Reference signal pattern association for channel estimation

Abstract

Methods, systems, and devices for wireless communication are described. A user equipment (UE) may receive a control signal that configures a low density mode for channel state information (CSI) reference signal (RS) reception for a set of multiple antenna ports. The low density pattern may indicate a subset of the set of multiple antenna ports for reception via the CSI-RS of one or more resource blocks (RBs). The UE may receive a set of a plurality of CSI-RSs based on the low density pattern. In some cases, the UE, or some other training device, may train an artificial neural network to process the CSI-RS according to the low density pattern. The artificial neural network may be an example of a generalized neural network or a neural network specific to one or more low density patterns. The UE may transmit a CSI report based on processing the CSI-RS according to the low density mode.

Description

Background Art

[0001] The following relates to wireless communications, including managing resources for channel estimation.

[0002] Wireless communication systems are widely deployed to provide various types of communication content, such as voice, video, packet data, messaging, broadcast, and the like. These systems may be able to support communication with multiple users by sharing available system resources (e.g., time, frequency, and power). Examples of such multiple access systems include fourth generation (4G) systems (such as long term evolution (LTE) systems, advanced LTE (LTE-A) systems, or LTE-A Pro systems) and fifth generation (5G) systems (which may be referred to as new radio (NR) systems). These systems may employ techniques such as code division multiple access (CDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal FDMA (OFDMA), or discrete Fourier transform spread orthogonal frequency division multiplexing (DFT-S-OFDM). A wireless multiple access communication system may include one or more base stations, each of which supports wireless communications for communication devices, which may be referred to as user equipment (UE). Summary of the invention

[0003] An apparatus for wireless communication at a UE is described. The apparatus may include a processor and a memory coupled to the processor. The processor may be configured to receive a control signal from a network entity, the control signal configuring a low-density mode for channel state information reference signal reception for a set of multiple antenna ports, wherein the low-density mode indicates a subset of the set of multiple antenna ports for channel state information reference signal reception via one or more resource blocks. In some examples, the processor may be configured to receive a set of multiple channel state information reference signals from the network entity according to the low-density mode. In some examples, the processor may be configured to send a channel state information report to the network entity based on the set of multiple channel state information reference signals.

[0004] A method for wireless communication at a UE is described. The method may include receiving a control signal from a network entity that configures a low-density mode for channel state information reference signal reception for a set of multiple antenna ports, wherein the low-density mode indicates a subset of the set of multiple antenna ports for channel state information reference signal reception via one or more resource blocks. In some examples, the method may include receiving a set of multiple channel state information reference signals from the network entity according to the low-density mode. In some examples, the method may also include sending a channel state information report to the network entity based on the set of multiple channel state information reference signals.

[0005] Another apparatus for wireless communication at a UE is described. The apparatus may include components for receiving a control signal from a network entity, the control signal configuring a low-density mode for channel state information reference signal reception for a set of multiple antenna ports, wherein the low-density mode indicates a subset of the set of multiple antenna ports for channel state information reference signal reception via one or more resource blocks. In some examples, the apparatus may include components for receiving a set of multiple channel state information reference signals from the network entity according to the low-density mode. In some examples, the apparatus may also include components for sending a channel state information report to the network entity based on the set of multiple channel state information reference signals.

[0006] A non-transitory computer-readable medium storing code for wireless communication at a UE is described. The code may include instructions that are executable by a processor to receive a control signal from a network entity, the control signal configuring a low-density mode for channel state information reference signal reception for a set of multiple antenna ports, wherein the low-density mode indicates a subset of the set of multiple antenna ports for channel state information reference signal reception via one or more resource blocks. In some examples, the instructions may be executable by the processor to receive a set of multiple channel state information reference signals from the network entity according to the low-density mode. In some examples, the instructions may also be executable by the processor to send a channel state information report to the network entity based on the set of multiple channel state information reference signals.

[0007] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for determining a low density mode based on a control signal indicating a mapping from a subset of a set of multiple antenna ports to a set of multiple antenna ports for one or more resource blocks.

[0008] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the mapping may be specific to a resource block, may be specific to a group of resource blocks, or may be common to a set of multiple resource blocks in a frequency band corresponding to channel state information reference signal reception.

[0009] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for determining a low density mode based on a control signal indicating a resource block muting pattern for one or more antenna ports in a set of multiple antenna ports.

[0010] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the resource block muting pattern may be specific to one antenna port in a set of multiple antenna ports, may be specific to a group of antenna ports in a set of multiple antenna ports, or may be common to a set of multiple antenna ports.

[0011] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for determining a low density mode based on a control signal indicating an antenna port muting mode for one or more resource blocks.

[0012] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the antenna port muting pattern may be specific to a resource block, may be specific to a group of resource blocks, or may be common to a set of multiple resource blocks in a frequency band corresponding to channel state information reference signal reception.

[0013] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for determining a low-density mode based on a control signal indicating a cover code that configures a set of multiple antenna port-resource block pairs for channel state information reference signal reception.

[0014] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for determining a channel state information measurement based on an artificial neural network and a set of multiple channel state information reference signals received according to a low density mode, wherein the channel state information report includes the channel state information measurement.

[0015] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for zero-filling a set of multiple received channel state information reference signals based on a low density pattern and inputting the zero-filled set of multiple received channel state information reference signals into an artificial neural network, where the channel state information measurement can be determined based on an output of the artificial neural network.

[0016] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for training an artificial neural network based on a low-density pattern.

[0017] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the control signal includes a bitmap indicating a low density mode for channel state information reference signal reception.

[0018] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the control signal indicates a first number of subsets of a set of multiple antenna ports and a second number of a set of multiple antenna ports, and the methods, apparatus, and non-transitory computer-readable media may include further operations, features, components, or instructions for determining a low-density mode for channel state information reference signal reception based on the first number, the second number, and a rule, a lookup table, or both that maps from the first number and the second number to the low-density mode.

[0019] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for storing a set of multiple low-density patterns, wherein the control signal includes an index value indicating a low-density pattern from the set of multiple low-density patterns.

[0020] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the control signal also includes auxiliary information indicating an antenna configuration, a channel type, environmental information, transmission-related information, or a combination thereof corresponding to a set of multiple antenna ports, and the channel state information report may be further based on the auxiliary information.

[0021] An apparatus for wireless communication at a network entity is described. The apparatus may include a processor and a memory coupled to the processor. The processor may be configured to output a control signal that configures a low-density mode for channel state information reference signal reception at a UE for a set of multiple antenna ports, wherein the low-density mode indicates a subset of the set of multiple antenna ports for channel state information reference signal reception via one or more resource blocks. In some examples, the processor may be configured to output a set of multiple channel state information reference signals according to the low-density mode. In some examples, the processor may be configured to obtain a channel state information report based on the set of multiple channel state information reference signals.

[0022] A method for wireless communication at a network entity is described. The method may include outputting a control signal that configures a low-density pattern for channel state information reference signal reception at a UE for a set of multiple antenna ports, wherein the low-density pattern indicates a subset of the set of multiple antenna ports for channel state information reference signal reception via one or more resource blocks. In some examples, the method may include outputting a set of multiple channel state information reference signals according to the low-density pattern. In some examples, the method may also include obtaining a channel state information report based on the set of multiple channel state information reference signals.

[0023] Another apparatus for wireless communication at a network entity is described. The apparatus may include components for outputting a control signal that configures a low-density pattern for channel state information reference signal reception at a UE for a set of multiple antenna ports, wherein the low-density pattern indicates a subset of the set of multiple antenna ports for channel state information reference signal reception via one or more resource blocks. In a certain example, the apparatus may include components for outputting a set of multiple channel state information reference signals according to the low-density pattern. In some examples, the apparatus may also include components for obtaining a channel state information report based on the set of multiple channel state information reference signals.

[0024] A non-transitory computer-readable medium storing code for wireless communication at a network entity is described. The code may include instructions that are executable by a processor to output a control signal that configures a low-density mode for channel state information reference signal reception at a UE for a set of multiple antenna ports, wherein the low-density mode indicates a subset of the set of multiple antenna ports for channel state information reference signal reception via one or more resource blocks. In some examples, the instructions may be executable by the processor to output a set of multiple channel state information reference signals according to the low-density mode. In some examples, the instructions may also be executable by the processor to obtain a channel state information report based on the set of multiple channel state information reference signals.

[0025] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the control signal includes a bitmap indicating a low density mode for channel state information reference signal reception.

[0026] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the control signal includes a first control signal and indicates a first number of subsets of a set of multiple antenna ports and a second number of sets of multiple antenna ports, and the methods, apparatus, and non-transitory computer-readable media may include further operations, features, components, or instructions for outputting a second control signal configured for mapping a value pair from the first number of subsets of a set of multiple antenna ports and the second number of sets of multiple antenna ports to a rule, a lookup table, or both for a low-density mode.

[0027] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for storing a set of multiple low-density patterns, wherein the control signal includes an index value indicating a low-density pattern from the set of multiple low-density patterns.

[0028] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the control signal also includes auxiliary information indicating an antenna configuration, a channel type, environmental information, transmission-related information, or a combination thereof corresponding to a set of multiple antenna ports, and the channel state information report may be further based on the auxiliary information.

[0029] An apparatus for wireless communication at a device is described. The apparatus may include a processor and a memory coupled to the processor. The processor may be configured to obtain a set of multiple channel state information reference signals for a set of multiple antenna ports and a set of multiple resource blocks. In some examples, the processor may be configured to determine a low density pattern for an artificial neural network training process. In some examples, the processor may be configured to train a generalized artificial neural network based on a subset of the set of multiple channel state information reference signals according to a determined low density pattern, wherein the determined low density pattern indicates a subset of the set of multiple antenna ports for one or more resource blocks in a set of multiple resource blocks. In some examples, the processor may be configured to output a trained generalized artificial neural network.

[0030] A method for wireless communication at a device is described. The method may include obtaining a set of multiple channel state information reference signals for a set of multiple antenna ports and a set of multiple resource blocks. In some examples, the method may include determining a low density pattern for an artificial neural network training process. In some examples, the method may also include training a generalized artificial neural network based on a subset of the set of multiple channel state information reference signals according to the determined low density pattern, wherein the determined low density pattern indicates a subset of the set of multiple antenna ports for one or more resource blocks in the set of multiple resource blocks. In some examples, the method may also include outputting the trained generalized artificial neural network.

[0031] Another apparatus for wireless communication at a device is described. The apparatus may include components for obtaining a set of multiple channel state information reference signals for a set of multiple antenna ports and a set of multiple resource blocks. In some examples, the apparatus may include components for determining a low density pattern for an artificial neural network training process. In some examples, the apparatus may also include components for training a generalized artificial neural network based on a subset of the set of multiple channel state information reference signals according to a determined low density pattern, wherein the determined low density pattern indicates a subset of the set of multiple antenna ports for one or more resource blocks in the set of multiple resource blocks. In some examples, the apparatus may also include components for outputting the trained generalized artificial neural network.

[0032] A non-transitory computer-readable medium storing code for wireless communication at a device is described. The code may include instructions that can be executed by a processor to obtain a set of multiple channel state information reference signals for a set of multiple antenna ports and a set of multiple resource blocks. In some examples, the instructions can be executed by the processor to determine a low-density pattern for an artificial neural network training process. In some examples, the instructions can also be executed by the processor to train a generalized artificial neural network based on a subset of the set of multiple channel state information reference signals according to the determined low-density pattern, wherein the determined low-density pattern indicates a subset of the set of multiple antenna ports for one or more resource blocks in the set of multiple resource blocks. In some examples, the instructions can also be executed by the processor to output a trained generalized artificial neural network.

[0033] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for determining one or more additional low-density patterns for an artificial neural network training process and further training the generalized artificial neural network based on the one or more additional low-density patterns.

[0034] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for randomly selecting one or more low-density patterns, where the low-density patterns may be determined based on the random selection.

[0035] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the determined low density pattern indicates a random selection of a subset of the set of multiple antenna ports for each resource block in the set of multiple resource blocks.

[0036] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the determined low-density pattern indicates a random selection of a subset of a set of multiple antenna ports for a first set of resource blocks in a set of multiple resource blocks, and selection of a subset of a set of multiple antenna ports for a second set of resource blocks in the set of multiple resource blocks may be based on the random selection of a subset of the set of multiple antenna ports for the first set of resource blocks.

[0037] An apparatus for wireless communication at a device is described. The apparatus may include a processor and a memory coupled to the processor. The processor may be configured to obtain a set of multiple channel state information reference signals for a set of multiple antenna ports and a set of multiple resource blocks. In some examples, the processor may be configured to train an artificial neural network specific to one or more low-density modes based on a subset of the set of multiple channel state information reference signals according to one or more low-density modes configured at the device, wherein a low-density mode in the one or more low-density modes indicates a subset of the set of multiple antenna ports for one or more resource blocks in the set of multiple resource blocks. In some examples, the processor may be configured to output the trained artificial neural network.

[0038] A method for wireless communication at a device is described. The method may include obtaining a set of multiple channel state information reference signals for a set of multiple antenna ports and a set of multiple resource blocks. In some examples, the method may include training an artificial neural network specific to one or more low-density modes based on a subset of the set of multiple channel state information reference signals according to one or more low-density modes configured at the device, wherein a low-density mode in the one or more low-density modes indicates a subset of the set of multiple antenna ports for one or more resource blocks in the set of multiple resource blocks. In some examples, the method may also include outputting the trained artificial neural network.

[0039] Another apparatus for wireless communication at a device is described. The apparatus may include components for obtaining a set of multiple channel state information reference signals for a set of multiple antenna ports and a set of multiple resource blocks. In some examples, the apparatus may include components for training an artificial neural network specific to one or more low-density modes based on a subset of the set of multiple channel state information reference signals according to one or more low-density modes configured at the device, wherein a low-density mode in the one or more low-density modes indicates a subset of the set of multiple antenna ports for one or more resource blocks in the set of multiple resource blocks. In some examples, the apparatus may also include components for outputting the trained artificial neural network.

[0040] A non-transitory computer-readable medium storing code for wireless communication at a device is described. The code may include instructions that are executable by a processor to obtain a set of multiple channel state information reference signals for a set of multiple antenna ports and a set of multiple resource blocks. In some examples, the instructions may be executable by the processor to train an artificial neural network specific to one or more low-density modes based on a subset of the set of multiple channel state information reference signals according to one or more low-density modes configured at the device, wherein a low-density mode in the one or more low-density modes indicates a subset of the set of multiple antenna ports for one or more resource blocks in the set of multiple resource blocks. In some examples, the instructions may also be executable by the processor to output the trained artificial neural network.

[0041] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for obtaining a configuration of one or more low-density patterns, wherein an artificial neural network may be trained based on the configuration.

[0042] Some examples of the methods, apparatus, and non-transitory computer-readable media described herein may also include operations, features, components, or instructions for storing one or more low-density patterns at the device, wherein the artificial neural network can be trained based on the stored one or more low-density patterns.

[0043] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, the artificial neural network may be specific to the low-density mode, and the methods, apparatus, and non-transitory computer-readable media may include further operations, features, components, or instructions for training one or more additional artificial neural networks specific to one or more additional low-density modes configured at the device and outputting one or more additional trained artificial neural networks.

[0044] In some examples of the methods, apparatus, and non-transitory computer-readable media described herein, outputting the trained artificial neural network may include operations, features, components, or instructions for outputting the trained artificial neural network and indicating that the trained artificial neural network may be specific to one or more low-density patterns. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 An example of a wireless communication system supporting reference signal pattern association for channel estimation according to one or more aspects of the present disclosure is illustrated.

[0046] Figure 2 An example of a network architecture supporting reference signal pattern association for channel estimation according to one or more aspects of the present disclosure is illustrated.

[0047] Figure 3An example of a wireless communication system supporting reference signal pattern association for channel estimation according to one or more aspects of the present disclosure is illustrated.

[0048] Figure 4 An example of rule-based association supporting a low-density pattern of reference signal pattern association for channel estimation in accordance with one or more aspects of the present disclosure is illustrated.

[0049] Figure 5 An example of a low density mode supporting reference signal pattern association for channel estimation according to one or more aspects of the present disclosure is illustrated.

[0050] Figure 6 An example of a channel estimation process supporting reference signal pattern association for channel estimation according to one or more aspects of the present disclosure is illustrated.

[0051] Figure 7 An example of a machine learning process supporting reference signal pattern association for channel estimation in accordance with one or more aspects of the present disclosure is illustrated.

[0052] Figure 8 An example of a process flow supporting reference signal pattern association for channel estimation in accordance with one or more aspects of the present disclosure is illustrated.

[0053] Fig. 9 and Fig.10 A block diagram of an apparatus supporting reference signal pattern association for channel estimation according to one or more aspects of the present disclosure is shown.

[0054] Fig.11 A block diagram of a communication manager supporting reference signal pattern association for channel estimation is shown in accordance with one or more aspects of the present disclosure.

[0055] Fig.12 A diagram of a system including a device supporting reference signal pattern association for channel estimation is shown in accordance with one or more aspects of the present disclosure.

[0056] Fig.13 and Fig.14 A block diagram of an apparatus supporting reference signal pattern association for channel estimation according to one or more aspects of the present disclosure is shown.

[0057] Fig.15 A block diagram of a communication manager supporting reference signal pattern association for channel estimation is shown in accordance with one or more aspects of the present disclosure.

[0058] Fig.16 A diagram of a system including a device supporting reference signal pattern association for channel estimation is shown in accordance with one or more aspects of the present disclosure.

[0059] Figures 17 to 20 A flow chart illustrating a method of supporting reference signal pattern association for channel estimation according to one or more aspects of the present disclosure is shown. DETAILED DESCRIPTION

[0060] In some wireless communication systems, a network entity (e.g., a base station, a radio unit (RU)) may send a set of channel state information (CSI) reference signals (RS) to support channel estimation by a UE. If the network entity includes multiple antenna ports, the network entity may send the CSI-RS based on a "high density" or "full density" mode, where each antenna port is configured to send the CSI-RS via each frequency resource (e.g., each resource block (RB)) within a frequency range (e.g., a channel bandwidth, a subband, a bandwidth part (BWP)). The UE may receive the CSI-RS and may use the received CSI-RS to perform channel estimation. Using this high density mode for the CSI-RS may support relatively fine-grained CSI measurements by the UE. However, using a subset of antenna ports, a subset of frequency resources, or both to communicate CSI-RS, rather than using each antenna port via each frequency resource, may improve the channel overhead associated with CSI-RS, may improve the processing overhead associated with sending CSI-RS at a network entity and associated with receiving and processing CSI-RS at a UE, or some combination thereof.

[0061] As described herein, a network entity and a UE may implement a "low density" mode for CSI-RS communication to reduce the number of CSI-RS used for channel estimation. The low density mode may indicate a subset of the total number of antenna ports used for CSI-RS communication (e.g., transmission by the network entity and reception by the UE), a subset of the total number of RBs in a frequency range used for CSI-RS communication, or both. The low density mode may be different from a high density mode, which may indicate the total number of antenna ports used for CSI-RS communication and the total number of RBs in a frequency range used for CSI-RS communication. Thus, sending CSI-RS according to the low density mode may involve the network entity sending a subset of CSI-RS, compared to sending a complete set of CSI-RS corresponding to each antenna port and each RB for the high density mode. The network entity may send a control signal to the UE, the control signal configuring the low density mode for CSI-RS reception at the UE. The network entity may additionally send a set of multiple CSI-RS according to the low density mode. The UE may determine the low density mode based on the control signal, and may use the low density mode to receive and process the CSI-RS sent by the network entity. The UE may send a CSI report to a network entity, the CSI report including channel estimation parameters or other CSI measurements determined based on processing the CSI-RS. In some examples, the UE may use an artificial neural network (which may be simply referred to as a neural network in some cases) to process the CSI-RS for channel estimation. In some cases, the UE may train a generalized neural network, for example, to process CSI-RS sent according to any low-density mode selected by the network entity. In some other cases, the UE may train one or more neural networks specific to one or more low-density modes (such as a set of low-density modes configured at the UE). The trained neural network may support estimating the full channel (e.g., for a total set of antenna ports and a total set of RBs) using a subset of CSI-RS received via a subset of antenna ports, a subset of RBs, or both for the channel.

[0062] Various aspects of the subject matter described herein may be implemented by a device that supports improved processing complexity and improved channel overhead associated with CSI-RS communication. For example, a network entity may choose to use a low-density mode to reduce the number of CSI-RS sent via a channel, thereby effectively improving channel overhead. In addition, the network entity may improve the processing overhead associated with generating and sending CSI-RS at the network entity. Similarly, the UE may improve the processing overhead associated with receiving and processing CSI-RS at the UE based on the use of a low-density mode. For example, the UE may receive and process a reduced number of CSI-RS for channel estimation. By coordinating the low-density mode used (e.g., via control signaling issued by the network entity), the network entity and the UE may use the same low-density mode and improve CSI-RS reception and processing at the UE based on the coordination. Additionally or alternatively, the UE may use a subset of CSI-RS to train a neural network for channel estimation according to the low-density mode. The UE may improve the accuracy of channel estimation based on one or more neural networks trained to process the low-density mode of the CSI-RS and may improve communication reliability and performance. For example, the UE may accurately perform channel estimation on the channel using a reduced number of CSI-RSs transmitted via the channel.

[0063] As described herein, a low-density mode for CSI-RS communication may indicate a set of antenna ports, a set of RBs, or both, via which the CSI-RS is communicated (e.g., sent by a network entity, received by a UE). The mode may be "low-density" based on the number of antenna ports used for CSI-RS transmission being less than the total number of antenna ports at the network entity, the number of RBs used for CSI-RS transmission being less than the total number of RBs within a frequency range (e.g., channel bandwidth, subband, bandwidth part (BWP)) used for CSI-RS transmission, or some combination thereof. In some examples, a control signal configuring the low-density mode may indicate a muting mode (e.g., an RB muting mode, an antenna port muting mode), and the UE may determine the low-density mode based on the muting mode. The muting mode may be an example of an array or other bit field indicating a resource set suppressed for CSI-RS communication. For example, an RB muting mode may indicate which RBs the network entity suppresses for CSI-RS transmission (e.g., for each antenna port or for a set of antenna ports), and an antenna port muting mode may indicate which antenna ports the network entity suppresses for CSI-RS transmission (e.g., for each RB or for a set of RBs). Additionally or alternatively, the control signal configuring the low density mode may indicate a cover code, and the UE may determine the low density mode based on the cover code. The cover code may be an example of a matrix or other bit field for multiplexing CSI-RS to transmit a CSI-RS subset. For example, the cover code may include a number of bits equal to the total number of antenna ports multiplied by the total number of RBs, and each bit of the cover code may indicate whether a particular antenna port-RB pair is configured for CSI-RS communication.

