatus according to claim 25, wherein the reference signal is sent as part of a data collection phase.

29. The apparatus according to claim 25, wherein the one or more attributes comprise: a pre-coder applied by the UE; an antenna configuration associated with the UE; a beamforming configuration used by the UE; a phase rotation algorithm applied by the UE; or a singular value decomposition algorithm applied by the UE.

30. The apparatus according to claim 25, wherein the one or more processors are configured to cause the network node to: send a model indicator in response to the reception of the meta-indicator.

Images