Dynamic channel state information compression based on input channel state information spectral entropy
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-05-16
- Publication Date
- 2026-08-13
Smart Images
Figure US2025029749_13082026_PF_FP_ABST
Abstract
Description
DYNAMIC CHANNEL STATE INFORMATION COMPRESSION BASED ON INPUT CHANNEL STATE INFORMATION SPECTRAL ENTROPYTECHNICAL FIELD
[0001] This application relates generally to wireless communication systems, including wireless communication systems using AI / ML models for CSI feedback compression and decompression.BACKGROUND
[0002] Wireless mobile communication technology uses various standards and protocols to transmit data between a base station and a wireless communication device. Wireless communication system standards and protocols can include, for example, 3rd Generation Partnership Project (3GPP) Long Term Evolution (LTE) (e.g., 4G), 3GPP New Radio (NR) (e.g., 5G), and Institute of Electrical and Electronics Engineers (IEEE) 802.11 standard for Wireless Local Area Networks (WLAN) (commonly known to industry groups as Wi-Fi®).
[0003] As contemplated by the 3GPP, different wireless communication systems' standards and protocols can use various radio access networks (RANs) for communicating between a base station of the RAN (which may also sometimes be referred to generally as a RAN node, a network node, or simply a node) and a wireless communication device known as a user equipment (UE). 3GPP RANs can include, for example. Global System for Mobile communications (GSM), Enhanced Data Rates for GSM Evolution (EDGE) RAN (GERAN). Universal Terrestrial Radio Access Network (UTRAN), Evolved Universal Terrestrial Radio Access Network (E-UTRAN), and / or Next-Generation Radio Access Network (NG-RAN).
[0004] Each RAN may use one or more radio access technologies (RATs) to perform communication between the base station and the UE. For example, the GERAN implements GSM and / or EDGE RAT, the UTRAN implements Universal Mobile Telecommunication System (UMTS) RAT or other 3 GPP RAT, the E-UTRAN implements LTE RAT (sometimes simply referred to as LTE). and NG-RAN implements NR RAT (sometimes referred to herein as 5G RAT, 5GNR RAT, or simply NR). In certain deployments, the E-UTRAN may also implement NR RAT. In certain deployments, NG-RAN may also implement LTE RAT.14898-6248-3268 1 P70857WO1
[0005] A base station used by a RAN may correspond to that RAN. One example of an E-UTRAN base station is an Evolved Universal Terrestrial Radio Access Network (E-UTRAN) Node B (also commonly denoted as evolved Node B, enhanced Node B, eNodeB, or eNB). One example of an NG-RAN base station is a next generation Node B (also sometimes referred to as a g Node B or gNB).
[0006] A RAN provides its communication services with external entities through its connection to a core network (CN). For example, E-UTRAN may utilize an Evolved Packet Core (EPC) while NG-RAN may utilize a 5G Core Network (5GC).
[0007] Frequency bands for 5G NR may be separated into two or more different frequency ranges. For example, Frequency Range 1 (FR1) may include frequency bands operating in sub-6 gigahertz (GHz) frequencies, some of which are bands that may be used by previous standards, and may potentially be extended to cover new spectrum offerings from 410 megahertz (MHz) to 7125 MHz. Frequency Range 2 (FR2) may include frequency bands from 24.25 GHz to 52.6 GHz. Note that in some systems, FR2 may also include frequency bands from 52.6 GHz to 71 GHz (or beyond). Bands in the millimeter wave (mmWave) range of FR2 may have smaller coverage but potentially higher available bandwidth than bands in FR1. Skilled persons will recognize these frequency ranges, which are provided by way of example, may change from time to time or from region to region.BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS
[0008] To easily identify the discussion of any particular element or act, the most significant digit or digits in a reference number refer to the figure number in which that element is first introduced.
[0009] FIG. 1 illustrates a diagram showing an example of a two-sided AI / ML model for CSI compression and decompression, according to embodiments discussed herein.
[0010] FIG. 2 illustrates an example of CSI compression and decompression.
[0011] FIG. 3 illustrates an example of performing 2D DFT to generate a power profile, according to embodiments herein.
[0012] FIG. 4 illustrates an example flow diagram for dynamic CSI compression using a PSE value, according to embodiments herein.
[0013] FIG. 5 illustrates a method of a UE, according to embodiments herein.
[0014] FIG. 6 illustrates a method of a base station, according to embodiments herein.24898-6248-3268 1 P70857WO1
[0015] FIG. 7 illustrates an example architecture of a wireless communication system, according to embodiments disclosed herein.