[0064] The UE may determine a CSI measurement based on the received CSI-RS. In some examples, the CSI measurement may be an example of a reference signal received power (RSRP) of the CSI-RS, a reference signal received quality (RSRQ) of the CSI-RS, a signal-to-noise ratio (SNR) of the CSI-RS, or any other parameter associated with measuring the strength or quality of the received CSI-RS. Additionally or alternatively, the CSI measurement may be an example of a channel estimation parameter to be included in the CSI report, such as channel quality information (CQI), a precoding matrix indicator (PMI), a layer indicator (LI), a rank indicator (RI), or any other channel estimation parameter. In some examples, the UE may use an artificial neural network to perform channel estimation using a low-density pattern of the CSI-RS. The artificial neural network may be an example of any machine learning model trained to perform channel estimation according to one or more low-density patterns. For example, the artificial neural network may be an example of a feedforward (FF) or deep feedforward (DFF) neural network, a recurrent neural network (RNN), a long / short-term memory (LSTM) neural network, or any other type of neural network trained for channel estimation. The UE may use zero padding to pre-process the received CSI-RS before using the artificial neural network. Zero padding may be an example of a technique for increasing the array size according to a specific pattern. For example, the UE may receive a subset of CSI-RS and may use zero padding to map the number of received CSI-RS to the correct antenna ports and RBs for transmitting the CSI-RS in a total set of antenna ports and a total set of RBs. The UE may use a low-density pattern to appropriately map the received CSI-RS to the antenna ports and RBs, thereby effectively increasing the array size from the number of received CSI-RS to the number of total antenna ports multiplied by the number of total RBs in the frequency range. Zero padding may involve adding zero values ​​to specific positions of the array (e.g., positions corresponding to antenna ports and RB pairs that suppress transmitting CSI-RS) according to a low-density pattern to obtain an array of a size that can be used for channel estimation (e.g., by an artificial neural network) for a complete set of antenna ports and RBs. In some examples, the artificial neural network may use the increased array size as an input size for processing the CSI-RS.

[0065] Various aspects of the disclosure are first described in the context of a wireless communication system. Various aspects of the disclosure are also described in the context of a low density mode, a channel estimation process, a machine learning process, and a process flow. Various aspects of the disclosure are further illustrated by and described with reference to apparatus diagrams, system diagrams, and flow charts associated with reference signal patterns for channel estimation.

[0066] Figure 1An example of a wireless communication system 100 supporting reference signal pattern association for channel estimation according to one or more aspects of the present disclosure is illustrated. The wireless communication system 100 may include one or more network entities 105, one or more UEs 115, and a core network 130. In some examples, the wireless communication system 100 may be a Long Term Evolution (LTE) network, an Advanced LTE (LTE-A) network, an LTE-A Pro network, a New Radio (NR) network, or a network operating according to other systems and radio technologies, including future systems and radio technologies not explicitly mentioned herein.

[0067] The network entities 105 may be dispersed throughout a geographic area to form the wireless communication system 100, and may include devices in different forms or with different capabilities. In various examples, the network entities 105 may be referred to as network elements, mobility elements, radio access network (RAN) nodes, or network equipment, among other nomenclature. In some examples, the network entities 105 and the UE 115 may communicate wirelessly via one or more communication links 125 (e.g., radio frequency (RF) access links). For example, the network entity 105 may support a coverage area 110 (e.g., a geographic coverage area) within which the UE 115 and the network entity 105 may establish one or more communication links 125. The coverage area 110 may be an example of a geographic area within which the network entity 105 and the UE 115 may support signal communications according to one or more radio access technologies (RATs).

[0068] The UEs 115 may be dispersed throughout the coverage area 110 of the wireless communication system 100, and each UE 115 may be stationary or mobile or both stationary and mobile at different times. The UEs 115 may be devices in different forms or with different capabilities. Figure 1 Some example UEs 115 are illustrated in FIG. 1. The UEs 115 described herein may be capable of supporting communication with various types of devices such as Figure 1 Other UEs 115 or network entities 105 are shown communicating.

[0069] As described herein, a node of the wireless communication system 100 (which may be referred to as a network node or a wireless node) may be a network entity 105 (e.g., any network entity described herein), a UE 115 (e.g., any UE described herein), a network controller, an apparatus, a device, a computing system, one or more components, or another suitable processing entity configured to perform any of the techniques described herein. For example, the node may be a UE 115. As another example, the node may be a network entity 105. As another example, a first node may be configured to communicate with a second node or a third node. In one aspect of this example, the first node may be a UE 115, the second node may be a network entity 105, and the third node may be a UE 115. In another aspect of this example, the first node may be a UE 115, the second node may be a network entity 105, and the third node may be a network entity 105. In other aspects of this example, the first node, the second node, and the third node may be different relative to these examples. Similarly, references to UE 115, network entity 105, apparatus, device, computing system, etc. may include disclosure of UE 115, network entity 105, apparatus, device, computing system, etc. as nodes. For example, a disclosure that UE 115 is configured to receive information from network entity 105 also discloses that the first node is configured to receive information from a second node.

[0070] Consistent with the present disclosure, once a specific example is expanded according to the present disclosure (e.g., a UE is configured to receive information from a base station and it is also disclosed that a first network node is configured to receive information from a second network node), a broader example of a narrower example can be interpreted inversely, but in a broad, open-ended manner. In the above example where a UE is configured to receive information from a network entity and it is also disclosed that a first network node is configured to receive information from a second network node, the first network node may refer to a first UE configured to receive information, a first base station, a first device, a first equipment, a first computing system, a first one or more components, a first processing entity, etc.; and the second network node may refer to a second UE, a second base station, a second device, a second equipment, a second computing system, a second one or more components, a second processing entity, etc.

[0071] As described herein, different terms may be used in various aspects to describe the communication of information (e.g., any information, signal, etc.). Disclosure of one communication term includes disclosure of other communication terms. For example, a first network node may be described as being configured to send information to a second network node. In this example and consistent with the present disclosure, disclosure that the first network node is configured to send information to the second network node includes disclosure that the first network node is configured to provide, transmit, output, communicate, or send information to the second network node. Similarly, in this example and consistent with the present disclosure, disclosure that the first network node is configured to send information to the second network node includes disclosure that the second network node is configured to receive, obtain, or decode information provided, transmitted, output, communicated, or sent by the first network node.

[0072] In some examples, the network entities 105 may communicate with the core network 130, or with each other, or both. For example, the network entities 105 may communicate with the core network 130 via one or more backhaul communication links 120 (e.g., according to S1, N2, N3, or other interface protocols). In some examples, the network entities 105 may communicate with each other via the backhaul communication links 120 (e.g., according to X2, Xn, or other interface protocols) directly (e.g., directly between the network entities 105) or indirectly (e.g., via the core network 130). In some examples, the network entities 105 may communicate with each other via the midhaul communication links 162 (e.g., according to the midhaul interface protocol) or the fronthaul communication links 168 (e.g., according to the fronthaul interface protocol) or any combination thereof. The backhaul communication links 120, the midhaul communication links 162, or the fronthaul communication links 168 may be or include one or more wired links (e.g., electrical links, optical fiber links), one or more wireless links (e.g., radio links, wireless optical links), etc. or various combinations thereof. UE 115 may communicate with core network 130 via communication link 155 .

[0073] One or more of the network entities 105 described herein may include or may be referred to as a base station 140 (e.g., a transceiver base station, a radio base station, an NR base station, an access point, a radio transceiver, a Node B, an evolved Node B (eNB), a next-generation Node B, or a Gigabit Node B (any of which may be referred to as a gNB), a 5G NB, a next-generation eNB (ng-eNB), a Home Node B, a Home Evolved Node B, or other suitable terms). In some examples, the network entity 105 (e.g., a base station 140) may be implemented in an aggregated (e.g., monolithic, stand-alone) base station architecture, which may be configured to utilize a protocol stack physically or logically integrated within a single network entity 105 (e.g., a single RAN node, such as a base station 140).

[0074] In some examples, the network entity 105 may be implemented in a disaggregated architecture (e.g., a disaggregated base station architecture, a disaggregated RAN architecture) that may be configured to utilize a protocol stack that is physically or logically distributed between two or more network entities 105, such as an integrated access backhaul (IAB) network, an open RAN (O-RAN) (e.g., a network configuration sponsored by the O-RAN Alliance), or a virtualized RAN (vRAN) (e.g., a cloud RAN (C-RAN)). For example, the network entity 105 may include one or more of the following: a central unit (CU) 160, a distributed unit (DU) 165, a RU 170, a RAN intelligent controller (RIC) 175 (e.g., a near real-time RIC (near RT RIC), a non-real-time RIC (non-RT RIC)), a service management and orchestration (SMO) 180 system, or any combination thereof. The RU 170 may also be referred to as a radio head, a smart radio head, a remote radio head (RRH), a remote radio unit (RRU), or a transmit receive point (TRP). One or more components of the network entity 105 in the decomposed RAN architecture may be co-located, or one or more components of the network entity 105 may be located in distributed locations (e.g., separate physical locations). In some examples, one or more network entities 105 of the decomposed RAN architecture may be implemented as virtual units (e.g., virtual CU (VCU), virtual DU (VDU), virtual RU (VRU)).

[0075] The functional split between CU 160, DU 165, and RU 170 is flexible and may support different functionalities depending on which functions (e.g., network layer functions, protocol layer functions, baseband functions, RF functions, and any combination thereof) are performed at CU 160, DU 165, or RU 170. For example, a functional split of a protocol stack may be employed between CU 160 and DU 165 such that CU 160 may support one or more layers of a protocol stack and DU 165 may support one or more different layers of a protocol stack. In some examples, CU 160 may host higher protocol layer (e.g., layer 3 (L3), layer 2 (L2)) functionality and signaling (e.g., radio resource control (RRC), service data adaptation protocol (SDAP), packet data convergence protocol (PDCP)). The CU 160 may be connected to one or more DUs 165 or RUs 170, and the one or more DUs 165 or RUs 170 may host lower protocol layers, such as layer 1 (L1) (e.g., physical (PHY) layer) or L2 (e.g., radio link control (RLC) layer, medium access control (MAC) layer) functionality and signaling, and may each be at least partially controlled by the CU 160. Additionally or alternatively, a functional split of the protocol stack may be employed between the DUs 165 and RUs 170, such that the DUs 165 may support one or more layers of the protocol stack, and the RUs 170 may support one or more different layers of the protocol stack. The DUs 165 may support one or more different cells (e.g., via one or more RUs 170). In some cases, the functional split between CU 160 and DU 165 or between DU 165 and RU 170 may be within the protocol layer (e.g., some functions of the protocol layer may be performed by one of CU 160, DU 165, or RU 170, while other functions of the protocol layer are performed by different ones of CU 160, DU 165, or RU 170). CU 160 may also be functionally split into CU control plane (CU-CP) and CU user plane (CU-UP) functions. CU 160 may be connected to one or more DUs 165 via midhaul communication links 162 (e.g., F1, F1-c, F1-u), and DU 165 may be connected to one or more RUs 170 via fronthaul communication links 168 (e.g., open fronthaul (FH) interface). In some examples, midhaul communication link 162 or fronthaul communication link 168 may be implemented based on an interface (e.g., a channel) between layers of a protocol stack supported by respective network entities 105 that communicate via such communication links.

[0076] In some wireless communication systems (e.g., wireless communication system 100), infrastructure and spectrum resources for radio access may support wireless backhaul link capabilities to supplement wired backhaul connections, thereby providing an IAB network architecture (e.g., to core network 130). In some cases, in an IAB network, one or more network entities 105 (e.g., IAB nodes 104) may be partially controlled by each other. One or more IAB nodes 104 may be referred to as donor entities or IAB donors. One or more DUs 165 or one or more RUs 170 may be controlled in part by one or more CUs 160 associated with a donor network entity 105 (e.g., donor base station 140). One or more donor network entities 105 (e.g., IAB donors) may communicate with one or more additional network entities 105 (e.g., IAB nodes 104) via supported access and backhaul links (e.g., backhaul communication links 120). The IAB node 104 may include an IAB mobile terminal (IAB-MT) controlled (e.g., scheduled) by a coupled IAB donor's DU 165. The IAB-MT may include an independent set of antennas for relaying communications with the UE 115, or may share the same antennas of the IAB node 104 (e.g., of the RU 170) for access via the DU 165 of the IAB node 104 (e.g., referred to as a virtual IAB-MT (vIAB-MT)). In some examples, the IAB node 104 may include a DU 165 that supports communication links with additional entities (e.g., IAB node 104, UE 115) within a relay chain or configuration (e.g., downstream) of the access network. In such cases, one or more components of the decomposed RAN architecture (e.g., one or more IAB nodes 104 or components of the IAB node 104) may be configured to operate according to the techniques described herein.

[0077] In the case where the techniques described herein are applied to the context of a decomposed RAN architecture, one or more components of the decomposed RAN architecture may be configured to support reference signal pattern association for channel estimation as described herein. For example, some operations described as being performed by a UE 115 or a network entity 105 (e.g., a base station 140) may additionally or alternatively be performed by one or more components of the decomposed RAN architecture (e.g., an IAB node 104, a DU 165, a CU 160, a RU 170, a RIC 175, a SMO 180).

[0078] UE 115 may include or may be referred to as a mobile device, a wireless device, a remote device, a handheld device, or a subscriber device, or some other suitable term, where a "device" may also be referred to as a unit, a station, a terminal, or a client, etc. UE 115 may also include or may be referred to as a personal electronic device, such as a cellular phone, a personal digital assistant (PDA), a tablet computer, a laptop computer, or a personal computer. In some examples, UE 115 may include or may be referred to as a wireless local loop (WLL) station, an Internet of Things (IoT) device, an Internet of Everything (IoE) device, or a machine type communication (MTC) device, etc., which may be implemented in various objects such as appliances or vehicles, meters, etc.

[0079] The UE 115 described herein may be capable of communicating with various types of devices, such as other UEs 115, which may sometimes act as relays, as well as network entities 105 and network equipment including macro eNBs or gNBs, small cell eNBs or gNBs, or relay base stations, etc. Figure 1 shown.

[0080] The UE 115 and the network entity 105 may wirelessly communicate with each other via one or more communication links 125 (e.g., access links) using resources associated with one or more carriers. The term "carrier" may refer to a collection of RF spectrum resources having a physical layer structure defined for supporting the communication link 125. For example, a carrier for the communication link 125 may include a portion of an RF spectrum band (e.g., a BWP) that operates according to one or more physical layer channels for a given radio access technology (e.g., LTE, LTE-A, LTE-A Pro, NR). Each physical layer channel may carry acquisition signaling (e.g., synchronization signals, system information), control signaling for coordinating carrier operations, user data, or other signaling. The wireless communication system 100 may support communications with the UE 115 using carrier aggregation or multi-carrier operation. Depending on the carrier aggregation configuration, the UE 115 may be configured to have multiple downlink component carriers and one or more uplink component carriers. Carrier aggregation may be used for both frequency division duplex (FDD) and time division duplex (TDD) component carriers. Communication between the network entity 105 and other devices may refer to communication between these devices and any portion (e.g., entity, sub-entity) of the network entity 105. For example, the terms "send," "receive," or "communicate" when referring to the network entity 105 may refer to any portion of a network entity 105 (e.g., base station 140, CU 160, DU 165, RU 170) of the RAN communicating with another device (e.g., directly or via one or more other network entities 105).

[0081] The signal waveform transmitted via the carrier may include multiple subcarriers (e.g., using multi-carrier modulation (MCM) techniques, such as orthogonal frequency division multiplexing (OFDM) or discrete Fourier transform spread OFDM (DFT-S-OFDM)). In a system employing MCM techniques, a resource element may refer to a resource of one symbol period (e.g., the duration of one modulation symbol) and one subcarrier, in which case the symbol period and subcarrier spacing may be inversely related. The amount of bits carried by each resource element may depend on the modulation scheme (e.g., the order of the modulation scheme, the coding rate of the modulation scheme, or both), so that a relatively higher amount of resource elements (e.g., in the transmission duration) and a relatively higher modulation scheme order may correspond to a relatively higher communication rate. Wireless communication resources may refer to a combination of RF spectrum resources, time resources, and spatial resources (e.g., spatial layers or beams), and the use of multiple spatial resources may increase the data rate or data integrity used for communication with UE 115.

[0082] The time interval for the network entity 105 or the UE 115 may be expressed in multiples of a basic time unit, which may be, for example, a sampling period T s =1 / (Δf max ·N f ) seconds, where Δf max It can represent the supported subcarrier spacing, and N f The supported discrete Fourier transform (DFT) size may be indicated. Time intervals of the communication resources may be organized according to radio frames, each having a specified duration (e.g., 10 milliseconds (ms)). Each radio frame may be identified by a system frame number (SFN) (e.g., ranging from 0 to 1023).

[0083] Each frame may include multiple consecutively numbered subframes or time slots, and each subframe or time slot may have the same duration. In some examples, the frame may be divided into subframes (e.g., in the time domain), and each subframe may be further divided into a certain number of time slots. Alternatively, each frame may include a variable number of time slots, and the number of time slots may depend on the subcarrier spacing. Each time slot may include a certain number of symbol periods (e.g., depending on the length of the cyclic prefix appended in front of each symbol period). In some wireless communication systems 100, the time slot may be further divided into multiple mini-time slots associated with one or more symbols. Excluding the cyclic prefix, each symbol period may be associated with one or more (e.g., N f The duration of a symbol period may depend on the subcarrier spacing or the operating frequency band.

[0084] A subframe, a time slot, a mini-time slot, or a symbol may be the smallest scheduling unit (e.g., in the time domain) of the wireless communication system 100 and may be referred to as a transmission time interval (TTI). In some examples, the TTI duration (e.g., the amount of symbol periods in a TTI) may be variable. Additionally or alternatively, the smallest scheduling unit of the wireless communication system 100 may be dynamically selected (e.g., in a burst of a shortened TTI (sTTI)).

[0085] According to various techniques, physical channels may be multiplexed using carriers for communication. Physical control channels and physical data channels may be multiplexed for signaling via downlink carriers, for example, using one or more of a time division multiplexing (TDM) technique, a frequency division multiplexing (FDM) technique, or a hybrid TDM-FDM technique. A control region (e.g., a control resource set (CORESET)) of a physical control channel may be defined by a set of symbol periods and may extend across a system bandwidth of a carrier or a subset of that system bandwidth. One or more control regions (e.g., CORESETs) may be configured for a set of UEs 115. For example, one or more UEs in UE 115 may monitor or search a control region to obtain control information according to one or more search space sets, and each search space set may include one or more control channel candidates in one or more aggregation levels arranged in a cascaded manner. The aggregation level of a control channel candidate may refer to the amount of control channel resources (e.g., control channel elements (CCEs)) associated with coded information for a control information format having a given payload size. The search space sets may include a common search space set configured for transmitting control information to multiple UEs 115 , and a UE-specific search space set for transmitting control information to a specific UE 115 .

[0086] In some examples, the network entities 105 (e.g., base stations 140, RUs 170) may be mobile and thus provide communication coverage for mobile coverage areas 110. In some examples, different coverage areas 110 associated with different technologies may overlap, but the different coverage areas 110 may be supported by the same network entity 105. In some other examples, overlapping coverage areas 110 associated with different technologies may be supported by different network entities 105. The wireless communication system 100 may include, for example, a heterogeneous network in which different types of network entities 105 provide coverage for various coverage areas 110 using the same or different radio access technologies.

[0087] The wireless communication system 100 may be configured to support ultra-reliable communication or low-latency communication or various combinations thereof. For example, the wireless communication system 100 may be configured to support ultra-reliable low-latency communication (URLLC). UE 115 may be designed to support ultra-reliable or low-latency or critical functions. Ultra-reliable communication may include private communication or group communication, and may be supported by one or more services (such as push-to-talk, video, or data). Support for ultra-reliable, low-latency functions may include prioritization of services, and such services may be used for public safety or general commercial applications. The terms "ultra-reliable", "low latency", and "ultra-reliable low latency" are used interchangeably herein.

[0088] In some examples, a UE 115 may be configured to support communication directly with other UEs 115 via a device-to-device (D2D) communication link 135 (e.g., according to a peer-to-peer (P2P), D2D, or sidelink protocol). In some examples, one or more UEs 115 in a group that are performing D2D communication may be within a coverage area 110 of a network entity 105 (e.g., a base station 140, a RU 170), which may support aspects of such D2D communication configured by the network entity 105 (e.g., scheduled by the network entity). In some examples, one or more UEs 115 in such a group may be outside the coverage area 110 of the network entity 105, or may otherwise be unable or not configured to receive transmissions from the network entity 105. In some examples, a group of UEs 115 communicating via D2D communication may support a one-to-many (1:M) system, in which each UE 115 transmits to each of the other UEs 115 in the group. In some examples, network entity 105 may facilitate scheduling of resources for D2D communications. In some other examples, D2D communications may be performed between UEs 115 without involving network entity 105.

[0089] The core network 130 may provide user authentication, access authorization, tracking, Internet Protocol (IP) connectivity, and other access, routing, or mobility functions. The core network 130 may be an evolved packet core (EPC) or a 5G core (5GC), which may include at least one control plane entity (e.g., a mobility management entity (MME), an access and mobility management function (AMF)) for managing access and mobility and at least one user plane entity (e.g., a serving gateway (S-GW), a packet data network (PDN) gateway (P-GW), or a user plane function (UPF)) for routing packets or interconnecting to an external network. The control plane entity may manage non-access layer (NAS) functions, such as mobility, authentication, and bearer management of UE 115 served by a network entity 105 (e.g., a base station 140) associated with the core network 130. User IP packets may be delivered through the user plane entity, which may provide IP address allocation and other functions. The user plane entity may be connected to the IP service 150 of one or more network operators. IP services 150 may include access to the Internet, an intranet, an IP Multimedia Subsystem (IMS), or packet-switched streaming services.

[0090] The wireless communication system 100 may operate using one or more frequency bands that may be in the range of 300 megahertz (MHz) to 300 gigahertz (GHz). The 300 MHz to 3 GHz region may be referred to as the ultra-high frequency (UHF) region or decimeter band because the wavelengths are in the range of from about 1 decimeter to 1 meter long. UHF waves may be blocked or redirected by buildings and environmental features (which may be referred to as clusters), but these waves may be sufficient to penetrate structures so that macro cells provide service to UEs 115 located indoors. Communications using UHF waves may be associated with smaller antennas and shorter ranges (e.g., less than 100 kilometers) than communications using smaller frequencies and longer waves in the high frequency (HF) or very high frequency (VHF) portions of the spectrum below 300 MHz.

[0091] The wireless communication system 100 can utilize licensed and unlicensed RF spectrum bands. For example, the wireless communication system 100 can use unlicensed bands (such as the 5 GHz Industrial, Scientific, and Medical (ISM) band) to employ license assisted access (LAA), LTE unlicensed (LTE-U) radio access technology, or NR technology. When operating using unlicensed RF spectrum bands, devices such as network entity 105 and UE 115 can employ carrier sensing for conflict detection and avoidance. In some examples, operations using unlicensed bands can be based on carrier aggregation configuration (e.g., LAA) in combination with component carriers operating using licensed bands. Operations using unlicensed spectrum may include downlink transmissions, uplink transmissions, P2P transmissions, or D2D transmissions, and the like.

[0092] The electromagnetic spectrum is typically subdivided into various categories, bands, channels, etc. based on frequency / wavelength. In 5G NR, two initial operating bands have been identified as frequency range designations 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, FR1 is often (interchangeably) referred to as the “sub-6 GHz” band in various documents and articles. A similar naming issue sometimes occurs with respect to FR2, which is often (interchangeably) referred to as the “millimeter wave” band in documents and articles, although different from the extremely high frequency (EHF) band (30 GHz–300 GHz) identified as the “millimeter wave” band by the International Telecommunication Union (ITU).

[0093] Frequencies between FR1 and FR2 are generally referred to as mid-band frequencies. Recent 5G NR research has identified the operating bands for these mid-band frequencies as frequency range designation FR3 (7.125GHz–24.25GHz). The bands falling within FR3 can inherit FR1 characteristics or FR2 characteristics, and thus the features of FR1 or FR2 can be effectively extended to mid-band frequencies. In addition, higher frequency bands are currently being explored to extend 5G NR operations to more than 52.6GHz. For example, three higher operating bands have been identified as frequency range designations FR4a or FR4–1 (52.6GHz–71GHz), FR4 (52.6GHz–114.25GHz), and FR5 (114.25GHz–300GHz). Each of these higher frequency bands falls within the EHF band.

[0094] In view of the above aspects, unless otherwise specifically stated, it should be understood that if the term "below 6 GHz" or the like is used in this document, it can be broadly referred to as a frequency that may be less than 6 GHz, may be within FR1, or may include mid-band frequencies. In addition, unless otherwise specifically stated, it should be understood that if the term "millimeter wave" or the like is used in this document, it can be broadly referred to as a frequency that may include mid-band frequencies, may be within FR2, FR4, FR4-a or FR4-1 or FR5, or may be within the EHF band.

[0095] The network entity 105 (e.g., base station 140, RU 170) or UE 115 may be equipped with multiple antennas that can be used to employ technologies such as transmit diversity, receive diversity, multiple-input multiple-output (MIMO) communication, or beamforming. The antennas of the network entity 105 or UE 115 may be located in one or more antenna arrays or antenna panels, which may support MIMO operations or transmit or receive beamforming. For example, one or more base station antennas or antenna arrays may be co-located at an antenna assembly such as an antenna tower. In some examples, antennas or antenna arrays associated with the network entity 105 may be located at different geographical locations. The network entity 105 may include an antenna array having a collection of multiple rows and columns of antenna ports that the network entity 105 can use to support beamforming for communications with the UE 115. Similarly, the UE 115 may include one or more antenna arrays that may support various MIMO or beamforming operations. Additionally or alternatively, the antenna panel may support RF beamforming for signals sent via the antenna ports.

[0096] The network entity 105 or UE 115 may use MIMO communication to utilize multipath signal propagation and improve spectral efficiency by sending or receiving multiple signals via different spatial layers. Such a technique may be referred to as spatial multiplexing. The multiple signals may be sent, for example, by a transmitting device via different antennas or different combinations of antennas. Similarly, the multiple signals may be received by a receiving device via different antennas or different combinations of antennas. Each of the multiple signals may be referred to as a separate spatial stream and may carry information associated with the same data stream (e.g., the same codeword) or different data streams (e.g., different codewords). Different spatial layers may be associated with different antenna ports for channel measurement and reporting. MIMO techniques include: single-user MIMO (SU-MIMO), in which multiple spatial layers are sent to the same receiving device; and multi-user MIMO (MU-MIMO), in which multiple spatial layers are sent to multiple devices.

[0097] Beamforming (which may also be referred to as spatial filtering, directional transmission, or directional reception) is a signal processing technique that may be used at a transmitting device or a receiving device (e.g., a network entity 105, a UE 115) to shape or direct an antenna beam (e.g., a transmit beam, a receive beam) along a spatial path between the transmitting device and the receiving device. Beamforming may be achieved by combining signals conveyed via antenna elements of an antenna array so that some signals propagating along a particular orientation relative to the antenna array experience constructive interference, while other signals experience destructive interference. Adjustments to signals conveyed via antenna elements may include the transmitting device or the receiving device applying an amplitude offset, a phase offset, or both to signals carried via antenna elements associated with the device. Adjustments associated with each of these antenna elements may be defined by a set of beamforming weights associated with a particular orientation (e.g., relative to the antenna array of the transmitting device or the receiving device or relative to some other orientation).

[0098] The network entity 105 or UE 115 may use beam scanning techniques as part of a beamforming operation. For example, the network entity 105 (e.g., base station 140, RU 170) may use multiple antennas or antenna arrays (e.g., antenna panels) to perform beamforming operations for directional communication with UE 115. Some signals (e.g., synchronization signals, reference signals, beam selection signals, or other control signals) may be sent multiple times by the network entity 105 along different directions. For example, the network entity 105 may send signals according to different sets of beamforming weights associated with different transmission directions. Transmissions along different beam directions may be used to identify (e.g., by a transmitting device (such as network entity 105), or by a receiving device (such as UE 115)) beam directions for later transmission or reception by the network entity 105.

[0099] Some signals, such as data signals associated with a particular receiving device, may be sent by a transmitting device (e.g., transmitting network entity 105, transmitting UE 115) along a single beam direction (e.g., a direction associated with a receiving device (such as receiving network entity 105 or receiving UE 115)). In some examples, a beam direction associated with transmission along a single beam direction may be determined based on signals sent along one or more beam directions. For example, UE 115 may receive one or more of the signals sent by network entity 105 along different directions, and may report to network entity 105 an indication of the signal received by UE 115 with the highest signal quality or other acceptable signal quality.

[0100] In some examples, transmission by a device (e.g., by network entity 105 or UE 115) may be performed using multiple beam directions, and the device may use a combination of digital precoding or beamforming to generate a combined beam for transmission (e.g., from network entity 105 to UE 115). UE 115 may report feedback indicating precoding weights for one or more beam directions, and the feedback may correspond to a configured set of beams across a system bandwidth or one or more subbands. Network entity 105 may send reference signals (e.g., cell-specific reference signals (CRS), CSI-RS) that may be precoded or uncoded. UE 115 may provide feedback for beam selection, which may be PMI or codebook-based feedback (e.g., multi-panel codebook, linear combination codebook, port selection codebook). Although these techniques are described with reference to signals sent along one or more directions by a network entity 105 (e.g., base station 140, RU 170), UE 115 may use similar techniques to send signals multiple times along different directions (e.g., to identify a beam direction for subsequent transmission or reception by UE 115), or to send signals along a single direction (e.g., to send data to a receiving device).

[0101] A receiving device (e.g., UE 115) may perform receiving operations according to multiple receiving configurations (e.g., directional listening) when receiving various signals (such as synchronization signals, reference signals, beam selection signals, or other control signals) from a receiving device (e.g., network entity 105). For example, the receiving device may perform reception according to multiple receiving directions by: receiving via different antenna subarrays, processing received signals according to different antenna subarrays, receiving according to different receiving beamforming weight sets (e.g., different directional listening weight sets) applied to signals received at multiple antenna elements of an antenna array, or processing received signals according to different receiving beamforming weight sets applied to signals received at multiple antenna elements of an antenna array, any of which may be referred to as "listening" according to different receiving configurations or receiving directions. In some examples, the receiving device may use a single receiving configuration to receive along a single beam direction (e.g., when receiving a data signal). A single receive configuration may be aligned along a beam direction determined based on listening according to different receive configuration directions (e.g., a beam direction determined to have the highest signal strength, highest signal-to-noise ratio (SNR), or other acceptable signal quality based on listening according to multiple beam directions).

[0102] The wireless communication system 100 may be a packet-based network operating according to a layered protocol stack. In the user plane, communications at the bearer or PDCP layer may be IP-based. The RLC layer may perform packet segmentation and reassembly to communicate via logical channels. The MAC layer may perform priority handling and multiplexing of logical channels into transport channels. The MAC layer may also implement error detection techniques, error correction techniques, or both to support retransmission to improve link efficiency. In the control plane, the RRC layer may provide the establishment, configuration, and maintenance of an RRC connection for a radio bearer supporting user plane data between the UE 115 and the network entity 105 or the core network 130. The PHY layer may map transport channels to physical channels.

[0103] UE 115 and network entity 105 may support retransmission of data to increase the likelihood that the data is successfully received. Hybrid automatic repeat request (HARQ) feedback is a technique for increasing the likelihood of correctly receiving data via a communication link (e.g., communication link 125, D2D communication link 135). HARQ may include a combination of error detection (e.g., using a cyclic redundancy check (CRC)), forward error correction (FEC), and retransmission (e.g., automatic repeat request (ARQ)). HARQ may improve throughput at the MAC layer under poor radio conditions (e.g., low signal-to-noise ratio conditions). In some examples, a device may support same-slot HARQ feedback, in which case the device may provide HARQ feedback in a specific slot for data received in a previous symbol in the slot. In some other examples, the device may provide HARQ feedback in a subsequent slot or according to some other time interval.

[0104] The wireless communication system 100 may support CSI measurement based on CSI-RS transmission. For example, the network entity 105 (e.g., the base station 140 or other network entity 105 including multiple antenna ports) may transmit a set of multiple CSI-RS via a channel. In some examples, the network entity 105 may transmit the CSI-RS via each frequency resource (e.g., RB) of the channel bandwidth, subband, or BWP using each antenna port. The UE 115 may receive the CSI-RS and may perform channel measurement using the CSI-RS (e.g., based on RSRP of the CSI-RS, SNR of the CSI-RS, or any other signal metric). The UE 115 may determine one or more CSI parameters such as CQI, PMI, LI, RI, or any other CSI parameter based on the channel measurement. The UE 115 may send a CSI report including the determined CSI parameters to the network entity 105, and the UE 115 and the network entity 105 may communicate based on the information included in the CSI report.

[0105] However, sending CSI-RS via each RB using each antenna port may involve significant processing overhead (e.g., at the network entity 105 that sends the CSI-RS and at the UE 115 that receives and measures the CSI-RS), significant channel overhead, or both. In order to improve the processing overhead and channel overhead associated with CSI-RS transmission, the network entity 105 may use a "low density" mode to send CSI-RS (e.g., a subset of CSI-RS). The low density mode may be configured for a subset of antenna ports for sending CSI-RS, a subset of RBs via which CSI-RS is sent, or a combination thereof. In order to support the low density mode, the network entity 105 (e.g., using the communication manager 102) may send a control signal configuring the low density mode for the UE 115 so that the UE 115 (e.g., using the communication manager 101) may receive the transmitted CSI-RS using the low density mode. Additionally or alternatively, UE 115 (e.g., communications manager 101 or another component or device) may train an artificial neural network (which may be referred to simply as a neural network) to process low-density patterns of CSI-RS and determine channel measurements for the full channel based on the transmitted CSI-RS subset.

[0106] Figure 2 An example of a network architecture 200 supporting reference signal pattern association for channel estimation according to one or more aspects of the present disclosure is illustrated. The network architecture 200 may be an example of a decomposed base station architecture or a decomposed RAN architecture. The network architecture 200 may illustrate an example for implementing one or more aspects of the wireless communication system 100. The network architecture 200 may include one or more CUs 160-a, which may communicate directly with the core network 130-a via a backhaul communication link 120-a, or indirectly communicate with the core network 130-a through one or more decomposed network entities 105 (e.g., a near RT RIC 175-b via an E2 link or a non-RT RIC 175-a associated with an SMO 180-a (e.g., an SMO framework), or both. The CU 160-a may communicate with one or more DUs 165-a via a corresponding midhaul communication link 162-a (e.g., an F1 interface). The DU 165-a may communicate with one or more RUs 170-a via a corresponding fronthaul communication link 168-a. The RU 170-a may be associated with a respective coverage area 110-a and may communicate with the UE 115-a via one or more communication links 125-a. In some implementations, the UE 115-a may be served by multiple RUs 170-a simultaneously.

[0107] Each of the network entities 105 of the network architecture 200 (e.g., CU 160-a, DU 165-a, RU 170-a, non-RT RIC 175-a, near-RT RIC 175-b, SMO 180-a, open cloud (O-Cloud) 205, open eNB (O-eNB) 210) may include one or more interfaces or may be coupled to one or more interfaces configured to receive or send signals (e.g., data, information) via a wired or wireless transmission medium. Each network entity 105 or an associated processor (e.g., a controller) that provides instructions to an interface of the network entity 105 may be configured to communicate with one or more of the other network entities 105 via a transmission medium. For example, these network entities 105 may include a wired interface that is configured to receive signals on a wired transmission medium or to send signals to one or more of the other network entities 105 on a wired transmission medium. Additionally or alternatively, the network entity 105 may include a wireless interface, which may include a receiver, transmitter, or transceiver (e.g., an RF transceiver) configured to receive signals on a wireless transmission medium, or to send signals to one or more of the other network entities 105 on a wireless transmission medium, or both.

[0108] In some examples, CU 160-a may host one or more higher layer control functions. Such control functions may include RRC, PDCP, SDAP, etc. Each control function may be implemented using an interface that is configured to communicate signals with other control functions hosted by CU 160-a. CU 160-a may be configured to handle user plane functions (e.g., CU-UP), control plane functions (e.g., CU-CP), or a combination thereof. In some examples, CU 160-a 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 unit may communicate bidirectionally with the CU-CP unit via an interface (such as an E1 interface). As needed, CU 160-a may be implemented to communicate with DU 165-a for network control and signaling.

[0109] DU 165-a may correspond to a logical unit that includes one or more functions (e.g., base station functions, RAN functions) for controlling the operation of one or more RUs 170-a. In some examples, DU 165-a may at least partially host one or more of the RLC layer, the MAC layer, and one or more aspects of the PHY layer (e.g., a high PHY layer, such as modules for FEC encoding and decoding, scrambling, modulation and demodulation, etc.), which depends at least in part on functional divisions, such as those defined by the Third Generation Partnership Project (3GPP). In some examples, DU 165-a may also host one or more low PHY layers. Each layer may be implemented using an interface that is configured to communicate signals with other layers hosted by DU 165-a or with control functions hosted by CU160-a.

[0110] In some examples, lower layer functions may be implemented by one or more RUs 170-a. For example, a RU 170-a controlled by a DU 165-a may correspond to a logical node that hosts RF processing functions or low PHY layer functions (e.g., performing fast Fourier transform (FFT), inverse FFT (iFFT), digital beamforming, physical random access channel (PRACH) extraction and filtering, etc.) or both based at least in part on functional splitting (such as lower layer functional splitting). In this architecture, RU 170-a may be implemented to handle over-the-air (OTA) communications with one or more UEs 115-a. In some specific implementations, real-time and non-real-time aspects of control plane and user plane communications with RU 170-a may be controlled by the corresponding DU 165-a. In some examples, this configuration may enable DU 165-a and CU 160-a to be implemented in a cloud-based RAN architecture (such as a vRAN architecture).

[0111] The SMO 180-a may be configured to support RAN deployment and provisioning of non-virtualized and virtualized network entities 105. For non-virtualized network entities 105, the SMO 180-a may be configured to support the deployment of dedicated physical resources for RAN coverage requirements, which may be managed via an operation and maintenance interface (e.g., an O1 interface). For virtualized network entities 105, the SMO 180-a may be configured to interact with a cloud computing platform (e.g., O-Cloud 205) via a cloud computing platform interface (e.g., an O2 interface) to perform network entity lifecycle management (e.g., to instantiate virtualized network entities 105). Such virtualized network entities 105 may include, but are not limited to, CU 160-a, DU 165-a, RU 170-a, and near-RT RIC 175-b. In some specific implementations, the SMO 180-a may communicate with components configured according to a 4G RAN (e.g., via an O1 interface). Additionally or alternatively, in some implementations, the SMO 180-a may communicate directly with one or more RUs 170-a via an O1 interface. The SMO 180-a may also include a non-RT RIC 175-a configured to support the functionality of the SMO 180-a.

[0112] The non-RT RIC 175-a may be configured to include logic functions that implement non-real-time control and optimization of RAN elements and resources, artificial intelligence (AI) or machine learning (ML) workflows (including model training and updating, or policy-based guidance of applications / features in the near-RT RIC 175-b). The non-RT RIC 175-a may be coupled to or communicate with the near-RT RIC 175-b (e.g., via an A1 interface). The near-RT RIC 175-b may be configured to include logic functions that implement near real-time control and optimization of RAN elements and resources via data collection and actions on an interface connecting one or more CUs 160-a, one or more DUs 165-a, or both, and the O-eNB 210 to the near-RT RIC 175-b (e.g., via an E2 interface).

[0113] In some examples, in order to generate an AI / ML model to be deployed in the near-RT RIC 175-b, the non-RT RIC 175-a may receive parameters or external enrichment information from an external server. Such information may be utilized by the near-RT RIC 175-b and may be received from a non-network data source or from a network function at the SMO 180-a or the non-RT RIC 175. In some examples, the non-RT RIC 175-a or the near-RT RIC 175-b may be configured to tune RAN behavior or performance. For example, the non-RT RIC 175-a may monitor long-term trends and patterns of performance and employ an AI model or ML model to perform corrective actions through the SMO 180-a (e.g., via reconfiguration of O1) or via the generation of a RAN management policy (such as an A1 policy).

[0114] One or more network entities 105 may support a CSI process. For example, RU 170-a may support a set of multiple antenna ports for conveying signaling. RU 170-a may use antenna ports to transmit a set of multiple CSI-RS, for example, according to a low-density mode for CSI-RS transmission. In addition, RU 170-a may receive CSI reports from one or more UEs 115-a. RU 170-a, DU 165-a, CU 160-a, or any combination thereof may process the CSI reports to determine communication parameters for communicating with one or more UEs 115-a.

[0115] Figure 3 An example of a wireless communication system 300 that supports reference signal pattern association for channel estimation according to one or more aspects of the present disclosure is illustrated. The wireless communication system 300 may be implemented by aspects of the wireless communication system 100, the network architecture 200, or both. For example, the wireless communication system 300 may include a UE 115-b and a network entity 105-a, which may be a reference signal pattern association. Figure 1 and Figure 2 An example of a UE 115 and a network entity 105 is described. The wireless communication system 300 may support the network entity 105-a to configure the UE 115-b with a low density mode 315 for CSI-RS reception. The UE 115-b may receive a set of CSI-RS 330 using the configured low density mode 315 and perform CSI measurements using the CSI-RS 330.

[0116] In the wireless communication system 300, the network entity 105-a may send one or more CSI-RS 330 via a channel (e.g., a downlink channel 305) to support channel estimation of the channel (e.g., the downlink channel 305). The UE 115-b may receive the CSI-RS 330 and may use the received CSI-RS 330 to measure one or more characteristics of the channel. The UE 115-b may determine one or more parameters associated with modulation, code rate, beamforming, or other CSI aspects, and may report the one or more parameters to the network entity 105-a using a CSI report 340. In some cases, the UE 115-b may perform one or more CSI measurements 390 on the received CSI-RS 330, and may include the one or more CSI measurements 390 in the CSI report 340.

[0117] In some examples, CSI-RS 330 may be sent, received, or both based on a density pattern. The density pattern may indicate which antenna ports are configured to send CSI-RS via which frequency resources (e.g., RBs, RB groups, subcarriers). The network entity 105-a may communicate using a set of multiple antenna ports 325. The antenna ports 325 may correspond to (e.g., according to a one-to-one mapping or a one-to-many mapping) physical antenna elements of an antenna array, such as a uniform planar array (UPA) (e.g., an antenna panel) or some other antenna configuration. For example, a specific set of logical antenna ports 325 mapped to one or more physical antenna elements may be used for transmission. The antenna array may include one or more columns of antenna elements and one or more rows of antenna elements, and each antenna element may support multiple (e.g., two) polarizations for signaling. The antenna elements of the antenna array may also be logically configured into subgroups (e.g., subarrays). For example, a subgroup may span antenna elements in a row of the antenna array. For example, a 2x2 antenna array (e.g., an antenna array having two rows and two columns of antenna elements, each antenna element supporting two polarizations) may support a set of eight antenna ports 325 and may include two subsets corresponding to the two rows. In some examples, the density pattern may be the same for different polarizations. For example, the density pattern may specify CSI-RS transmissions for four antenna ports based on a density pattern applied across polarizations, such that a four-antenna port pattern defines CSI-RS transmissions for a total of eight antenna ports (e.g., four antenna ports with a first polarization and four antenna ports with a second polarization).

[0118] In some implementations, the network entity 105-a can transmit CSI-RS 330 via the channel based on a "high density" or "full density" mode, where each antenna port is configured to transmit CSI-RS 330 via each frequency resource (e.g., RB) within a set of frequency resources (e.g., channel bandwidth, subband, BWP). Such a high density mode can provide relatively fine-grained CSI measurements for the channel.

[0119] However, in order to save network power, reduce signaling overhead (e.g., CSI-RS 330 overhead), or both, the network entity 105-a may use a "low density" mode for CSI-RS 330 transmission. Compared to the high density mode, the low density mode 315 may reduce the number of CSI-RS 330 transmitted, thereby effectively reducing the processing overhead and channel overhead associated with the CSI-RS transmission. The low density mode 315 may indicate a subset 345 of antenna ports used for CSI-RS transmission via one or more frequency resources (e.g., RBs). The low density mode 315 in the spatial domain may indicate that the number of antenna ports used to transmit the CSI-RS 330 is less than the total number of antenna ports configured at the network entity 105-a. For example, the low density mode 315 may indicate that two of the four antenna ports will be used for CSI-RS transmission in the spatial domain. Additionally or alternatively, the low density pattern 315 in the frequency domain may indicate that the number of RBs used to transmit the CSI-RS 330 is less than the total number of RBs used for CSI-RS transmission (e.g., corresponding to the channel bandwidth, subband, BWP). For example, the low density pattern 315 may indicate that two of the four RBs will be used for CSI-RS transmission in the frequency domain.

[0120] The low-density pattern 315 may indicate that two antenna ports (e.g., a subset of antenna ports 345) out of a total of four antenna ports (e.g., all antenna ports 325) for each RB of the bandwidth are used to transmit the CSI-RS 330. For example, the low-density pattern 315 may indicate that the CSI-RS 330 is transmitted via the first RB 320-a using the first antenna port 325-a and the fourth antenna port 325-d, via the second RB 320-b using the third antenna port 325-c and the fourth antenna port 325-d, via the third RB 320-c using the first antenna port 325-a and the second antenna port 325-b, and via the fourth RB 320-d using the first antenna port 325-a and the third antenna port 325-c. In some examples, configuring CSI-RS 330 transmission for the first antenna port 325-a via the first RB 320-a can effectively configure CSI-RS 330 transmission for two polarizations corresponding to the first antenna port 325-a via the first RB 320-a. This low density pattern 315 can reduce CSI-RS overhead by approximately half. Additionally or alternatively, the network entity 105-a sending CSI-RS 330 according to this low density pattern 315, the UE 115-b receiving and processing CSI-RS 330 according to this low density pattern 315, or both can reduce CSI-RS processing overhead by approximately half.

[0121] The network entity 105-a may send a control signal 310 to the UE 115-b via the downlink channel 305 to configure a low-density pattern 315 for CSI-RS reception at the UE 115-b for a set of multiple antenna ports 325. The low-density pattern 315 may indicate a subset 345 of the multiple antenna ports used for CSI-RS reception via one or more RBs. For example, the control signal 310 may indicate an association between a set of antenna ports that transmit the CSI-RS 330 (e.g., a first set of antenna ports, such as the subset 345 of antenna ports used for CSI-RS reception) and a total set of antenna ports 325 configured at the network entity 105-a (e.g., a second set of antenna ports).

[0122] In some implementations, the association between the first set of antenna ports (e.g., a subset of antenna ports 345) and the second set of antenna ports (e.g., a total set of antenna ports 325) may include transmit position information that maps the first set of antenna ports to a subset of the second set of antenna ports. For example, the control signal 310 may indicate a mapping 355 from the subset of antenna ports 345 used for CSI-RS transmission to the full set of antenna ports 325 used for one or more RBs, and the UE 115-b may determine the low-density mode 315 based on the mapping 355. In some cases, the mapping may be specific to an RB (e.g., RB-specific), or specific to an RB group (e.g., RB-group-specific), or common to a set of multiple RBs in a frequency band. For example, the same subset of antenna ports may be configured for CSI-RS transmission within one RB or one RB group, or the same subset of antenna ports may be used commonly for CSI-RS transmission across RBs.

[0123] In some implementations, the association between the first set of antenna ports and the second set of antenna ports can be based on an RB muting pattern for each antenna port in the second set of antenna ports (e.g., the total set of antenna ports 325). For example, the control signal 310 can include a muting pattern 360 for RBs for one or more antenna ports in the full set of antenna ports 325, and the UE 115-b can use the muting pattern 360 to determine the low density mode 315. In some examples, the RB muting pattern can be specific 392 to one antenna port in the total set of antenna ports 325 (e.g., port-specific), or specific 392 to a group of antenna ports in the total set of antenna ports 325 (e.g., port-group-specific), or common 394 across the total set of antenna ports 325. For example, the muting pattern 360 may mute RB 320-b for antenna port 325-a to indicate that the network entity 105-a may use antenna port 325-a to send CSI-RS 330 via RB 320-a, RB 320-c, and RB 320-d (e.g., refrain from using antenna port 325-a to send CSI-RS via RB 320-b). Figure 3 As illustrated, muting pattern 360 may indicate different RB muting patterns for antenna port 325 - b , antenna port 325 - c , and antenna port 325 - d .

[0124] In some implementations, the association between the first set of antenna ports and the second set of antenna ports may be based on an antenna port muting pattern for each RB (e.g., within a channel bandwidth, subband, BWP). For example, the control signal 310 may include a muting pattern 360 for the antenna ports of one or more RBs, and the UE 115-b may use the muting pattern 360 to determine the low density mode 315. In some examples, the antenna port muting pattern may be specific 392 to an RB (e.g., RB specific), or specific 392 to an RB group (e.g., RB group specific), or common 394 across RBs in a frequency band. For example, the muting pattern 360 may mute the antenna port 325-b and the antenna port 325-c for the RB 320-a to indicate that the network entity 105-a may send the CSI-RS 330 via the RB 320-a using the antenna port 325-a and the antenna port 325-d (e.g., refrain from sending the CSI-RS via the RB 320-a using the antenna port 325-b and the antenna port 325-c). Figure 3 As illustrated, muting pattern 360 may indicate different antenna port muting patterns for RB 320-b, RB 320-c, and RB 320-d.

[0125] In some implementations, the association between the first set of antenna ports and the second set of antenna ports may include a cover code that maps each antenna port in the second set of antenna ports (e.g., the total set of antenna ports 325 at the network entity 105-a) to a resource element (RE) of a first set of RBs (e.g., RBs for CSI-RS transmission). For example, the control signal 310 may include a cover code as a 2-dimensional (2D) pattern or array, where a first value in the array (e.g., a "1" bit value) may configure CSI-RS transmission, and a second value in the array (e.g., a "0" bit value) may indicate suppression of transmission of CSI-RS. Each value in the array may be mapped to an antenna port-RB pair. For example, a first value in a first row of the array may be set to "1", indicating that the first antenna port 325-a is configured to transmit CSI-RS via the first RB 320-a. A second value in a first row of the array may be set to "0", indicating that the second antenna port 325-b is configured to suppress transmission of CSI-RS via the first RB 320-a. The UE 115 - b may use a cover code to determine a low density pattern 315 for CSI-RS transmissions (eg, the network entity 105 - a transmitting CSI-RS may use a cover code to multiplex the CSI-RS transmissions).

[0126] The network entity 105-a may configure an association between a first set of antenna ports (e.g., a subset 345 of antenna ports) and a second set of antenna ports (e.g., a total set of antenna ports 325) via any control signaling. For example, the network entity 105-a may indicate a configuration 350 of the low-density mode 315 to the UE 115-a using RRC signaling, MAC-CE, DCI signaling, or any other control signaling. In some examples, the network entity 105-a may indicate a parameter value associated with the low-density mode 315. For example, the control signal 310 may include a P value 370 indicating the number of antenna ports in the first set of antenna ports (e.g., a subset 345 of antenna ports configured for CSI-RS transmission and reception). Additionally or alternatively, the control signal 310 may include a Q value 375 indicating the number of antenna ports in the second set of antenna ports (e.g., a total set of antenna ports configured at the network entity 105-a).

[0127] In some examples, the control signal 310 may use a bitmap 365 to indicate a P value 370 and a Q value 375, and a low-density mode 315 for CSI-RS transmission and reception using the indicated P value 370. Additionally or alternatively, the P value 370 and the Q value 375 may define the size of the bitmap 365 for configuring the low-density mode 315. For example, if the mapping is RB-common for transmission position information or antenna port muting mode, the bitmap 365 may have a size of Q, where the P value (e.g., a "1" bit value) in the bitmap 365 indicates the location of the active P antenna port for CSI-RS transmission. If the mapping is RB-specific for transmission position information or antenna port muting mode, the bitmap 365 may have a size of Q×N_RB, where N_RB indicates the number of RBs used for CSI-RS transmission. The bitmap 365 may include P×N_RB values ​​(e.g., a "1" bit value) indicating the location of the active P antenna port for each RB used for CSI-RS transmission. Similarly, if the mapping is antenna port specific for the RB muting pattern, the bitmap 365 may have a size of Q×N_RB and may include P×N_RB values ​​(e.g., a “1” bit value) indicating the location of the active RB for each antenna port. The network entity 105-a may use the bitmap 365 to indicate support for any low density mode 315 for CSI-RS transmission.

[0128] Additionally or alternatively, the UE 115-b may determine the low density mode 315 based on the P value 370 and the Q value 375 (e.g., the P value 370 and the Q value 375 indicated by the control signal 310) using a rule, a lookup table, or other metric or heuristic. The rule, lookup table, or other metric or heuristic may map each {P, Q} pair to a corresponding low density mode 315. In some examples, the network entity 105-a may configure the rule, lookup table, or other metric or heuristic to the UE 115-b, for example, using control signaling (e.g., RRC signaling). In some other examples, the UE 115-b may be pre-configured with the rule, lookup table, or other metric or heuristic. The UE 115-b may receive the control signal 310 indicating the P value 370, the Q value 375, or both, and may determine the low density mode 315 based on the rule, lookup table, or other metric or heuristic and the indicated P value 370, the Q value 375, or both.

[0129] In some examples, the network entity 105 may select any low-density mode 315 for CSI-RS transmission, and may indicate the selected low-density mode 315 via the control signal 310. In some cases, the low-density mode 315 may be uniform, non-uniform, RB-common, RB-specific, randomized, structured random, or any combination thereof. In some other examples, the network entity 105 may select the low-density mode 315 from a set of low-density mode options configured at the network entity 115-a, the UE 105-b, or both. In some such examples, the low-density mode 315 (e.g., mode options) may be stored with corresponding index values ​​assigned to each mode. In some cases, the control signal 310 may use the index value to indicate which low-density mode 315 to use in a set of multiple low-density mode options configured at the UE 115-a. In some examples, the network entity 105-a may additionally use control signaling to configure the low-density mode option for the UE 115-b.

[0130] In some examples, the network entity 105-a may include additional assistance information 380 in the control signal 310 to configure the low density mode 315. The UE 115-b may use the additional assistance information 380 to improve channel estimation, determine CSI-RS resource configuration, or both. In some cases, the additional assistance information 380 may indicate an antenna configuration at the network entity 105-a, an antenna layout at the network entity 105-a, an antenna element to a transmit radio unit (TxRU) mapping at the network entity 105-a, analog / digital precoding information for the network entity 105-a, or any combination thereof. Additionally or alternatively, the additional assistance information 380 may include a meta information identifier (e.g., for metadata), and the corresponding meta information (e.g., environmental information) may be provided by the network entity 105-a via higher layer signaling (e.g., location management function (LMF) signaling). In some cases, the additional assistance information 380 may indicate a transmission correlation with a reference signal (e.g., quasi co-location (QCL) information with a tracking reference signal (TRS)). In some cases, the transmit correlation may be for a TRS corresponding to a full antenna port transmission associated with a relatively long periodicity and a relatively low bandwidth.

[0131] UE 115-b may receive control signal 310 and determine the indicated low density mode 315 based on the content of control signal 310. Network entity 105-a may send a set of multiple CSI-RS 330 via downlink channel 305 according to the indicated low density mode 315. UE 115-b may receive CSI-RS 330 via subset of antenna ports 345 and may map CSI-RS 330 to the total set of antenna ports 325 based on low density mode 315 (e.g., association between subset of antenna ports 345 and the total set of antenna ports 325). In some cases, UE 115-b may determine a channel for the total set of antenna ports 325 based on CSI measurements of subset of antenna ports 345 and association between subset of antenna ports 345 and the total set of antenna ports 325.

[0132] In some examples, the UE 115-b may use a neural network 385 to determine a channel estimate using a subset of the received CSI-RS 330 (e.g., CSI-RS corresponding to a subset 345 of antenna ports for CSI-RS reception). For example, the wireless communication system 300 may use machine learning techniques (e.g., artificial intelligence (AI) techniques) to perform CSI-RS optimization (e.g., AI-based CSI-RS optimization). In some aspects, CSI-RS optimization may enable the UE 115-b to use a low-density mode 315 to perform channel estimation and provide CSI feedback. In some examples, the UE 115-b may determine CSI measurements based on the neural network 385 and receiving a set of multiple CSI-RS 330 associated with the low-density mode 315. In some examples, the UE 115-b may send a CSI report 340 to the network entity 105-a via an uplink channel 335. The CSI report 340 may include one or more CSI measurements 390 determined by the UE 115-b.

[0133] Figure 4 An example of a rule-based association 400 for supporting a low-density mode for reference signal pattern association for channel estimation in accordance with one or more aspects of the present disclosure is illustrated. The rule-based association 400 may be implemented by aspects of the wireless communication system 100, the network architecture 200, the wireless communication system 300, or any combination thereof. For example, the rule-based association 400 illustrates possible rules for determining a low-density mode based on a P value (e.g., a subset of antenna ports used for CSI-RS communication), a Q value (e.g., a total set of antenna ports at the network entity 105), or both. As described herein with reference to Figures 1 to 3 As described, the UE 115, the network entity 105, or both may use the rule-based association 400 to determine the same low-density pattern.

[0134] The network entity 105 may include an antenna array 405 (e.g., a UPA) that includes a plurality of antenna elements 435, wherein each antenna element 435 may also include two polarizations, namely a first polarization 410-a and a second polarization 410-b. In some examples, the antenna elements 435 may correspond to different antenna ports 415 for communicating at the network entity 105. For example, the antenna array 405 may support N1 columns of antenna elements 435 and N2 rows of antenna elements 435, and for these two polarizations, the antenna array 405 may support N1×N2×2 antenna ports 415 (e.g., the first antenna port 415 may be mapped to the first polarization 410-a of the first antenna element 435). Each row of antenna elements 435 may be referred to as a subgroup or subarray of antenna elements. In some examples, the low density mode may be the same for these two polarizations. Therefore, the bitmap may use N1×N2 bits for each RB 425 to indicate the low density mode.

[0135] For example, the antenna array 405 of the network entity 105 may include four columns and four rows of antenna elements 435, such that N1=4, N2=4. Therefore, for both polarizations, the antenna array 405 may support a Q value of 32, indicating a total of 32 antenna ports 415 (e.g., for both polarizations). If the network entity 105 uses a low density mode to reduce the CSI-RS overhead by half, the network entity 105 may configure a P value of 16. If the same mode is used for both polarizations, the network entity 105 may indicate eight of the sixteen bits in the bitmap to indicate the resources configured for CSI-RS transmission 430. The antenna array 405 may include four subgroups of size four each, namely, subgroup 420-a, subgroup 420-b, subgroup 420-c, and subgroup 420-d. The network entity 105 may configure four RBs 425 for CSI-RS transmission, namely, RB 425 - a , RB 425 - b , RB 425 - c , and RB 425 - d .

[0136] The network entity 105 may send a control signal indicating the P value and the Q value to the UE 115. The UE 115 may receive the P value and the Q value and may use a rule to determine a low density pattern corresponding to a particular {P, Q} pair. In some cases, the network entity 105 may use the same rule to ensure that the network entity 105 and the UE 115 use the same low density pattern for CSI-RS transmission and CSI-RS reception, respectively.

[0137] If P / 2>N1 (e.g., if the number of antenna ports 415 selected for RB 425 is greater than the number of antenna ports 415 in the subgroup), UE 115 and network entity 105 may use a basic transmit position rule. For the first subgroup 420-a, the rule may configure each antenna port 415 of the first subgroup 420-a to transmit CSI-RS. For the rest of the N2-1 subgroup, according to the basic transmit position rule, if Then the rule may configure one antenna port 415 per subgroup. The antenna port 415 of each subgroup may be α, where 0≤α≤N1-1. For example, the antenna port 415 with index 1 may be configured to transmit CSI-RS in the second subgroup 420-b, the third subgroup 420-c, and the fourth subgroup 420-d. According to the basic transmission position rule, if The rule may then configure one antenna port 415 (α) per subgroup and one or more additional antenna ports 415 (α+1) per subgroup to satisfy the number P of antenna ports configured for CSI-RS transmission. For example, the antenna port 415 with index 2 may be configured to transmit CSI-RS in the second subgroup 420-b, so that P=8 antenna ports are configured for CSI-RS transmission 430 of the first RB 425-a. The remaining 8 antenna ports may suppress CSI-RS transmission 440 of the first RB 425-a.

[0138] The UE 115 and the network entity 105 may use the RB shifting rule to determine the antenna ports 415 configured for CSI-RS transmission 430 of other RBs 425. For example, for the next RB 425-b, the positions of the antenna ports 415 configured for CSI-RS transmission 430 in the first subgroup 420-a may be shifted by N1. For example, the subgroup of each antenna port 415 configured to transmit CSI-RS may be shifted by N1 to correspond to the second subgroup 420-b. For the other N2-1 subgroups, the positions of the antenna ports 415 configured for CSI-RS transmission 430 may be shifted by N1+1 (e.g., to shift to different antenna port indices). Thus, based on α and α+1, the antenna port 415 with index 2 may be configured to transmit CSI-RS in the third subgroup 420-c, the fourth subgroup 420-d, and the first subgroup 420-a (e.g., wrapped from the fourth subgroup 420-d of the first RB 425-a), and the antenna port 415 with index 3 may be configured to transmit CSI-RS in the third subgroup 420-c, such that P=8 antenna ports are configured for CSI-RS transmission 430 of the second RB 425-b. Using such rules for RB 425-c and RB 425-d, the UE 115 and the network entity 105 may determine the antenna ports configured for CSI-RS transmission 430 and the antenna ports configured to suppress CSI-RS transmission 440. Based on such rules, the device may determine a low density mode for CSI-RS transmission based on a Q value, a P value, an N1 value, an N2 value, or some combination thereof, which may be indicated via control signaling. Additionally or alternatively, the UE 115 and the network entity 105 may store a lookup table to map from any combination of Q, P, N1, and N2 values ​​to a low density mode.

[0139] Figure 5 An example of a low-density pattern 500 supporting reference signal pattern association for channel estimation according to one or more aspects of the present disclosure is illustrated. The low-density pattern 500 may be implemented by aspects of the wireless communication system 100, the network architecture 200, the wireless communication system 300, or any combination thereof. For example, the network entity 105 may select a low-density pattern for CSI-RS transmission from a set of low-density patterns 500, and the UE 115 may be configured with the selected low-density pattern. The network entity 105 and the UE 115 may be as described herein with reference to Figures 1 to 4 Examples of corresponding network entities 105 and UEs 115 are described.

[0140] Different low density modes 500 may correspond to different performance levels and different complexities. In some examples, low density mode 500 may be executed at different levels (e.g., relatively high performance level, relatively low performance level) depending on the configuration of the mode (e.g., a specific type of low density mode). Figure 5 A low density pattern 500 using a block array having columns representing a plurality of antenna ports and rows representing a plurality of RBs is illustrated. For example, the low density pattern 500 may correspond to the number of antenna ports (e.g., nTx), where the first column represents a first antenna port having an index of 0, the second column represents a second antenna port having an index of 1, the third column represents a third antenna port having an index of 2, up to the total number of antenna ports. Additionally, the low density pattern 500 may correspond to the number of frequency resources (e.g., RBs) across a frequency range, where the first row represents a first frequency resource (e.g., a first RB), the second row represents a second frequency resource (e.g., a second RB), up to the total number of RBs for the frequency range.

[0141] The low density pattern 505 can be an example of a uniform and RB-shared low density pattern. The low density pattern 505 can be uniform based on the resources configured for CSI-RS transmission 535 being uniformly spaced according to a pattern (e.g., even antenna ports configured for CSI-RS transmission 535, odd antenna ports configured for suppressing CSI-RS transmission). For example, the low density pattern 505 can indicate that the first antenna port with index 0, the third antenna port with index 2, the fifth antenna port with index 4, and the seventh antenna port with index 6 in the total set of antenna ports will be configured for CSI-RS transmission 535. In addition, the low density pattern 505 can be RB-shared, so that each antenna port can be configured to operate the low density pattern across the set of RBs (e.g., transmit or suppress transmission of CSI-RS for each RB). The low density pattern 505 can support relatively low configuration complexity and latency based on the uniform and RB-shared nature of the low density pattern 505 (e.g., a relatively small number of bits can be used to configure the low density pattern 505).

[0142] The low-density pattern 510 may be an example of a non-uniform and RB-shared low-density pattern. The low-density pattern 510 may be non-uniform based on a pattern having inconsistent spacing between resources configured for CSI-RS transmission 535. For example, the low-density pattern 510 may indicate that antenna ports with indices 0, 3, 4, and 7 are configured for CSI-RS transmission 535. Similar to the low-density pattern 505, the low-density pattern 510 may be RB-shared so that each antenna port may be configured to operate the low-density mode across the set of RBs (e.g., transmit or suppress transmission of CSI-RS for each RB). Based on the non-uniformity of the low-density pattern 510, the low-density pattern 510 may support relatively higher performance (e.g., improved channel estimation) than the low-density pattern 505.

[0143] The low-density pattern 515 can be an example of a uniform and RB-specific low-density pattern. The low-density pattern 515 can be uniform based on the resources configured for CSI-RS transmission 535 being uniformly spaced according to a pattern. For example, antenna ports with even indexes can be configured for CSI-RS transmission 535 via RBs with even indexes, and antenna ports with odd indexes can be configured for CSI-RS transmission 535 via RBs with odd indexes. In addition, the low-density pattern 515 can be RB-specific, so that the antenna ports can be configured to operate differently for different RBs (for example, the first antenna port can transmit CSI-RS via even RBs but not via odd RBs). Based on the RB specificity of the low-density pattern 515, the low-density pattern 515 can support relatively higher performance than the low-density pattern 505.

[0144] Low-density pattern 520-a may be an example of a non-uniform and RB-specific low-density pattern. In some examples, pattern 520-a may be defined as a randomized pattern in which there is no pattern for CSI-RS transmission between antenna ports and RBs. In some cases, in order to generate pattern 520-a, the device may randomly or pseudo-randomly select the number of antenna ports (e.g., L antenna ports) from the total set of antenna ports for each RB. This random selection process may cause different antenna ports to transmit CSI-RS via different numbers of RBs. For example, pattern 520-a may include different antenna ports configured with different frequency domain densities. As illustrated, the first antenna port may be configured to transmit CSI-RS via three RBs, while the sixth antenna port may be configured to transmit CSI-RS via one RB. In some examples, the device may use a random non-uniform and RB-specific low-density pattern to train a neural network for channel estimation. Based on the RB specificity of low-density mode 520 - a , low-density mode 520 - a may support relatively higher performance than low-density mode 510 , and based on the non-uniformity of low-density mode 520 - a , low-density mode 520 - a may support relatively higher performance than low-density mode 515 .

[0145] Pattern 520-b may be another example of a non-uniform and RB-specific low-density pattern. In some examples, pattern 520-b may be defined as a structured random pattern (e.g., a specific pattern, a dedicated pattern) for CSI-RS transmission. Pattern 520-b may include the same frequency domain density for each antenna port (e.g., a frequency domain density equal to 0.5 for each port). For example, each antenna port may be configured to transmit CSI-RS via the same number of RBs (e.g., three). Pattern 520-b may be defined as a randomized pattern because there is no pattern for transmission between antenna ports and RBs. In some examples, RB sets may be grouped together. For example, a first RB 525-a with an index of 0 and a second RB 525-b with an index of 1 may be grouped together to form a group 530. In some cases, in order to construct a random pattern, the low-density pattern 520-b may include multiple antenna ports that may be configured for CSI-RS transmission 535 once per group 530. In some cases, to generate pattern 520-b, the device may randomly or pseudo-randomly select the number of antenna ports (e.g., L antenna ports) from the total set of antenna ports for the first RB 525-a of group 530. To ensure consistent frequency domain density, the device may select other antenna ports for the second RB 525-b that are not selected for the first RB 525-a, rather than using a random process to select antenna ports for the second RB 525-b of group 530. In some examples, the network entity 105 may use a structured random non-uniform and RB-specific low-density pattern for CSI-RS transmission.

[0146] Figure 6 An example of a channel estimation process 600 supporting reference signal pattern association for channel estimation in accordance with one or more aspects of the present disclosure is illustrated. The wireless communication system 100, the network architecture 200, the wireless communication system 300, or a combination thereof may implement the channel estimation process 600. For example, the UE 115 may use the channel estimation process 600 to process CSI-RS 605 received according to the low density pattern 610. The UE 115 or another training device or entity may train one or more neural networks 625 to support the channel estimation process 600. The UE 115 may use the neural network 625 to determine a full channel measurement (e.g., a channel measurement corresponding to each antenna port and each RB in the frequency range) based on a reduced set of CSI-RS 605 (e.g., transmitted according to the low density pattern 610).

[0147] A device (such as a UE 115 or another training device or entity) may train a neural network 625 (e.g., an artificial neural network, a machine learning model, an artificial intelligence (AI) system) to handle CSI-RS 605 received according to the low density pattern 610. In some examples, the UE 115 and the network entity 105 may jointly design a bilateral model for channel estimation. For example, the network entity 105 may determine a non-orthogonal cover code for multiplexing the CSI-RS 605, and the UE 115 may use machine learning techniques to determine the neural network 625 for channel estimation. In some other examples, the UE 115 may design a unilateral model for channel estimation. For example, the UE 115 may train the neural network 625 for channel estimation using machine learning techniques independently of the network entity 105.

[0148] In some examples, a device (e.g., UE 115, a component of UE 115, another training device) may train a generalized neural network for CSI-RS processing. The generalized neural network may be trained to handle processing of CSI-RS sent using any low density pattern 610 selected by the network entity 105. The UE 115 may use the generalized neural network to adapt to different low density patterns 610. For example, a network entity 105 that sends CSI-RS 605 according to a low density pattern 610 may use multiple different low density patterns 610. In some cases, the network entity 105 may use a randomized low density pattern. In order to save processing resources and memory resources associated with training the neural network 625, the UE 115 may train the generalized neural network to support any low density pattern configured by the network entity 105. The device (e.g., UE 115 or another training device) may train the generalized neural network using a set of training patterns. For example, the UE 115 may select one or more low density patterns for training independently of the network entity 105. Once the UE 115 has trained the generalized neural network, the UE 115 can deploy the generalized neural network for channel estimation. The UE 115 can use the generalized neural network to process CSI-RS transmitted according to any low density mode selected by the network entity 105.

[0149] However, different low-density patterns used for training may result in different channel estimation performance of the resulting generalized neural network. Additionally or alternatively, different low-density patterns used for CSI-RS transmissions performed by the network entity 105 may result in different channel estimation performance of the trained generalized neural network. In some cases, the UE 115 may train the generalized neural network using a random antenna port-RB pattern (e.g., with different frequency densities for different antenna ports). For example, the UE 115 may randomly or pseudo-randomly select L antenna ports from a total set of antenna ports for each RB, and the UE 115 may select different combinations of antenna ports for different RBs. In contrast, the network entity 105 may use a structured random antenna port-RB pattern (e.g., with the same frequency density for each antenna port) for CSI-RS 605 transmissions (e.g., for the low-density pattern 610 selected by the network entity 105). In some examples, such a configuration may improve the performance of the low-density pattern 610 for processing the CSI-RS 605. Alternatively, the UE 115 may train the generalized neural network using a structured random antenna port-RB pattern or any other type of pattern, and the network entity 105 may send the CSI-RS according to the random antenna port-RB pattern or any other type of pattern.

[0150] In some other examples, the device may train one or more neural networks 625 specific to one or more low density patterns 610. For example, a UE 115 may be configured with one or more low density pattern options for CSI-RS reception at the UE 115. In some cases, the UE 115 or another training device may train the neural network 625 to handle processing of CSI-RS 605 sent using one or more low density patterns 610. In some other cases, the UE 115 or another training device may train multiple neural networks 625, and each neural network 625 may be trained to handle processing of CSI-RS 605 sent using a specific low density pattern 610 from one or more low density pattern options. The network entity 105 that transmits the CSI-RS 605 may select the low density pattern 610 from the one or more low density pattern options, and may indicate the selected low density pattern 610 to the UE 115. The UE 115 may determine, based on the indicated low density pattern 610, which neural network 625 to use for CSI-RS processing (eg, a neural network 625 trained using the low density pattern 610).

[0151] Training the neural network 625 using the low density pattern 610 may involve processing a complete set of CSI-RS (e.g., where each antenna port in the complete set of antenna ports transmits a CSI-RS via each RB in the set of RBs across a frequency range) to determine a channel estimate based on the complete set of CSI-RS. The training device may use the low density pattern 610 to select a CSI-RS subset from the complete set of CSI-RS, and may input the CSI-RS subset into the neural network 625. The training device may obtain an output from the neural network 625 indicating a channel estimate based on the CSI-RS subset. The training device may compare the channel estimate output by the neural network 625 based on the CSI-RS subset with the channel estimate determined based on the complete set of CSI-RS. The training device may provide feedback to the neural network 625 based on the comparison. For example, the training device may adjust weight values, nodes, or other aspects of the neural network 625 based on the difference between the channel estimates so that the output of the neural network 625 may more accurately predict the channel estimate based on the complete set of CSI-RS. In some examples, the training device may perform such a training process for multiple received CSI-RS, multiple low-density patterns 610, or both. Additionally or alternatively, CSI-RS measurements, low-density patterns 610 for training, or both may be provided to the training device by another device (e.g., UE 115). In some cases, the training device may periodically or aperiodically refine (e.g., further train) the neural network 625 (e.g., after deployment).

[0152] UE 115 may use a deployed, trained neural network 625 to handle channel estimation based on a subset of CSI-RS 605. For example, UE 115 may receive a set of CSI-RS from network entity 105. UE 115 may perform zero padding 615 to adjust the size of array y of CSI-RS 605 according to low density pattern 610 (e.g., low density pattern 610 configured by network entity 105). For example, zero padding 615 may use low density pattern 610 to map received CSI-RS 605 to antenna ports and RBs on which the CSI-RS are transmitted. In some examples, zero padding 615 may receive a CSI-RS array of size N_RB×L (or N_RB×L×2 for both polarizations) and may expand the array to a size of N_RB×N t (or N_RB×N for both polarizations t ×2), where L is the number of antenna ports selected for each RB for transmitting CSI-RS, and N t is the total number of antenna ports at the network entity 105. The UE 115 may use the resulting array 620 (y p) (e.g., one or more measurements of the received CSI-RS) as input to the trained neural network 625.

[0153] In some examples, neural network 625 may be based on a transformer design for performing channel estimation. Neural network 625 may input array 620 (y p ) into a block 630 corresponding to a different RB. For example, the neural network 625 may determine a block of size 1×2N t The neural network 625 may pass the tile 630 to the first linear embedding layer 635-a to change the dimension of the tile 630 to support the input to the model (e.g., to the transformer 640). For example, the first linear embedding layer 635-a may change the dimension of the tile to N_RB×d model , and d model The dimensionality may be supported by the transformer 640. The neural network 625 may add the positional encoding to the output of the first linear embedding layer 635-a and may transmit the resulting data to the transformer 640 (e.g., a set of six layers of transformers). The neural network 625 may transmit the output of the transformer 640 to the second linear embedding layer 635-b to change the dimension of the output of the transformer 640 to match the total set N across the antenna ports. t Channel estimation of the channel The corresponding 2×N t (e.g., for both polarizations.) Thus, UE 115 may receive a subset of CSI-RS 605 from a subset of antenna ports and may use neural network 625 and configured low density mode 610 to determine channel estimates 645 across the total set of antenna ports.

[0154] Figure 7 An example of a machine learning process 700 for supporting reference signal pattern association for channel estimation according to one or more aspects of the present disclosure is illustrated. The machine learning process 700 may be performed in a UE 115 or another device supporting machine learning (e.g., a reference signal pattern association). Figures 1 to 6 The machine learning process 700 may support training a neural network for channel estimation using one or more low-density patterns of CSI-RS.

[0155] The machine learning process 700 may include a machine learning algorithm 710. As illustrated, the machine learning algorithm 710 may be an example of a neural network (e.g., an artificial neural network), such as a FF or DFF neural network, a RNN, a LSTM neural network, or any other type of neural network. However, any other machine learning algorithm may be supported. For example, the machine learning algorithm 710 may implement a nearest neighbor algorithm, a linear regression algorithm, a naive Bayes algorithm, a random forest algorithm, or any other machine learning algorithm. In addition, the machine learning process 700 may involve supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, or any combination thereof.

[0156] The machine learning algorithm 710 may include an input layer 715, one or more hidden layers 720, and an output layer 725. In a fully connected neural network with one hidden layer 720, each hidden layer node 735 may receive a value as an input from each input layer node 730, where each input may be weighted. These neural network weights may be based on a cost function modified during training of the machine learning algorithm 710. Similarly, each output layer node 740 may receive a value as an input from each hidden layer node 735, where the input is weighted. If post-deployment training (e.g., online training) is supported, memory may be allocated to store errors or gradients of inverse matrix multiplications. These errors or gradients may support updating the machine learning algorithm 710 based on output feedback. Training the machine learning algorithm 710 may support the calculation of weights (e.g., connecting the input layer node 730 to the hidden layer node 735 and connecting the hidden layer node 735 to the output layer node 740) to map the input pattern to the desired output result. The training may generate a device-specific machine learning algorithm 710 based on historical application data and data transfer for a particular network entity 105 or UE 115 .

[0157] In some examples, input values ​​705 may be transmitted to machine learning algorithm 710 for processing. In some examples, pre-processing may be performed according to a sequence of operations on input values ​​705 so that input values ​​705 may be in a format compatible with machine learning algorithm 710. In some examples, pre-processing may involve zero padding a received CSI-RS set according to a low density pattern, as described herein with reference to Figure 6 Described. The input value 705 may be converted to a set of k input layer nodes 730 at the input layer 715. In some cases, different measurements may be input at different input layer nodes 730 of the input layer 715. If the number of input layer nodes 730 exceeds the number of inputs corresponding to the input value 705, some input layer nodes 730 may be assigned default values ​​(e.g., value 0). As illustrated, the input layer 715 may include three input layer nodes 730-a, 730-b, and 730-c. However, it should be understood that the input layer 715 may include any number of input layer nodes 730 (e.g., 20 input nodes).

[0158] The machine learning algorithm 710 may convert the input layer 715 into a hidden layer 720 based on the number of input-to-hidden weights between the k input layer nodes 730 and the n hidden layer nodes 735. The machine learning algorithm 710 may include any number of hidden layers 720 as an intermediate step between the input layer 715 and the output layer 725. In addition, each hidden layer 720 may include any number of nodes. For example, as illustrated, the hidden layer 720 may include four hidden layer nodes 735-a, 735-b, 735-c, and 735-d. However, it should be understood that the hidden layer 720 may include any number of hidden layer nodes 735 (e.g., 10 input nodes). In a fully connected neural network, each node in a layer may be based on each node in a previous layer. For example, the value of the hidden layer node 735-a may be based on the values ​​of the input layer nodes 730-a, 730-b, and 730-c (e.g., different weights are applied to each node value).

[0159] The machine learning algorithm 710 may determine the value of the output layer node 740 of the output layer 725 after the one or more hidden layers 720. For example, the machine learning algorithm 710 may convert the hidden layer 720 into the output layer 725 based on the number of hidden-to-output weights between the n hidden layer nodes 735 and the m output layer nodes 740. In some cases, n=m. Each output layer node 740 may correspond to a different output value 745 of the machine learning algorithm 710. As illustrated, the machine learning algorithm 710 may include three output layer nodes 740-a, 740-b, and 740-c, which support three different thresholds. However, it should be understood that the output layer 725 may include any number of output layer nodes 740. In some examples, the output value 745 may be post-processed according to the sequence of operations so that the output value 745 may be in a format compatible with the report output value 745.

[0160] The machine learning algorithm 710 may support neural network training for channel estimation. For example, a device (e.g., UE 115 or other training device) may use the machine learning process 700 to train a generalized neural network, a specific neural network, or both. Thus, the input values ​​705 may correspond to CSI measurements associated with CSI-RS received by UE 115 according to a low density pattern of the channel, and the output values ​​745 may correspond to channel estimation parameters for the full channel (e.g., extrapolated from a subset of CSI-RS corresponding to the low density pattern).

[0161] Figure 8An example of a process flow 800 for supporting reference signal pattern association for channel estimation in accordance with one or more aspects of the present disclosure is illustrated. In some examples, the process flow 800 may be implemented by aspects of the wireless communication system 100, the network architecture 200, the wireless communication system 300, or any combination thereof. For example, the process flow 800 may include a network entity 105-b and a UE 115-c, which may be a reference signal pattern association. Figures 1 to 7 Examples of network entities 105 and UEs 115 are described. In the following description of process flow 800, operations between network entity 105-b and UE 115-c may be performed in a different order or at a different time. Some operations may also be excluded from process flow 800, or other operations may be added. Although network entity 105-b and UE 115-c are shown as performing operations of process flow 800, some aspects of some operations may also be performed by one or more other devices.

[0162] At 805, UE 115-c (or another device or component) may train a neural network based on a low density pattern of CSI-RS. In some cases, the neural network may be an artificial neural network or some other machine learning model or AI system. In some cases, a device (e.g., UE 115-c or another device) may train a generalized artificial neural network. The device may obtain a set of multiple CSI-RS for a set of multiple antenna ports and a set of multiple RBs. For example, UE 115-c may receive CSI-RS from each antenna port in a set of multiple antenna ports via each RB in a set of multiple RBs. The device may determine a low density pattern for an artificial neural network training process. For example, the device may randomly or pseudo-randomly select a low density pattern for training, or may be configured with a low density pattern for training. The device may train a generalized artificial neural network based on a subset of the obtained set of multiple CSI-RS according to the determined low density pattern. For example, the low density pattern may indicate that a subset of the set of multiple CSI-RS for one or more RBs in a set of multiple RBs will be used for training. In some examples, the device may train a generalized artificial neural network using a plurality of random low-density patterns. The device may output the trained generalized artificial neural network, for example, for use by UE 115-c for channel estimation.

[0163] In some other cases, the device (e.g., UE 115-c or another device) may train one or more specific artificial neural networks. For example, a specific artificial neural network may be trained using one or more specific low-density patterns so that the neural network can perform channel estimation using CSI-RS received using the one or more specific patterns. UE 115-c may be configured (e.g., pre-configured, configured by network entity 105-b) with a set of multiple low-density patterns. UE 115-c may train one or more artificial neural networks specific to a set of multiple low-density patterns (e.g., a different neural network for each configured low-density pattern or a neural network for a set of multiple configured low-density patterns).

[0164] The device may obtain a set of multiple CSI-RS for a set of multiple antenna ports and a set of multiple RBs. For example, the UE 115-c may receive a CSI-RS from each antenna port in the set of multiple antenna ports via each RB in the set of multiple RBs. The device may train an artificial neural network specific to one or more low-density modes configured at the device (e.g., provided to the device, stored at the device) based on a subset of the obtained set of multiple CSI-RS according to one or more low-density modes. The device may output the trained artificial neural network, for example, for use by the UE 115-c for channel estimation for a specific one or more low-density modes. In some cases, the device may output the trained artificial neural network and indicate that the neural network is specific to one or more low-density modes. If the UE 115-c is configured with a low-density mode (e.g., configured by the network entity 105-b), the UE 115-c may select a specific neural network to be used (e.g., a neural network trained using the configured low-density mode) based on the configured low-density mode.

[0165] At 810, the network entity 105-b may output (e.g., send) a control signal to the UE 115-c. In some examples, the control signal may configure a low-density mode for a set of multiple antenna ports at the network entity 105-b for CSI-RS reception at the UE 115-c. The low-density mode may indicate a subset of a set of multiple antenna ports for CSI-RS reception at the UE 115-c via one or more RBs. In some cases, the control signal may indicate a mapping from a subset of the set of antenna ports to a set of antenna ports for one or more RBs. In some cases, the mapping may be specific to an RB, a group of RBs, or common to a set of RBs in a frequency band corresponding to the CSI-RS reception. In some examples, the control signal may include a bitmap to indicate a low-density mode for CSI-RS reception. In some cases, the control signal may include auxiliary information for an antenna configuration with an antenna port set, a channel type, environmental information, transmission-related information, or a combination thereof. In some examples, the control signal may include a bitmap, number of antenna ports, or an index to a low-density mode to be used for UE 115-b.

[0166] At 815, UE 115-c may determine a low density mode based on the control signal. In some examples, a mapping from the control signal may be used to indicate an association between one or more antenna ports and RBs. For example, the low density mode may be determined using some association such as an antenna port muting pattern, an RB muting pattern, a cover code association, or some combination thereof. In some cases, the low density mode may indicate a subset of a set of antenna ports for CSI-RS reception via one or more RBs. In some examples, the low density mode may be based on a number of antenna ports, a rule, a lookup table, or a combination thereof.

[0167] At 820, the network entity 105-b may send a CSI-RS to the UE 115-c. In some examples, the CSI-RS may be sent based on a low density pattern indicated by the control signal. In some cases, the network entity 105-b may use a structured random low density pattern for the CSI-RS transmission.

[0168] At 825, the UE 115-c may input the CSI-RS into the neural network. In some examples, the CSI-RS may be zero padded based on a low density pattern. The neural network may input the zero padded CSI-RS into the neural network to determine the CSI measurement.

[0169] At 830, the UE 115-c may determine CSI measurements based on the neural network and based on receiving the CSI-RS set in the low density mode. In some cases, the CSI measurements may be included in a CSI report. For example, the UE 115-c may generate a CSI report including one or more CSI measurements, one or more channel estimation parameters, or a combination thereof. At 835, the UE 115-c may send the CSI report to the network entity 105-b.

[0170] Fig. 9 A block diagram 900 of a device 905 supporting reference signal pattern association for channel estimation according to one or more aspects of the present disclosure is shown. The device 905 may be an example of aspects of a UE 115 or a neural network training device as described herein. The device 905 may include a receiver 910, a transmitter 915, and a communication manager 920. The device 905 may also include a processor. Each of these components may communicate with each other (e.g., via one or more buses).

[0171] The receiver 910 may provide means for receiving information (such as packets, user data, control information, or any combination thereof) associated with various information channels (e.g., control channels associated with reference signal patterns for channel estimation, data channels, information channels). The information may be communicated to other components of the device 905. The receiver 910 may utilize a single antenna or a collection of multiple antennas.

[0172] The transmitter 915 may provide means for transmitting signals generated by other components of the device 905. For example, the transmitter 915 may transmit information associated with various information channels (e.g., control channels associated with reference signal patterns for channel estimation, data channels, information channels), such as packets, user data, control information, or any combination thereof. In some examples, the transmitter 915 may be co-located with the receiver 910 in a transceiver module. The transmitter 915 may utilize a single antenna or a collection of multiple antennas.

[0173] The communication manager 920, the receiver 910, the transmitter 915, or various combinations thereof, or various components thereof, may be examples of means for performing various aspects of reference signal pattern association for channel estimation as described herein. For example, the communication manager 920, the receiver 910, the transmitter 915, or various combinations thereof, or components thereof, may support methods for performing one or more of the functions described herein.

[0174] In some examples, the communication manager 920, the receiver 910, the transmitter 915, or various combinations or components thereof may be implemented in hardware (e.g., in a communication management circuit). The hardware may include a processor, a digital signal processor (DSP), a central processing unit (CPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a microcontroller, discrete gate or transistor logic components, discrete hardware components, or any combination thereof that is configured to or otherwise supports components for performing the functions described herein. In some examples, the processor and a memory coupled to the processor may be configured to perform one or more of the functions described herein (e.g., by executing instructions stored in the memory by the processor).

[0175] Additionally or alternatively, in some examples, the communication manager 920, the receiver 910, the transmitter 915, or various combinations or components thereof may be implemented in code executed by a processor (e.g., as communication management software or firmware). If implemented in code executed by a processor, the functionality of the communication manager 920, the receiver 910, the transmitter 915, or various combinations or components thereof may be performed by a general purpose processor (e.g., configured as or otherwise supporting components for performing the functions described in the present disclosure), a DSP, a CPU, an ASIC, an FPGA, a microcontroller, or any combination of these or other programmable logic devices.

[0176] In some examples, the communication manager 920 may be configured to perform various operations (e.g., receive, obtain, monitor, output, transmit) using or otherwise cooperating with the receiver 910, the transmitter 915, or both. For example, the communication manager 920 may receive information from the receiver 910, transmit information to the transmitter 915, or be integrated in conjunction with the receiver 910, the transmitter 915, or both to obtain information, output information, or perform various other operations as described herein.

[0177] According to examples as disclosed herein, the communication manager 920 may support wireless communications at a device (e.g., a UE). For example, the communication manager 920 may be configured to or otherwise support a component for receiving a control signal from a network entity, the control signal configuring a low-density mode for CSI-RS reception for a set of multiple antenna ports, wherein the low-density mode indicates a subset of the set of multiple antenna ports for CSI-RS reception via one or more RBs. The communication manager 920 may be configured to or otherwise support a component for receiving a set of multiple CSI-RS from the network entity according to the low-density mode. The communication manager 920 may be configured to or otherwise support a component for sending a CSI report to a network entity based on a set of multiple CSI-RS.

[0178] Additionally or alternatively, according to examples as disclosed herein, the communication manager 920 may support wireless communications at the device. For example, the communication manager 920 may be configured to or otherwise support components for obtaining a set of multiple CSI-RS for a set of multiple antenna ports and a set of multiple RBs. The communication manager 920 may be configured to or otherwise support components for determining a low-density pattern for an artificial neural network training process. The communication manager 920 may be configured to or otherwise support components for training a generalized artificial neural network based on a subset of a set of multiple CSI-RSs according to a determined low-density pattern, wherein the determined low-density pattern indicates a subset of a set of multiple antenna ports for one or more RBs in a set of multiple RBs. The communication manager 920 may be configured to or otherwise support components for outputting a trained generalized artificial neural network.

[0179] Additionally or alternatively, according to examples as disclosed herein, the communication manager 920 may support wireless communications at the device. For example, the communication manager 920 may be configured to or otherwise support components for obtaining a set of multiple CSI-RSs for a set of multiple antenna ports and a set of multiple RBs. The communication manager 920 may be configured to or otherwise support components for training an artificial neural network specific to one or more low-density patterns based on a subset of the set of multiple CSI-RSs according to one or more low-density patterns configured at the device, wherein a low-density pattern in the one or more low-density patterns indicates a subset of the set of multiple antenna ports for one or more RBs in the set of multiple RBs. The communication manager 920 may be configured to or otherwise support components for outputting the trained artificial neural network.

[0180] By including or configuring the communication manager 920 according to the examples described herein, the device 905 (e.g., a processor controlling or otherwise coupled to the receiver 910, the transmitter 915, the communication manager 920, or a combination thereof) can support techniques for reducing processing overhead and power consumption associated with CSI-RS reception and processing. For example, the device 905 can reduce the number of CSI-RS processed at the device 905 according to a low-density pattern. For example, based on training an artificial neural network, the device 905 can use a low-density pattern of CSI-RS to maintain accurate channel estimates for the full channel.

[0181] Fig.10A block diagram 1000 of a device 1005 supporting reference signal pattern association for channel estimation according to one or more aspects of the present disclosure is shown. The device 1005 may be an example of aspects of the device 905, UE 115, or neural network training device as described herein. The device 1005 may include a receiver 1010, a transmitter 1015, and a communication manager 1020. The device 1005 may also include a processor. Each of these components may communicate with each other (e.g., via one or more buses).

[0182] The receiver 1010 may provide means for receiving information (such as packets, user data, control information, or any combination thereof) associated with various information channels (e.g., control channels associated with reference signal patterns for channel estimation, data channels, information channels). The information may be communicated to other components of the device 1005. The receiver 1010 may utilize a single antenna or a collection of multiple antennas.

[0183] The transmitter 1015 may provide means for transmitting signals generated by other components of the device 1005. For example, the transmitter 1015 may transmit information associated with various information channels (e.g., control channels associated with reference signal patterns for channel estimation, data channels, information channels), such as packets, user data, control information, or any combination thereof. In some examples, the transmitter 1015 may be co-located with the receiver 1010 in a transceiver module. The transmitter 1015 may utilize a single antenna or a collection of multiple antennas.

[0184] The device 1005 or its various components may be examples of components for performing various aspects of reference signal pattern association for channel estimation as described herein. For example, the communication manager 1020 may include a low-density mode configuration component 1025, a CSI-RS receiving component 1030, a CSI reporting component 1035, a low-density mode determination component 1040, a neural network training component 1045, a neural network output component 1050, or any combination thereof. The communication manager 1020 may be an example of various aspects of the communication manager 920 as described herein. In some examples, the communication manager 1020 or its various components may be configured to use or otherwise cooperate with the receiver 1010, the transmitter 1015, or both to perform various operations (e.g., receive, obtain, monitor, output, send). For example, the communication manager 1020 may receive information from the receiver 1010, transmit information to the transmitter 1015, or be integrated with the receiver 1010, the transmitter 1015, or both to obtain information, output information, or perform various other operations as described herein.

[0185] According to examples as disclosed herein, the communication manager 1020 may support wireless communications at a UE. The low-density mode configuration component 1025 may be configured to or otherwise support components for receiving a control signal from a network entity that configures a low-density mode for CSI-RS reception for a set of multiple antenna ports, wherein the low-density mode indicates a subset of the set of multiple antenna ports for CSI-RS reception via one or more RBs. The CSI-RS reception component 1030 may be configured to or otherwise support components for receiving a set of multiple CSI-RSs from a network entity according to the low-density mode. The CSI reporting component 1035 may be configured to or otherwise support components for sending a CSI report to a network entity based on the set of multiple CSI-RSs.

[0186] Additionally or alternatively, according to examples as disclosed herein, the communication manager 1020 may support wireless communications at the device. The CSI-RS receiving component 1030 may be configured as or otherwise support components for obtaining a set of multiple CSI-RS for a set of multiple antenna ports and a set of multiple RBs. The low-density pattern determination component 1040 may be configured as or otherwise support components for determining a low-density pattern for an artificial neural network training process. The neural network training component 1045 may be configured as or otherwise support components for training a generalized artificial neural network based on a subset of a set of multiple CSI-RSs according to a determined low-density pattern, wherein the determined low-density pattern indicates a subset of a set of multiple antenna ports for one or more RBs in a set of multiple RBs. The neural network output component 1050 may be configured as or otherwise support components for outputting a trained generalized artificial neural network.

[0187] Additionally or alternatively, according to examples as disclosed herein, the communication manager 1020 may support wireless communications at the device. The CSI-RS receiving component 1030 may be configured as or otherwise support a component for obtaining a set of multiple CSI-RS for a set of multiple antenna ports and a set of multiple RBs. The neural network training component 1045 may be configured as or otherwise support a component for training an artificial neural network specific to one or more low-density patterns based on a subset of the set of multiple CSI-RSs according to one or more low-density patterns configured at the device, wherein the low-density pattern in the one or more low-density patterns indicates a subset of the set of multiple antenna ports for one or more RBs in the set of multiple RBs. The neural network output component 1050 may be configured as or otherwise support a component for outputting the trained artificial neural network.

[0188] Fig.11A block diagram 1100 of a communication manager 1120 supporting reference signal pattern association for channel estimation according to one or more aspects of the present disclosure is shown. The communication manager 1120 may be an example of aspects of the communication manager 920, the communication manager 1020, or both as described herein. The communication manager 1120 or its various components may be examples of components for performing various aspects of reference signal pattern association for channel estimation as described herein. For example, the communication manager 1120 may include a low-density mode configuration component 1125, a CSI-RS reception component 1130, a CSI reporting component 1135, a low-density mode determination component 1140, a neural network training component 1145, a neural network output component 1150, a neural network component 1155, a low-density mode storage component 1160, a random selection component 1165, a zero filling component 1170, or any combination thereof. Each of these components may communicate directly or indirectly with each other (e.g., via one or more buses).

[0189] According to examples as disclosed herein, the communication manager 1120 may support wireless communications at a UE. The low-density mode configuration component 1125 may be configured to or otherwise support components for receiving a control signal from a network entity that configures a low-density mode for CSI-RS reception for a set of multiple antenna ports, wherein the low-density mode indicates a subset of the set of multiple antenna ports for CSI-RS reception via one or more RBs. The CSI-RS reception component 1130 may be configured to or otherwise support components for receiving a set of multiple CSI-RSs from a network entity according to the low-density mode. The CSI reporting component 1135 may be configured to or otherwise support components for sending a CSI report to a network entity based on the set of multiple CSI-RSs.

[0190] In some examples, low density mode configuration component 1125 can be configured to or otherwise support means for determining a low density mode based on a control signal indicating a mapping from a subset of a set of multiple antenna ports for one or more RBs to a set of multiple antenna ports. In some examples, the mapping is specific to an RB, specific to a group of RBs, or common to a set of multiple RBs in a frequency band corresponding to CSI-RS reception.

[0191] In some examples, low density mode configuration component 1125 can be configured to or otherwise support means for determining a low density mode based on a control signal indicating an RB muting pattern for one or more antenna ports in a set of multiple antenna ports. In some examples, the RB muting pattern is specific to one antenna port in the set of multiple antenna ports, specific to a group of antenna ports in the set of multiple antenna ports, or common to the set of multiple antenna ports.

[0192] In some examples, low density mode configuration component 1125 can be configured to or otherwise support components for determining a low density mode based on a control signal indicating an antenna port muting pattern for one or more RBs. In some examples, the antenna port muting pattern is specific to an RB, specific to an RB group, or common to a set of multiple RBs in a frequency band corresponding to CSI-RS reception.

[0193] In some examples, low density mode configuration component 1125 may be configured to or otherwise support components for determining a low density mode based on a control signal indicating a cover code that configures a set of multiple antenna port-RB pairs for CSI-RS reception.

[0194] In some examples, neural network component 1155 may be configured to or otherwise support components for determining a CSI measurement based on an artificial neural network and a set of multiple CSI-RS received according to a low density pattern, wherein the CSI report includes the CSI measurement.

[0195] In some examples, zero padding component 1170 may be configured or otherwise support components for zero padding a received set of multiple CSI-RS based on a low density pattern. In some examples, neural network component 1155 may be configured or otherwise support components for inputting the zero-padded received set of multiple CSI-RS into an artificial neural network, where a CSI measurement is determined based on an output of the artificial neural network. In some examples, neural network component 1155 may be configured or otherwise support components for training an artificial neural network based on a low density pattern.

[0196] In some examples, the control signal includes a bitmap indicating a low density mode for CSI-RS reception.

[0197] In some examples, the control signal indicates a first number of subsets of a set of multiple antenna ports and a second number of a set of multiple antenna ports, and the low-density mode configuration component 1125 may be configured as or otherwise support components for determining a low-density mode for CSI-RS reception based on the first number, the second number, and a rule, a lookup table, or both that maps from the first number and the second number to the low-density mode.

[0198] In some examples, low-density pattern storage component 1160 may be configured as or otherwise support components for storing a set of multiple low-density patterns, wherein the control signal includes an index value indicating a low-density pattern from the set of multiple low-density patterns.

[0199] In some examples, the control signal also includes auxiliary information indicating an antenna configuration corresponding to a set of multiple antenna ports, a channel type, environmental information, transmission related information, or a combination thereof. In some examples, the CSI report is further based on the auxiliary information.

[0200] Additionally or alternatively, the communication manager 1120 may support wireless communications at the device according to examples as disclosed herein. In some examples, the CSI-RS receiving component 1130 may be configured as or otherwise support components for obtaining a set of multiple CSI-RS for a set of multiple antenna ports and a set of multiple RBs. The low-density pattern determination component 1140 may be configured as or otherwise support components for determining a low-density pattern for an artificial neural network training process. The neural network training component 1145 may be configured as or otherwise support components for training a generalized artificial neural network based on a subset of a set of multiple CSI-RSs according to a determined low-density pattern, wherein the determined low-density pattern indicates a subset of a set of multiple antenna ports for one or more RBs in a set of multiple RBs. The neural network output component 1150 may be configured as or otherwise support components for outputting a trained generalized artificial neural network.

[0201] In some examples, low density pattern determination component 1140 can be configured or otherwise support components for determining one or more additional low density patterns for use in an artificial neural network training process. In some examples, neural network training component 1145 can be configured or otherwise support components for further training a generalized artificial neural network based on the one or more additional low density patterns.

[0202] In some examples, random selection component 1165 can be configured or otherwise support means for randomly selecting one or more low-density patterns, where the low-density patterns are determined based on the random selection.

[0203] In some examples, the determined low density pattern indicates random selection of a subset of the set of multiple antenna ports for each RB in the set of multiple RBs. In some other examples, the determined low density pattern indicates random selection of a subset of the set of multiple antenna ports for a first set of RBs in the set of multiple RBs, and the selection of the subset of the set of multiple antenna ports for a second set of RBs in the set of multiple RBs is based on the random selection of the subset of the set of multiple antenna ports for the first set of RBs.

[0204] Additionally or alternatively, the communication manager 1120 may support wireless communications at the device according to examples as disclosed herein. In some examples, the CSI-RS receiving component 1130 may be configured as or otherwise support components for obtaining a set of multiple CSI-RS for a set of multiple antenna ports and a set of multiple RBs. In some examples, the neural network training component 1145 may be configured as or otherwise support components for training an artificial neural network specific to one or more low-density patterns based on a subset of the set of multiple CSI-RSs according to one or more low-density patterns configured at the device, wherein a low-density pattern in the one or more low-density patterns indicates a subset of the set of multiple antenna ports for one or more RBs in the set of multiple RBs. In some examples, the neural network output component 1150 may be configured as or otherwise support components for outputting a trained artificial neural network.

[0205] In some examples, low density mode configuration component 1125 can be configured to or otherwise support components for obtaining a configuration of one or more low density modes, wherein an artificial neural network is trained based on the configuration.

[0206] In some examples, low-density pattern storage component 1160 may be configured to or otherwise support means for storing one or more low-density patterns at the device, wherein an artificial neural network is trained based on the stored one or more low-density patterns.

[0207] In some examples, the artificial neural network is specific to the low density mode, and the neural network training component 1145 can be configured as or otherwise support components for training one or more additional artificial neural networks specific to one or more additional low density modes configured at the device. In some examples, the artificial neural network is specific to the low density mode, and the neural network output component 1150 can be configured as or otherwise support components for outputting one or more additional trained artificial neural networks.

[0208] In some examples, to support outputting a trained artificial neural network, neural network output component 1150 can be configured or otherwise support components for outputting a trained artificial neural network and indicating that the trained artificial neural network is specific to one or more low-density patterns.

[0209] Fig.12A diagram of a system 1200 is shown that includes a device 1205 that supports reference signal pattern association for channel estimation in accordance with one or more aspects of the present disclosure. The device 1205 may be an example of a device 905, a device 1005, a UE 115, or a neural network training device as described herein or include a component of these devices. The device 1205 may communicate (e.g., wirelessly) with one or more network entities 105, one or more UEs 115, or any combination thereof. The device 1205 may include components for two-way voice and data communications, including components for sending and receiving communications, such as a communication manager 1220, an input / output (I / O) controller 1210, a transceiver 1215, an antenna 1225, a memory 1230, a code 1235, and a processor 1240. These components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more buses (e.g., bus 1245).

[0210] I / O controller 1210 can manage input signals and output signals of device 1205. I / O controller 1210 can also manage peripheral devices that are not integrated into device 1205. In some cases, I / O controller 1210 can represent a physical connection or port to an external peripheral device. In some cases, I / O controller 1210 can utilize an operating system, such as or another known operating system. Additionally or alternatively, I / O controller 1210 may represent or interact with a modem, keyboard, mouse, touch screen, or similar device. In some cases, I / O controller 1210 may be implemented as part of a processor, such as processor 1240. In some cases, a user may interact with device 1205 via I / O controller 1210 or via hardware components controlled by I / O controller 1210.

[0211] In some cases, the device 1205 may include a single antenna 1225. However, in some other cases, the device 1205 may have more than one antenna 1225, which may be capable of concurrently transmitting or receiving multiple wireless transmissions. The transceiver 1215 may communicate bidirectionally via one or more antennas 1225, a wired or wireless link, as described herein. For example, the transceiver 1215 may represent a wireless transceiver and may communicate bidirectionally with another wireless transceiver. The transceiver 1215 may also include a modem for: modulating packets; providing the modulated packets to one or more antennas 1225 for transmission; and demodulating packets received from one or more antennas 1225. The transceiver 1215 or the transceiver 1215 and one or more antennas 1225 may be examples of transmitters 915, transmitters 1015, receivers 910, receivers 1010, or any combination thereof or components thereof as described herein.

[0212] The memory 1230 may include random access memory (RAM) and read-only memory (ROM). The memory 1230 may store computer-readable, computer-executable code 1235 including instructions that, when executed by the processor 1240, cause the device 1205 to perform various functions described herein. The code 1235 may be stored in a non-transitory computer-readable medium such as a system memory or another type of memory. In some cases, the code 1235 may not be directly executable by the processor 1240, but may (e.g., when compiled and executed) cause the computer to perform the functions described herein. In some cases, the memory 1230 may also include, among other things, a basic I / O system (BIOS) that may control basic hardware or software operations, such as interaction with peripheral components or devices.

[0213] Processor 1240 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, a microcontroller, an ASIC, an FPGA, a programmable logic device, a discrete gate or transistor logic component, a discrete hardware component, or any combination thereof). In some cases, processor 1240 may be configured to operate a memory array using a memory controller. In some other cases, the memory controller may be integrated into processor 1240. Processor 1240 may be configured to execute computer-readable instructions stored in a memory (e.g., memory 1230) to enable device 1205 to perform various functions (e.g., various functions or tasks associated with supporting a reference signal pattern for channel estimation). For example, device 1205 or a component of device 1205 may include processor 1240 and memory 1230 coupled to or coupled to processor 1240, and processor 1240 and memory 1230 are configured to perform various functions described herein.

[0214] According to the examples disclosed herein, the communication manager 1220 may support wireless communication at the UE. For example, the communication manager 1220 may be configured to or otherwise support a component for receiving a control signal from a network entity, the control signal configuring a low-density mode for CSI-RS reception for a set of multiple antenna ports, wherein the low-density mode indicates a subset of the set of multiple antenna ports for CSI-RS reception via one or more RBs. The communication manager 1220 may be configured to or otherwise support a component for receiving a set of multiple CSI-RS from the network entity according to the low-density mode. The communication manager 1220 may be configured to or otherwise support a component for sending a CSI report to the network entity based on the set of multiple CSI-RS.

[0215] Additionally or alternatively, according to examples as disclosed herein, the communication manager 1220 may support wireless communications at the device. For example, the communication manager 1220 may be configured to or otherwise support components for obtaining a set of multiple CSI-RS for a set of multiple antenna ports and a set of multiple RBs. The communication manager 1220 may be configured to or otherwise support components for determining a low-density pattern for an artificial neural network training process. The communication manager 1220 may be configured to or otherwise support components for training a generalized artificial neural network based on a subset of a set of multiple CSI-RSs according to a determined low-density pattern, wherein the determined low-density pattern indicates a subset of a set of multiple antenna ports for one or more resource blocks in a set of multiple RBs. The communication manager 1220 may be configured to or otherwise support components for outputting a trained generalized artificial neural network.

[0216] Additionally or alternatively, according to examples as disclosed herein, the communication manager 1220 may support wireless communications at a device. For example, the communication manager 1220 may be configured to or otherwise support a component for obtaining a set of multiple CSI-RSs for a set of multiple antenna ports and a set of multiple RBs. The communication manager 1220 may be configured to or otherwise support a component for training an artificial neural network specific to one or more low-density patterns based on a subset of the set of multiple CSI-RSs according to one or more low-density patterns configured at the device, wherein a low-density pattern in the one or more low-density patterns indicates a subset of the set of multiple antenna ports for one or more RBs in the set of multiple RBs. The communication manager 1220 may be configured to or otherwise support a component for outputting a trained artificial neural network.

[0217] By including or configuring the communication manager 1220 according to examples as described herein, the device 1205 can support techniques for reduced processing overhead, reduced power consumption, and reduced channel overhead associated with CSI-RS signaling and processing. For example, the device 1205 can perform channel estimation using a reduced set of CSI-RS according to a low density pattern, and the device 1205 can train and use a neural network for reliable channel estimation based on the reduced set of CSI-RS.

[0218] In some examples, the communication manager 1220 may be configured to perform various operations (e.g., receive, monitor, transmit) using or otherwise cooperating with the transceiver 1215, one or more antennas 1225, or any combination thereof. Although the communication manager 1220 is illustrated as a separate component, in some examples, one or more functions described with reference to the communication manager 1220 may be supported or performed by the processor 1240, the memory 1230, the code 1235, or any combination thereof. For example, the code 1235 may include instructions that are executable by the processor 1240 to cause the device 1205 to perform various aspects of reference signal pattern association for channel estimation as described herein, or the processor 1240 and the memory 1230 may be otherwise configured to perform or support such operations.

[0219] Fig.13 A block diagram 1300 of a device 1305 supporting reference signal pattern association for channel estimation according to one or more aspects of the present disclosure is shown. The device 1305 may be an example of aspects of the network entity 105 as described herein. The device 1305 may include a receiver 1310, a transmitter 1315, and a communication manager 1320. The device 1305 may also include a processor. Each of these components may communicate with each other (e.g., via one or more buses).

[0220] Receiver 1310 may provide means for obtaining (e.g., receiving, determining, identifying) information associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack), such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units). The information may be passed to other components of device 1305. In some examples, receiver 1310 may support obtaining information by receiving signals via one or more antennas. Additionally or alternatively, receiver 1310 may support obtaining information by receiving signals via one or more wired (e.g., electrical, optical) interfaces, wireless interfaces, or any combination thereof.

[0221] The transmitter 1315 may provide a means for outputting (e.g., sending, providing, conveying, transmitting) information generated by other components of the device 1305. For example, the transmitter 1315 may output information associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack) such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units). In some examples, the transmitter 1315 may support outputting information by sending signals via one or more antennas. Additionally or alternatively, the transmitter 1315 may support outputting information by sending signals via one or more wired (e.g., electrical, optical) interfaces, wireless interfaces, or any combination thereof. In some examples, the transmitter 1315 and the receiver 1310 may be co-located in a transceiver, which may include a modem or be coupled to a modem.

[0222] The communication manager 1320, the receiver 1310, the transmitter 1315, or various combinations thereof, or various components thereof, may be examples of means for performing various aspects of reference signal pattern association for channel estimation as described herein. For example, the communication manager 1320, the receiver 1310, the transmitter 1315, or various combinations thereof, or components thereof, may support methods for performing one or more of the functions described herein.

[0223] In some examples, the communication manager 1320, the receiver 1310, the transmitter 1315, or various combinations or components thereof may be implemented in hardware (e.g., in a communication management circuit). The hardware may include a processor, a DSP, a CPU, an ASIC, an FPGA or other programmable logic device, a microcontroller, discrete gate or transistor logic components, discrete hardware components, or any combination thereof that is configured as or otherwise supports components for performing the functions described in the present disclosure. In some examples, a processor and a memory coupled to the processor may be configured to perform one or more of the functions described herein (e.g., by executing instructions stored in the memory by the processor).

[0224] Additionally or alternatively, in some examples, the communication manager 1320, the receiver 1310, the transmitter 1315, or various combinations or components thereof may be implemented in code executed by a processor (e.g., as communication management software or firmware). If implemented in code executed by a processor, the functionality of the communication manager 1320, the receiver 1310, the transmitter 1315, or various combinations or components thereof may be performed by a general purpose processor (e.g., configured as or otherwise supporting components for performing the functions described in the present disclosure), a DSP, a CPU, an ASIC, an FPGA, a microcontroller, or any combination of these or other programmable logic devices.

[0225] In some examples, communication manager 1320 may be configured to perform various operations (e.g., receive, obtain, monitor, output, send) using or otherwise cooperating with receiver 1310, transmitter 1315, or both. For example, communication manager 1320 may receive information from receiver 1310, transmit information to transmitter 1315, or be integrated in conjunction with receiver 1310, transmitter 1315, or both to obtain information, output information, or perform various other operations as described herein.

[0226] According to examples as disclosed herein, the communication manager 1320 may support wireless communications at a network entity. For example, the communication manager 1320 may be configured to or otherwise support a component for outputting a control signal that configures a low-density pattern for CSI-RS reception at a UE for a set of multiple antenna ports, wherein the low-density pattern indicates a subset of the set of multiple antenna ports for CSI-RS reception via one or more RBs. The communication manager 1320 may be configured to or otherwise support a component for outputting a set of multiple CSI-RSs according to the low-density pattern. The communication manager 1320 may be configured to or otherwise support a component for obtaining a CSI report based on a set of multiple CSI-RSs.

[0227] By including or configuring a communications manager 1320 according to the examples described herein, a device 1305 (e.g., a processor controlling or otherwise coupled to a receiver 1310, a transmitter 1315, a communications manager 1320, or a combination thereof) may support techniques for reduced power consumption and reduced processing overhead associated with CSI-RS transmissions.

[0228] Fig.14 A block diagram 1400 of a device 1405 supporting reference signal pattern association for channel estimation according to one or more aspects of the present disclosure is shown. The device 1405 may be an example of aspects of the device 1305 or network entity 105 as described herein. The device 1405 may include a receiver 1410, a transmitter 1415, and a communication manager 1420. The device 1405 may also include a processor. Each of these components may communicate with each other (e.g., via one or more buses).

[0229] Receiver 1410 may provide means for obtaining (e.g., receiving, determining, identifying) information associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack), such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units). The information may be passed to other components of device 1405. In some examples, receiver 1410 may support obtaining information by receiving signals via one or more antennas. Additionally or alternatively, receiver 1410 may support obtaining information by receiving signals via one or more wired (e.g., electrical, optical) interfaces, wireless interfaces, or any combination thereof.

[0230] The transmitter 1415 may provide a means for outputting (e.g., sending, providing, conveying, transmitting) information generated by other components of the device 1405. For example, the transmitter 1415 may output information associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack) such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units). In some examples, the transmitter 1415 may support outputting information by sending signals via one or more antennas. Additionally or alternatively, the transmitter 1415 may support outputting information by sending signals via one or more wired (e.g., electrical, optical) interfaces, wireless interfaces, or any combination thereof. In some examples, the transmitter 1415 and the receiver 1410 may be co-located in a transceiver, which may include a modem or be coupled to a modem.

[0231] Device 1405 or its various components may be examples of components for performing various aspects of reference signal pattern association for channel estimation as described herein. For example, communication manager 1420 may include low-density mode configuration component 1425, CSI-RS component 1430, CSI report receiving component 1435, or any combination thereof. Communication manager 1420 may be an example of various aspects of communication manager 1320 as described herein. In some examples, communication manager 1420 or its various components may be configured to use or otherwise cooperate with receiver 1410, transmitter 1415, or both to perform various operations (e.g., receive, obtain, monitor, output, send). For example, communication manager 1420 may receive information from receiver 1410, transmit information to transmitter 1415, or integrate with receiver 1410, transmitter 1415, or both to obtain information, output information, or perform various other operations as described herein.

[0232] According to examples as disclosed herein, the communication manager 1420 may support wireless communications at a network entity. The low-density mode configuration component 1425 may be configured to or otherwise support components for outputting a control signal that configures a low-density mode for CSI-RS reception at a UE for a set of multiple antenna ports, wherein the low-density mode indicates a subset of the set of multiple antenna ports for CSI-RS reception via one or more RBs. The CSI-RS component 1430 may be configured to or otherwise support components for outputting a set of multiple CSI-RSs according to the low-density mode. The CSI report receiving component 1435 may be configured to or otherwise support components for obtaining a CSI report based on a set of multiple CSI-RSs.

[0233] Fig.15 A block diagram 1500 of a communication manager 1520 supporting reference signal pattern association for channel estimation according to one or more aspects of the present disclosure is shown. The communication manager 1520 may be an example of aspects of the communication manager 1320, the communication manager 1420, or both as described herein. The communication manager 1520 or its various components may be examples of components for performing various aspects of reference signal pattern association for channel estimation as described herein. For example, the communication manager 1520 may include a low-density mode configuration component 1525, a CSI-RS component 1530, a CSI report receiving component 1535, a rule configuration component 1540, a low-density mode storage component 1545, or any combination thereof. Each of these components may communicate with each other directly or indirectly (e.g., via one or more buses), which communication may include communication within a protocol layer of a protocol stack, communication associated with a logical channel of a protocol stack (e.g., between protocol layers of a protocol stack, within a device, component, or virtualized component associated with the network entity 105, between devices, components, or virtualized components associated with the network entity 105), or any combination thereof.

[0234] According to examples as disclosed herein, the communication manager 1520 may support wireless communications at a network entity. The low-density mode configuration component 1525 may be configured to or otherwise support components for outputting a control signal that configures a low-density mode for CSI-RS reception at a UE for a set of multiple antenna ports, wherein the low-density mode indicates a subset of the set of multiple antenna ports for CSI-RS reception via one or more RBs. The CSI-RS component 1530 may be configured to or otherwise support components for outputting a set of multiple CSI-RSs according to the low-density mode. The CSI report receiving component 1535 may be configured to or otherwise support components for obtaining a CSI report based on a set of multiple CSI-RSs.

[0235] In some examples, the control signal includes a bitmap indicating a low density mode for CSI-RS reception.

[0236] In some examples, the control signal includes a first control signal and indicates a first number of subsets of a set of multiple antenna ports and a second number of sets of multiple antenna ports, and the rule configuration component 1540 may be configured as or otherwise support a component for outputting a second control signal configured for mapping a value pair from the first number of subsets of a set of multiple antenna ports and the second number of sets of multiple antenna ports to a rule, a lookup table, or both for a low-density mode.

[0237] In some examples, low-density pattern storage component 1545 may be configured as or otherwise support components for storing a set of multiple low-density patterns, wherein the control signal includes an index value indicating a low-density pattern from the set of multiple low-density patterns.

[0238] In some examples, the control signal also includes auxiliary information indicating an antenna configuration corresponding to a set of multiple antenna ports, a channel type, environmental information, transmission related information, or a combination thereof. In some examples, the CSI report is further based on the auxiliary information.

[0239] Fig.16 A diagram of a system 1600 is shown that includes a device 1605 that supports reference signal pattern association for channel estimation in accordance with one or more aspects of the present disclosure. The device 1605 may be an example of a device 1305, a device 1405, or a network entity 105 as described herein, or include components thereof. The device 1605 may communicate with one or more network entities 105, one or more UEs 115, or any combination thereof, which may include communication through one or more wired interfaces, through one or more wireless interfaces, or any combination thereof. The device 1605 may include components that support output and obtain communications, such as a communication manager 1620, a transceiver 1610, an antenna 1615, a memory 1625, a code 1630, and a processor 1635. These components may be electronically communicated or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more buses (e.g., bus 1640).

[0240] As described herein, the transceiver 1610 may support bidirectional communication via a wired link, a wireless link, or both. In some examples, the transceiver 1610 may include a wired transceiver and may communicate bidirectionally with another wired transceiver. Additionally or alternatively, in some examples, the transceiver 1610 may include a wireless transceiver and may communicate bidirectionally with another wireless transceiver. In some examples, the device 1605 may include one or more antennas 1615, which may be capable of sending or receiving wireless transmissions (e.g., concurrently). The transceiver 1610 may also include a modem for: modulating a signal; providing a modulated signal for transmission (e.g., via one or more antennas 1615, via a wired transmitter); receiving a modulated signal (e.g., from one or more antennas 1615, from a wired receiver); and demodulating a signal. In some implementations, the transceiver 1610 may include one or more interfaces, such as one or more interfaces coupled to one or more antennas 1615 configured to support various receiving or obtaining operations, or one or more interfaces coupled to one or more antennas 1615 configured to support various sending or outputting operations, or a combination thereof. In some implementations, the transceiver 1610 may include or be configured to be coupled to one or more processors or memory components that are operable to: perform or support operations based on received or obtained information or signals; or generate information or other signals for transmission or other output, or any combination thereof. In some implementations, the transceiver 1610, or the transceiver 1610 and one or more antennas 1615, or the transceiver 1610 and one or more antennas 1615 and one or more processors or memory components (e.g., processor 1635, or memory 1625, or both) may be included in a chip or chip assembly installed in the device 1605. In some examples, the transceiver may be operable to support communications via one or more communication links (eg, communication link 125, backhaul communication link 120, midhaul communication link 162, fronthaul communication link 168).

[0241] Memory 1625 may include RAM and ROM. Memory 1625 may store computer-readable, computer-executable code 1630 including instructions that, when executed by processor 1635, cause device 1605 to perform various functions described herein. Code 1630 may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. In some cases, code 1630 may not be directly executable by processor 1635, but may (e.g., when compiled and executed) cause a computer to perform the functions described herein. In some cases, memory 1625 may also include, among other things, a BIOS that may control basic hardware or software operations, such as interaction with peripheral components or devices.

[0242] Processor 1635 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, an ASIC, a CPU, an FPGA, a microcontroller, a programmable logic device, a discrete gate or transistor logic component, a discrete hardware component, or any combination thereof). In some cases, processor 1635 may be configured to operate a memory array using a memory controller. In some other cases, the memory controller may be integrated into processor 1635. Processor 1635 may be configured to execute computer-readable instructions stored in a memory (e.g., memory 1625) to enable device 1605 to perform various functions (e.g., various functions or tasks associated with supporting a reference signal pattern for channel estimation). For example, device 1605 or a component of device 1605 may include processor 1635 and memory 1625 coupled to processor 1635, and the processor 1635 and memory 1625 are configured to perform various functions described herein. The processor 1635 may be an example of a cloud computing platform (e.g., one or more physical nodes and supporting software such as an operating system, a virtual machine, or a container instance) that may host functions for performing the functions of the device 1605 (e.g., by executing code 1630). The processor 1635 may be any one or more suitable processors capable of executing scripts or instructions of one or more software programs stored in the device 1605 (such as in the memory 1625). In some specific implementations, the processor 1635 may be a component of a processing system. A processing system may refer to a system or a series of machines or components that receive inputs and process these inputs to produce a set of outputs (which may be passed to, for example, other systems or components of the device 1605). For example, the processing system of the device 1605 may refer to a system including various other components or subcomponents of the device 1605, such as the processor 1635, or the transceiver 1610, or the communication manager 1620, or other components or combinations of components of the device 1605. The processing system of device 1605 may interface with other components of device 1605, and may process information (such as input or signals) received from other components, or output information to other components. For example, a chip or modem of device 1605 may include a processing system and one or more interfaces for outputting information or for obtaining information or both. The one or more interfaces may be implemented as or otherwise include a first interface configured to output information and a second interface configured to obtain information, or the same interface configured to output information and obtain information, as well as other specific implementations. In some specific implementations, the one or more interfaces may refer to an interface between the processing system of the chip or modem and a transmitter, so that device 1605 can send information output from the chip or modem.Additionally or alternatively, in some implementations, the one or more interfaces may refer to an interface between a processing system of a chip or modem and a receiver, such that the device 1605 may obtain information or signal input, and the information may be passed to the processing system. One of ordinary skill in the art will readily recognize that the first interface may also obtain information or signal input, and the second interface may also output information or signal output.

[0243] In some examples, bus 1640 may support communications of a protocol layer (e.g., within a protocol layer) of a protocol stack. In some examples, bus 1640 may support communications associated with a logical channel of a protocol stack (e.g., between protocol layers of a protocol stack), which may include communications performed within a component of device 1605, or communications performed between different components of device 1605 that may be co-located or may be located in different locations (e.g., where device 1605 may refer to a system in which one or more of communication manager 1620, transceiver 1610, memory 1625, code 1630, and processor 1635 may be located in one of the different components or divided between the different components).

[0244] In some examples, communication manager 1620 may manage aspects of communications with core network 130 (e.g., via one or more wired or wireless backhaul links). For example, communication manager 1620 may manage delivery of data communications for client devices, such as one or more UEs 115. In some examples, communication manager 1620 may manage communications with other network entities 105 and may include a controller or scheduler for controlling communications with UE 115 in collaboration with other network entities 105. In some examples, communication manager 1620 may support an X2 interface within an LTE / LTE-A wireless communication network technology to provide communications between network entities 105.

[0245] According to the examples disclosed herein, the communication manager 1620 may support wireless communication at a network entity. For example, the communication manager 1620 may be configured to or otherwise support a component for outputting a control signal that configures a low-density pattern for a set of multiple antenna ports for CSI-RS signal reception at a UE, wherein the low-density pattern indicates a subset of the set of multiple antenna ports for CSI-RS reception via one or more RBs. The communication manager 1620 may be configured to or otherwise support a component for outputting a set of multiple CSI-RS according to the low-density pattern. The communication manager 1620 may be configured to or otherwise support a component for obtaining a CSI report based on a set of multiple CSI-RS.

[0246] By including or configuring the communication manager 1620 according to examples as described herein, the device 1605 can support techniques for reduced processing overhead and reduced channel overhead associated with CSI-RS transmission. For example, the device 1605 can support transmitting a reduced set of CSI-RS according to a low density mode.

[0247] In some examples, the communication manager 1620 may be configured to perform various operations (e.g., receive, obtain, monitor, output, transmit) using or otherwise cooperating with the transceiver 1610, one or more antennas 1615 (e.g., where applicable), or any combination thereof. Although the communication manager 1620 is illustrated as a separate component, in some examples, one or more functions described with reference to the communication manager 1620 may be supported or performed by the transceiver 1610, the processor 1635, the memory 1625, the code 1630, or any combination thereof. For example, the code 1630 may include instructions that are executable by the processor 1635 to cause the device 1605 to perform various aspects of reference signal pattern association for channel estimation as described herein, or the processor 1635 and the memory 1625 may be otherwise configured to perform or support such operations.

[0248] Fig.17 A flow chart illustrating a method 1700 for supporting reference signal pattern association for channel estimation according to one or more aspects of the present disclosure is shown. The operations of the method 1700 may be implemented by a UE or a component thereof as described herein. For example, the operations of the method 1700 may be implemented by a UE or a component thereof as described herein. Figures 1 to 12 The described UE 115 may be performed. In some examples, the UE may execute an instruction set to control the functional elements of the UE to perform the described functions. Additionally or alternatively, the UE may use dedicated hardware to perform various aspects of the described functions.

[0249] At 1705, the method may include receiving a control signal from a network entity that configures a low density pattern for CSI-RS reception of a set of multiple antenna ports, wherein the low density pattern indicates a subset of the set of multiple antenna ports for CSI-RS reception via one or more RBs. The operations of 1705 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1705 may be performed as described in reference to Fig.11 The described low density mode configuration component 1125 is executed.

[0250] At 1710, the method may include receiving a set of multiple CSI-RS from a network entity according to a low density mode. The operations of 1710 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1710 may be performed as described in reference to Fig.11The described CSI-RS receiving component 1130 is performed.

[0251] At 1715, the method may include sending a CSI report to a network entity based on a set of multiple CSI-RS. The operations of 1715 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1715 may be performed as described in reference to Fig.11 The described CSI reporting component 1135 is performed.

[0252] Fig.18 A flow chart illustrating a method 1800 for supporting reference signal pattern association for channel estimation according to one or more aspects of the present disclosure is shown. The operations of the method 1800 may be implemented by a network entity or a component thereof as described herein. For example, the operations of the method 1800 may be implemented by a network entity or a component thereof as described herein. Figures 1 to 8 as well as Figures 13 to 16 The network entity described herein may be executed by the network entity described herein. In some examples, the network entity may execute an instruction set to control the functional elements of the network entity to perform the described functions. Additionally or alternatively, the network entity may use dedicated hardware to perform various aspects of the described functions.

[0253] At 1805, the method may include outputting a control signal that configures a low-density pattern for CSI-RS reception at the UE for a set of multiple antenna ports, wherein the low-density pattern indicates a subset of the set of multiple antenna ports for CSI-RS reception via one or more RBs. The operations of 1805 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1805 may be performed as described in reference to Fig.15 The described low density mode configuration component 1525 is executed.

[0254] At 1810, the method may include outputting a set of multiple CSI-RS according to a low density mode. The operations of 1810 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1810 may be performed as described in reference to Fig.15 The described CSI-RS component 1530 is performed.

[0255] At 1815, the method may include obtaining a CSI report based on a set of multiple CSI-RS. The operations of 1815 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1815 may be performed as described in reference to Fig.15 The described CSI report receiving component 1535 is performed.

[0256] Fig.19A flow chart illustrating a method 1900 for supporting reference signal pattern association for channel estimation according to one or more aspects of the present disclosure is shown. The operations of the method 1900 may be implemented by a device (e.g., a neural network training device, a UE 115) or a component thereof as described herein. For example, the operations of the method 1900 may be implemented by a device (e.g., a neural network training device, a UE 115) or a component thereof as described herein. Figures 1 to 12 The described UE 115 may be performed. In some examples, the UE may execute an instruction set to control the functional elements of the UE to perform the described functions. Additionally or alternatively, the UE may use dedicated hardware to perform various aspects of the described functions.

[0257] At 1905, the method may include obtaining a set of multiple CSI-RS for a set of multiple antenna ports and a set of multiple RBs. The operations of 1905 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1905 may be performed as described in reference to Fig.11 The described CSI-RS receiving component 1130 is performed.

[0258] At 1910, the method may include determining a low density mode for an artificial neural network training process. The operations of 1910 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1910 may be performed as described in reference Fig.11 The described low density mode determination component 1140 is performed.

[0259] At 1915, the method may include training a generalized artificial neural network based on a subset of a set of multiple CSI-RSs according to a determined low density pattern, wherein the determined low density pattern indicates a subset of a set of multiple antenna ports for one or more RBs in a set of multiple RBs. The operations of 1915 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1915 may be performed as described in reference Fig.11 The described neural network training component 1145 is performed.

[0260] At 1920, the method may include outputting the trained generalized artificial neural network. The operations of 1920 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 1920 may be performed as described in reference Fig.11 The described neural network output component 1150 is executed.

[0261] Fig. 20 1 is a flowchart illustrating a method 2000 for supporting reference signal pattern association for channel estimation according to one or more aspects of the present disclosure. The operations of the method 2000 may be implemented by an apparatus (e.g., a neural network training apparatus, a UE 115) or a component thereof as described herein. For example, the operations of the method 2000 may be implemented by an apparatus (e.g., a neural network training apparatus, a UE 115) or a component thereof as described herein. Figures 1 to 12The described UE 115 may be performed. In some examples, the UE may execute an instruction set to control the functional elements of the UE to perform the described functions. Additionally or alternatively, the UE may use dedicated hardware to perform various aspects of the described functions.

[0262] At 2005, the method may include obtaining a set of multiple CSI-RS for a set of multiple antenna ports and a set of multiple RBs. The operations of 2005 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 2005 may be performed as described in reference to Fig.11 The described CSI-RS receiving component 1130 is performed.

[0263] At 2010, the method may include training an artificial neural network specific to one or more low-density patterns based on a subset of a set of multiple CSI-RSs according to one or more low-density patterns configured at the device, wherein a low-density pattern in the one or more low-density patterns indicates a subset of a set of multiple antenna ports for one or more RBs in a set of multiple RBs. The operations of 2010 may be performed according to examples as disclosed herein. In some examples, aspects of the operations of 2010 may be performed as described in reference to Fig.11 The described neural network training component 1145 is performed.

[0264] At 2015, the method may include outputting the trained artificial neural network. The operations of 2015 may be performed according to examples disclosed herein. In some examples, aspects of the operations of 2015 may be performed as described in reference to Fig.11 The described neural network output component 1150 is executed.

[0265] The following provides an overview of various aspects of the disclosure:

[0266] Aspect 1: An apparatus for performing wireless communications at a UE, the apparatus comprising: a processor; and a memory coupled to the processor, the processor being configured to: receive a control signal from a network entity, the control signal configuring a low-density mode for receiving channel state information reference signals for multiple antenna ports, wherein the low-density mode indicates a subset of the multiple antenna ports for receiving the channel state information reference signals via one or more resource blocks; receive multiple channel state information reference signals from the network entity according to the low-density mode; and send a channel state information report to the network entity based at least in part on the multiple channel state information reference signals.

[0267] Aspect 2: An apparatus according to Aspect 1, wherein the processor is further configured to: determine the low-density mode at least in part based on the control signal, the control signal indicating a mapping from the subset of the multiple antenna ports for the one or more resource blocks to the multiple antenna ports.

[0268] Aspect 3: The apparatus according to aspect 2, wherein the mapping is specific to a resource block, specific to a resource block group, or common to multiple resource blocks in a frequency band corresponding to the channel state information reference signal reception.

[0269] Aspect 4: An apparatus according to any one of Aspects 1 to 3, wherein the processor is further configured to: determine the low-density mode at least in part based on the control signal, wherein the control signal indicates a resource block muting mode for one or more antenna ports among the multiple antenna ports.

[0270] Aspect 5: The apparatus according to aspect 4, wherein the resource block muting pattern is specific to one antenna port among the multiple antenna ports, specific to a group of antenna ports among the multiple antenna ports, or common to the multiple antenna ports.

[0271] Aspect 6: An apparatus according to any one of Aspects 1 to 3, wherein the processor is further configured to: determine the low density mode at least in part based on the control signal, wherein the control signal indicates an antenna port muting mode for the one or more resource blocks.

[0272] Aspect 7: The apparatus according to Aspect 6, wherein the antenna port muting pattern is specific to a resource block, specific to a resource block group, or common to multiple resource blocks in a frequency band corresponding to the channel state information reference signal reception.

[0273] Aspect 8: An apparatus according to any one of Aspects 1 to 3, wherein the processor is further configured to: determine the low-density mode at least in part based on the control signal, the control signal indicating a cover code, and the cover code configures multiple antenna port-resource block pairs for reception of the channel state information reference signal.

[0274] Aspect 9: An apparatus according to any one of Aspects 1 to 8, wherein the processor is further configured to: determine a channel state information measurement based at least in part on an artificial neural network and the multiple channel state information reference signals received according to the low-density mode, wherein the channel state information report includes the channel state information measurement.

[0275] Aspect 10: An apparatus according to Aspect 9, wherein the processor is further configured to: zero-fill the received multiple channel state information reference signals based at least in part on the low-density pattern; and input the zero-filled received multiple channel state information reference signals into the artificial neural network, wherein the channel state information measurement is determined based at least in part on the output of the artificial neural network.

[0276] Aspect 11: The apparatus according to any one of aspects 9 to 10, wherein the processor is further configured to: train the artificial neural network based at least in part on the low-density pattern.

[0277] Aspect 12: An apparatus according to any one of Aspects 1 to 11, wherein the control signal comprises a bitmap indicating the low density mode for the channel state information reference signal reception.

[0278] Aspect 13: An apparatus according to any one of Aspects 1 to 11, wherein the control signal indicates a first number of the subset of the multiple antenna ports and a second number of the multiple antenna ports, and the processor is further configured to: determine the low-density mode for receiving the channel state information reference signal based at least in part on the first number, the second number, and a rule, a lookup table, or both for mapping from the first number and the second number to the low-density mode.

[0279] Aspect 14: An apparatus according to any one of Aspects 1 to 3 and 9 to 11, wherein the processor is further configured to: store a plurality of low-density modes, wherein the control signal comprises an index value indicating the low-density mode from the plurality of low-density modes.

[0280] Aspect 15: An apparatus according to any one of Aspects 1 to 14, wherein: the control signal also includes auxiliary information, the auxiliary information indicating a channel type, environmental information, transmission-related information, an antenna configuration corresponding to the multiple antenna ports, or a combination thereof; and the channel state information report is also at least partially based on the auxiliary information.

[0281] Aspect 16: An apparatus for performing wireless communications at a network entity, the apparatus comprising: a processor; and a memory coupled to the processor, the processor being configured to: output a control signal, the control signal configuring a low-density mode for channel state information reference signal reception at a UE for multiple antenna ports, wherein the low-density mode indicates a subset of the multiple antenna ports for receiving the channel state information reference signals via one or more resource blocks; output multiple channel state information reference signals according to the low-density mode; and obtain a channel state information report based at least in part on the multiple channel state information reference signals.

[0282] Aspect 17: The apparatus according to Aspect 16, wherein the control signal comprises a bitmap indicating the low density mode for the channel state information reference signal reception.

[0283] Aspect 18: An apparatus according to Aspect 16, wherein the control signal includes a first control signal and indicates a first number of the subset of the multiple antenna ports and a second number of the multiple antenna ports, and the processor is further configured to: output a second control signal, the second control signal being configured to map a value pair from the first number of the subset of the multiple antenna ports and the second number of the multiple antenna ports to a rule, a lookup table, or both of the low-density mode.

[0284] Aspect 19: The apparatus according to aspect 16, wherein the processor is further configured to: store a plurality of low-density modes, wherein the control signal comprises an index value indicating the low-density mode from the plurality of low-density modes.

[0285] Aspect 20: An apparatus according to any one of Aspects 16 to 19, wherein: the control signal also includes auxiliary information, the auxiliary information indicating a channel type, environmental information, transmission-related information, an antenna configuration corresponding to the multiple antenna ports, or a combination thereof; and the channel state information report is also at least partially based on the auxiliary information.

[0286] Aspect 21: An apparatus for performing wireless communications at a device, the apparatus comprising: a processor; and a memory coupled to the processor, the processor being configured to: obtain multiple channel state information reference signals for multiple antenna ports and multiple resource blocks; determine a low-density pattern for an artificial neural network training process; train a generalized artificial neural network based at least in part on a subset of the multiple channel state information reference signals according to the determined low-density pattern, wherein the determined low-density pattern indicates a subset of the multiple antenna ports for one or more of the multiple resource blocks; and output the trained generalized artificial neural network.

[0287] Aspect 22: An apparatus according to Aspect 21, wherein the processor is further configured to: determine one or more additional low-density patterns for the artificial neural network training process; and further train the generalized artificial neural network based at least in part on the one or more additional low-density patterns.

[0288] Aspect 23: The apparatus according to any one of aspects 21 to 22, wherein the processor is further configured to: randomly select one or more low-density patterns, wherein the low-density pattern is determined at least in part based on the random selection.

[0289] Aspect 24: The apparatus according to any one of aspects 21 to 23, wherein the determined low density pattern indicates a random selection of the subset of the plurality of antenna ports for each resource block in the plurality of resource blocks.

[0290] Aspect 25: An apparatus according to any one of Aspects 21 to 23, wherein: the determined low-density pattern indicates a random selection of the subset of the multiple antenna ports for a first set of resource blocks among the multiple resource blocks; and the selection of the subset of the multiple antenna ports for a second set of resource blocks among the multiple resource blocks is at least partially based on the random selection of the subset of the multiple antenna ports for the first set of resource blocks.

[0291] Aspect 26: An apparatus for performing wireless communications at a device, the apparatus comprising: a processor; and a memory coupled to the processor, the processor being configured to: obtain multiple channel state information reference signals for multiple antenna ports and multiple resource blocks; train an artificial neural network specific to the one or more low-density modes based at least in part on a subset of the multiple channel state information reference signals according to one or more low-density modes configured at the device, wherein a low-density mode in the one or more low-density modes indicates a subset of the multiple antenna ports for one or more of the multiple resource blocks; and output the trained artificial neural network.

[0292] Aspect 27: The apparatus according to Aspect 26, wherein the processor is further configured to: obtain a configuration of the one or more low-density patterns, wherein the artificial neural network is trained at least in part based on the configuration.

[0293] Aspect 28: An apparatus according to any one of Aspects 26 to 27, wherein the processor is further configured to: store the one or more low-density patterns at the device, wherein the artificial neural network is trained at least in part based on the stored one or more low-density patterns.

[0294] Aspect 29: An apparatus according to any one of Aspects 26 to 28, wherein the artificial neural network is specific to a low-density mode, and the processor is further configured to: train one or more additional artificial neural networks specific to one or more additional low-density modes configured at the device; and output the one or more additional trained artificial neural networks.

[0295] Aspect 30: According to the apparatus according to any one of Aspects 26 to 29, the processor configured to output the trained artificial neural network is configured to: output the trained artificial neural network and indicate that the trained artificial neural network is specific to the one or more low-density patterns.

[0296] Aspect 31: A method for performing wireless communications at a UE, the method comprising: receiving a control signal from a network entity, the control signal configuring a low-density mode for channel state information reference signal reception for multiple antenna ports, wherein the low-density mode indicates a subset of the multiple antenna ports for receiving the channel state information reference signals via one or more resource blocks; receiving multiple channel state information reference signals from the network entity according to the low-density mode; and sending a channel state information report to the network entity based at least in part on the multiple channel state information reference signals.

[0297] Aspect 32: According to the method according to Aspect 31, the method also includes: determining the low density mode at least in part based on the control signal, wherein the control signal indicates a mapping from the subset of the multiple antenna ports used for the one or more resource blocks to the multiple antenna ports.

[0298] Aspect 33: The method according to aspect 32, wherein the mapping is specific to a resource block, specific to a resource block group, or common to multiple resource blocks in a frequency band corresponding to the channel state information reference signal reception.

[0299] Aspect 34: According to the method described in any one of Aspects 31 to 33, the method further includes: determining the low-density mode at least in part based on the control signal, wherein the control signal indicates a resource block muting mode for one or more antenna ports among the multiple antenna ports.

[0300] Aspect 35: The method according to Aspect 34, wherein the resource block muting pattern is specific to one antenna port among the multiple antenna ports, specific to a group of antenna ports among the multiple antenna ports, or common to the multiple antenna ports.

[0301] Aspect 36: According to any one of Aspects 31 to 33, the method further includes: determining the low density mode at least in part based on the control signal, wherein the control signal indicates an antenna port muting mode for the one or more resource blocks.

[0302] Aspect 37: The method according to aspect 36, wherein the antenna port muting pattern is specific to a resource block, specific to a resource block group, or common to multiple resource blocks in a frequency band corresponding to the channel state information reference signal reception.

[0303] Aspect 38: According to the method described in any one of Aspects 31 to 33, the method further includes: determining the low-density mode at least in part based on the control signal, the control signal indicating a cover code, and the cover code configuring multiple antenna port-resource block pairs for reception of the channel state information reference signal.

[0304] Aspect 39: According to the method described in any one of Aspects 31 to 38, the method also includes: determining a channel state information measurement based at least in part on an artificial neural network and the multiple channel state information reference signals received according to the low-density mode, wherein the channel state information report includes the channel state information measurement.

[0305] Aspect 40: According to the method described in Aspect 39, the method also includes: zero-filling the received multiple channel state information reference signals at least in part based on the low-density mode; and inputting the zero-filled received multiple channel state information reference signals into the artificial neural network, wherein the channel state information measurement is determined at least in part based on the output of the artificial neural network.

[0306] Aspect 41: The method according to any one of Aspects 39 to 40, further comprising: training the artificial neural network based at least in part on the low-density pattern.

[0307] Aspect 42: A method according to any one of Aspects 31 to 41, wherein the control signal comprises a bitmap indicating the low density mode for the channel state information reference signal reception.

[0308] Aspect 43: A method according to any one of Aspects 31 to 41, wherein the control signal indicates a first number of the subset of the multiple antenna ports and a second number of the multiple antenna ports, and the method further includes: determining the low-density mode for receiving the channel state information reference signal based at least in part on the first number, the second number, and a rule, a lookup table, or both for mapping from the first number and the second number to the low-density mode.

[0309] Aspect 44: According to the method described in any one of Aspects 31 to 33 and 39 to 41, the method further includes: storing a plurality of low-density modes, wherein the control signal includes an index value indicating the low-density mode from the plurality of low-density modes.

[0310] Aspect 45: A method according to any one of Aspects 31 to 44, wherein: the control signal also includes auxiliary information, the auxiliary information indicating a channel type, environmental information, transmission-related information, an antenna configuration corresponding to the multiple antenna ports, or a combination thereof; and the channel state information report is also at least partially based on the auxiliary information.

[0311] Aspect 46: A method for performing wireless communications at a network entity, the method comprising: outputting a control signal, the control signal configuring a low-density mode for channel state information reference signal reception at a UE for multiple antenna ports, wherein the low-density mode indicates a subset of the multiple antenna ports for receiving the channel state information reference signal via one or more resource blocks; outputting multiple channel state information reference signals according to the low-density mode; and obtaining a channel state information report based at least in part on the multiple channel state information reference signals.

[0312] Aspect 47: The method according to aspect 46, wherein the control signal comprises a bitmap, the bitmap indicating the low density mode for the channel state information reference signal reception.

[0313] Aspect 48: A method according to Aspect 46, wherein the control signal includes a first control signal and indicates a first number of the subset of the multiple antenna ports and a second number of the multiple antenna ports, and the method further includes: outputting a second control signal, the second control signal being configured to map a value pair from the first number of the subset of the multiple antenna ports and the second number of the multiple antenna ports to a rule, a lookup table, or both of the low-density mode.

[0314] Aspect 49: The method according to aspect 46, the method further comprising: storing a plurality of low-density modes, wherein the control signal comprises an index value indicating the low-density mode from the plurality of low-density modes.

[0315] Aspect 50: A method according to any one of Aspects 46 to 49, wherein the control signal also includes: auxiliary information, the auxiliary information indicating a channel type, environmental information, transmission-related information, an antenna configuration corresponding to the multiple antenna ports, or a combination thereof; and the channel state information report is also based at least in part on the auxiliary information.

[0316] Aspect 51: A method for performing wireless communications at a device, the method comprising: obtaining multiple channel state information reference signals for multiple antenna ports and multiple resource blocks; determining a low density pattern for an artificial neural network training process; training a generalized artificial neural network based at least in part on a subset of the multiple channel state information reference signals according to the determined low density pattern, wherein the determined low density pattern indicates a subset of the multiple antenna ports for one or more resource blocks of the multiple resource blocks; and outputting the trained generalized artificial neural network.

[0317] Aspect 52: According to the method of Aspect 51, the method also includes: determining one or more additional low-density patterns for the artificial neural network training process; and further training the generalized artificial neural network based at least in part on the one or more additional low-density patterns.

[0318] Aspect 53: According to the method according to any one of aspects 51 to 52, the method further includes: randomly selecting one or more low-density patterns, wherein the low-density pattern is determined at least in part based on the random selection.

[0319] Aspect 54: The method according to any one of aspects 51 to 53, wherein the determined low density pattern indicates a random selection of the subset of the plurality of antenna ports for each resource block in the plurality of resource blocks.

[0320] Aspect 55: A method according to any one of Aspects 51 to 53, wherein: the determined low-density pattern indicates a random selection of the subset of the multiple antenna ports for a first set of resource blocks among the multiple resource blocks; and the selection of the subset of the multiple antenna ports for a second set of resource blocks among the multiple resource blocks is at least partially based on the random selection of the subset of the multiple antenna ports for the first set of resource blocks.

[0321] Aspect 56: A method for performing wireless communications at a device, the method comprising: obtaining multiple channel state information reference signals for multiple antenna ports and multiple resource blocks; training an artificial neural network specific to the one or more low-density modes based at least in part on a subset of the multiple channel state information reference signals according to one or more low-density modes configured at the device, wherein a low-density mode in the one or more low-density modes indicates a subset of the multiple antenna ports used for one or more of the multiple resource blocks; and outputting the trained artificial neural network.

[0322] Aspect 57: The method according to Aspect 56, further comprising: obtaining a configuration of the one or more low-density patterns, wherein the artificial neural network is trained at least in part based on the configuration.

[0323] Aspect 58: According to the method described in any one of Aspects 56 to 57, the method further includes: storing the one or more low-density patterns at the device, wherein the artificial neural network is trained at least in part based on the stored one or more low-density patterns.

[0324] Aspect 59: A method according to any one of Aspects 56 to 58, wherein the artificial neural network is specific to a low-density mode, the method further comprising: training one or more additional artificial neural networks specific to one or more additional low-density modes configured at the device; and outputting the one or more additional trained artificial neural networks.

[0325] Aspect 60: The method according to any one of Aspects 56 to 59, wherein outputting the trained artificial neural network further comprises: outputting the trained artificial neural network and indicating that the trained artificial neural network is specific to the one or more low-density patterns.

[0326] Aspect 61: An apparatus for wireless communication at a UE, the apparatus comprising at least one component for performing a method according to any one of aspects 31 to 45.

[0327] Aspect 62: A non-transitory computer-readable medium storing a code for wireless communication at a UE, the code comprising instructions executable by a processor to perform a method according to any one of aspects 31 to 45.

[0328] Aspect 63: An apparatus for wireless communication at a network entity, the apparatus comprising at least one component for performing a method according to any one of aspects 46 to 50.

[0329] Aspect 64: A non-transitory computer-readable medium storing code for wireless communication at a network entity, the code comprising instructions executable by a processor to perform a method according to any one of aspects 46 to 50.

[0330] Aspect 65: An apparatus for wireless communication at a device, the apparatus comprising at least one component for performing a method according to any one of aspects 51 to 55.

[0331] Aspect 66: A non-transitory computer-readable medium storing code for wireless communication at a device, the code comprising instructions executable by a processor to perform a method according to any one of aspects 51 to 55.

[0332] Aspect 67: An apparatus for wireless communication at a device, the apparatus comprising at least one component for performing a method according to any one of aspects 56 to 60.

[0333] Aspect 68: A non-transitory computer-readable medium storing code for wireless communication at a device, the code comprising instructions executable by a processor to perform a method according to any one of aspects 56 to 60.

[0334] It should be noted that the methods described herein describe possible implementations, and that the various operations and steps may be rearranged or otherwise modified and that other implementations are possible. Furthermore, aspects from two or more methods may be combined.

[0335] Although aspects of LTE, LTE-A, LTE-A Pro, or NR systems may be described for example purposes, and LTE, LTE-A, LTE-A Pro, or NR terminology may be used in much of the description, the techniques described herein may also be applicable to networks other than LTE, LTE-A, LTE-A Pro, or NR networks. For example, the techniques described may be applicable to various other wireless communication systems, such as Ultra Mobile Broadband (UMB), Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, Flash-OFDM, and other systems and radio technologies not explicitly mentioned herein.

[0336] The information and signals described herein may be represented using any of a variety of different techniques and methods. For example, data, instructions, commands, information, signals, bits, symbols, and chips mentioned throughout the specification may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or optical particles, or any combination thereof.

[0337] The various illustrative blocks and components described in conjunction with the disclosure herein may be implemented or performed using a general purpose processor, DSP, ASIC, CPU, FPGA or other programmable logic device, discrete gate or transistor logic components, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in an alternative, the processor may be any processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices (e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration).

[0338] The functions described herein may be implemented using hardware, software executed by a processor, firmware, or any combination thereof. When implemented using software executed by a processor, the functions may be stored as one or more instructions or codes of a computer-readable medium or sent using one or more instructions or codes of a computer-readable medium. Other examples and specific implementations are within the scope of the present disclosure and the appended claims. For example, due to the nature of software, the functions described herein may be implemented using software executed by a processor, hardware, firmware, hard wiring, or a combination of any of these items. Features that implement the functions may also be physically located at different locations, including being distributed so that the various parts of the functions are implemented at different physical locations.

[0339] Computer-readable medium includes both non-transient computer storage medium and communication medium, and it includes any medium that promotes computer program to be transmitted from one position to another position.Non-transient storage medium can be any available medium that can be accessed by general or special-purpose computer.By way of example and not limitation, non-transient computer-readable medium can include RAM, ROM, electrically erasable programmable ROM (EEPROM), flash memory, compact disc (CD) ROM or other optical disc storage device, disk storage device or other magnetic storage device, or can be used for carrying or storing desired program code parts and any other non-transient medium that can be accessed by general or special-purpose computer or general or special-purpose processor in the form of instruction or data structure.Moreover, any connection is appropriately referred to as computer-readable medium.For example, if software is sent from website, server or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL) or wireless technology such as infrared, radio and microwave, then coaxial cable, fiber optic cable, twisted pair, DSL or wireless technology such as infrared, radio and microwave are included in the definition of computer-readable medium. Disks and optical disks as used herein include CDs, laser optical disks, optical optical disks, digital versatile disks (DVDs), floppy disks, and Blu-ray disks. Disks can reproduce data magnetically, and optical disks can reproduce data optically using lasers. Combinations of the above are also included within the scope of computer-readable media.

[0340] As used herein (including in the claims), "or" used in a list of items (e.g., a list of items followed by a phrase such as "at least one of" or "one or more of") indicates an inclusive list, so that, for example, a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C). Moreover, as used herein, the phrase "based on" should not be interpreted as a reference to a closed set of conditions. For example, an example step described as "based on condition A" can be based on both condition A and condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase "based on" should be interpreted in the same manner as the phrase "based at least in part on."

[0341] The term "determining" encompasses a variety of actions, and thus, "determining" may include calculating, computing, processing, deriving, investigating, looking up (such as via looking up in a table, database or other data structure), ascertaining, and the like. Also, "determining" may include receiving (e.g., receiving information), accessing (e.g., accessing data stored in a memory), etc. Also, "determining" may include parsing, retrieving, selecting, choosing, establishing, and other such similar actions.

[0342] In the drawings, similar components or features may have the same reference label. In addition, various components of the same type may be distinguished by following the reference label with a dash and a second label to distinguish between the similar components. If only the first reference label is used in the specification, the description may apply to any of the similar components having the same first reference label, regardless of the second or other subsequent reference labels.

[0343] The descriptions set forth herein in conjunction with the accompanying drawings describe example configurations and do not represent all examples that may be implemented or within the scope of the claims. The term "example" as used herein means "used as an example, instance, or illustration," rather than "preferred" or "having advantages over other examples." The specific implementation includes specific details to provide an understanding of the described techniques. However, these techniques may be practiced without these specific details. In some cases, known structures and devices are shown in block diagram form to avoid obscuring the concepts of the described examples.

[0344] The description herein is provided to enable one of ordinary skill in the art to implement or use the present disclosure. Various modifications to the present disclosure will be apparent to one of ordinary skill in the art, and the general principles defined herein may be applied to other variations without departing from the scope of the present disclosure. Thus, the present disclosure is not limited to the examples and designs described herein, but should be granted the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An apparatus for wireless communication at a user equipment (UE), the apparatus comprising: processor; and a memory coupled to the processor, wherein the processor is configured to: receiving a control signal from a network entity, the control signal configuring a low density mode for channel state information reference signal reception for a plurality of antenna ports, wherein the low density mode indicates a subset of the plurality of antenna ports for the channel state information reference signal reception via one or more resource blocks; receiving a plurality of channel state information reference signals from the network entity according to the low density mode; as well as A channel state information report is sent to the network entity based at least in part on the plurality of channel state information reference signals.

2. The apparatus of claim 1, wherein the processor is further configured to: The low density mode is determined based at least in part on the control signal indicating a mapping from the subset of the plurality of antenna ports for the one or more resource blocks to the plurality of antenna ports.

3. The apparatus of claim 2, wherein the mapping is resource block specific, resource block group specific, or common to multiple resource blocks in a frequency band corresponding to the channel state information reference signal reception.

4. The apparatus of claim 1, wherein the processor is further configured to: The low density mode is determined based at least in part on the control signal indicating a resource block muting pattern for one or more of the plurality of antenna ports.

5. The apparatus of claim 4, wherein the resource block muting pattern is specific to one of the multiple antenna ports, specific to a group of antenna ports among the multiple antenna ports, or common to the multiple antenna ports.

6. The apparatus of claim 1, wherein the processor is further configured to: The low density mode is determined based at least in part on the control signal indicating an antenna port muting pattern for the one or more resource blocks.

7. The apparatus of claim 6, wherein the antenna port muting pattern is specific to a resource block, specific to a resource block group, or common to a plurality of resource blocks in a frequency band corresponding to the channel state information reference signal reception.

8. The apparatus of claim 1, wherein the processor is further configured to: The low density mode is determined based at least in part on the control signal, the control signal indicating a cover code, the cover code configuring a plurality of antenna port-resource block pairs for the channel state information reference signal reception.

9. The apparatus of claim 1, wherein the processor is further configured to: Channel state information measurements are determined based at least in part on an artificial neural network and the plurality of channel state information reference signals received according to the low density mode, wherein the channel state information report includes the channel state information measurements.

10. The apparatus of claim 9, wherein the processor is further configured to: zero padding the received plurality of channel state information reference signals based at least in part on the low density pattern; and The zero-filled received plurality of channel state information reference signals are input into the artificial neural network, wherein the channel state information measurement is determined based at least in part on an output of the artificial neural network.

11. The apparatus of claim 9, wherein the processor is further configured to: The artificial neural network is trained based at least in part on the low-density patterns.

12. The apparatus of claim 1, wherein the control signal comprises a bitmap indicating the low density mode for the channel state information reference signal reception.

13. The apparatus of claim 1 , wherein the control signal indicates a first number of the subset of the plurality of antenna ports and a second number of the plurality of antenna ports, and the processor is further configured to: The low density mode for the channel state information reference signal reception is determined based at least in part on the first number, the second number, and a rule, a lookup table, or both for mapping from the first number and the second number to the low density mode.

14. The apparatus of claim 1, wherein the processor is further configured to: A plurality of low-density patterns are stored, wherein the control signal comprises an index value indicating the low-density pattern from the plurality of low-density patterns.

15. The device according to claim 1, wherein: The control signal further includes auxiliary information indicating a channel type, environmental information, transmission related information, an antenna configuration corresponding to the plurality of antenna ports, or a combination thereof; and The channel state information report is also based at least in part on the assistance information.

16. An apparatus for wireless communication at a network entity, the apparatus comprising: processor; and a memory coupled to the processor, wherein the processor is configured to: outputting a control signal that configures a low-density mode for channel state information reference signal reception at a user equipment (UE) for a plurality of antenna ports, wherein the low-density mode indicates a subset of the plurality of antenna ports for the channel state information reference signal reception via one or more resource blocks; outputting a plurality of channel state information reference signals according to the low density mode; as well as A channel state information report is obtained based at least in part on the plurality of channel state information reference signals.

17. The apparatus of claim 16, wherein the control signal comprises a bitmap indicating the low density mode for the channel state information reference signal reception.

18. The apparatus of claim 16, wherein the control signal comprises a first control signal and indicates a first number of the subsets of the plurality of antenna ports and a second number of the plurality of antenna ports, and the processor is further configured to: A second control signal is outputted, the second control signal being configured for mapping from a value pair of the first number of the subset of the plurality of antenna ports and the second number of the plurality of antenna ports to a rule, a lookup table, or both for the low density mode.

19. The apparatus of claim 16, wherein the processor is further configured to: A plurality of low-density patterns are stored, wherein the control signal comprises an index value indicating the low-density pattern from the plurality of low-density patterns.

20. The apparatus of claim 16, wherein: The control signal further includes auxiliary information indicating a channel type, environmental information, transmission related information, an antenna configuration corresponding to the plurality of antenna ports, or a combination thereof; and The channel state information report is also based at least in part on the assistance information.

21. An apparatus for wireless communication at a device, the apparatus comprising: processor; and a memory coupled to the processor, wherein the processor is configured to: obtaining a plurality of channel state information reference signals for a plurality of antenna ports and a plurality of resource blocks; Identify low-density patterns for use in the artificial neural network training process; training a generalized artificial neural network based at least in part on a subset of the plurality of channel state information reference signals according to a determined low density pattern, wherein the determined low density pattern indicates a subset of the plurality of antenna ports used for one or more resource blocks of the plurality of resource blocks; as well as Output the trained generalized artificial neural network.

22. The apparatus of claim 21, wherein the processor is further configured to: determining one or more additional low-density patterns for use in the artificial neural network training process; and The generalized artificial neural network is further trained based at least in part on the one or more additional low-density patterns.

23. The apparatus of claim 21, wherein the processor is further configured to: One or more low-density patterns are randomly selected, wherein the low-density patterns are determined based at least in part on the random selections.

24. The apparatus of claim 21, wherein the determined low density pattern indicates a random selection of the subset of the plurality of antenna ports for each of the plurality of resource blocks.

25. The apparatus of claim 21, wherein: The determined low density pattern indicates a random selection of the subset of the plurality of antenna ports for a first set of resource blocks in the plurality of resource blocks; and The selection of the subset of the plurality of antenna ports for a second set of resource blocks in the plurality of resource blocks is based at least in part on the random selection of the subset of the plurality of antenna ports for the first set of resource blocks.

26. An apparatus for wireless communication at a device, the apparatus comprising: processor; and a memory coupled to the processor, wherein the processor is configured to: obtaining a plurality of channel state information reference signals for a plurality of antenna ports and a plurality of resource blocks; training an artificial neural network specific to the one or more low density patterns based at least in part on a subset of the plurality of channel state information reference signals according to the one or more low density patterns configured at the device, wherein a low density pattern in the one or more low density patterns indicates a subset of the plurality of antenna ports for one or more resource blocks in the plurality of resource blocks; as well as Output the trained artificial neural network.

27. The apparatus of claim 26, wherein the processor is further configured to: A configuration of the one or more low-density patterns is obtained, wherein the artificial neural network is trained based at least in part on the configuration.

28. The apparatus of claim 26, wherein the processor is further configured to: The one or more low-density patterns are stored at the device, wherein the artificial neural network is trained based at least in part on the stored one or more low-density patterns.

29. The apparatus of claim 26, wherein the artificial neural network is specific to low density mode, and the processor is further configured to: training one or more additional artificial neural networks specific to one or more additional low-density modes configured at the device; and The one or more additionally trained artificial neural networks are outputted.

30. The apparatus of claim 26, wherein the processor configured to output the trained artificial neural network is configured to: The trained artificial neural network is output and indicates that the trained artificial neural network is specific to the one or more low-density patterns.

Images