[0016] FIG. 8 illustrates a system for performing signaling between a wireless device and a network device, according to embodiments disclosed herein.DETAILED DESCRIPTION
[0017] Various embodiments are described with regard to a UE. However, reference to a UE is merely provided for illustrative purposes. The example embodiments may be utilized with any electronic component that may establish a connection to a network and is configured with the hardware, software, and / or firmware to exchange information and data with the network. Therefore, the UE as described herein is used to represent any appropriate electronic component.
[0018] Downlink channel state information (CSI) may be sent from a UE to a base station through feedback channels. The base station may use the CSI feedback to, for example, reduce interference and increase throughput for massive multiple input multiple output (MIMO) communication.
[0019] It may be understood that such feedback represents a relatively large amount of signaling overhead. In various wireless communication systems, vector quantization or codebook-based feedback may be used with the expectation of reducing this overhead. The feedback quantities resulting from these approaches, however, scale linearly with the number of transmit antennas. Accordingly, these approaches may still, for some cases (e.g., when hundreds or thousands of centralized or distributed transmit antennas are used) represent a high level of signaling overhead.
[0020] Accordingly, in various wireless communication systems, artificial intelligence (Al)Zmachine learning (ML)-based CSI encoding / compression and decoding / decompression mechanisms may be used in order to reduce signaling overhead associated with the transmission of CSI from the UE to the base station.
[0021] FIG. 1 illustrates a diagram 100 showing an example of a two-sided AI / ML model 102 for CSI compression and decompression, according to examples discussed herein. The AI / ML model 102 includes the (logical) UE side 104 (a portion of the AI / ML model 102 that exists at a UE 106) and the (logical) network side 108 (a portion of the AI / ML model 102 that exists at, for example, a base station of a network 110), as illustrated.34898-6248-3268 1 P70857WO1
[0022] The UE side 104 of the AI / ML model 102 that operates at the UE 106 includes an encoder 112. The encoder 112 is configured to accept an input 116 and to provide a bitstream 118 that is based on that input 116 as output. As illustrated, in some cases, the input 116 may include CSI, such as a raw downlink (DL) channel estimate or precoder information (such as a codebook-based indication of a precoder W and / or a set of eigenvectors corresponding to a precoder W).
[0023] The bitstream 118 is then transmitted from the UE 106 to the network 110.
[0024] The network side 108 of the AI / ML model 102 that operates at the network 110 (e.g., a base station of the network 110) includes a decoder 114. The decoder 114 is configured to accept the bitstream 118 as input and to decode information therein as output 120 to the network 110 for further processing. In this way, the information from the input 116 is made known to the network 110. Accordingly, in some cases, the output 120 may be understood to include CSI, such as a raw DL channel estimate or precoder information (such as a codebook-based indication of a precoder W and / or a set of eigenvectors corresponding to a precoder W), corresponding to the format of the input 116.
[0025] Based on the encoding mechanism used by the encoder 112, the bitstream 118 may be smaller than the raw or data as presented in the input 116. The encoder 112 may thus be understood to “compress” the input 116 into the bitstream, which is correspondingly understood to represent “compressed” information.
[0026] The result is that the transmission of the bitstream 118 to from the UE 106 to the network 110 results in the use of fewer radio resources than an alternative case where the input 116 is itself sent from the UE 106 to the network side 108 without such encoding / compression.
[0027] The output 120 may correspondingly be referred to variously herein as “decoded,” “decompressed,” “recovered,” etc.
[0028] It may be beneficial to monitor the operation of an AI / ML model 102 model for CSI compression and decompression. This monitoring may be used to determine that, for example, a given AI / ML model is no longer performing with acceptable accuracy / precision (in the sense that, for example, the output 120 of the decoder 114 exhibits a sufficient or insufficient match to the input 116 of the encoder 112), and thus that the AI / ML model needs to be retrained and / or that use of the AI / ML model should be ended.44898-6248-3268 1 P70857WO1
[0029] Various aspects with respect to the utility and / or feasibility of various types of monitoring for an AI / ML model for CSI compression and decompression may be considered. For example, when considering aspects for network-side monitoring for such an AI / ML model, overhead, latency, complexity, monitoring accuracy, and / or corresponding UE capabilities may be relevant factors. Such monitoring may be based on a target CSI that is reported by the UE to the network via an enhanced Type 2 (eT2) codebook or some other eT2-like high resolution codebook. Sounding reference signal (SRS) monitoring may be used.
[0030] As another example, when considering aspects for UE-side monitoring for such an AI / ML model, overhead, latency, complexity, monitoring accuracy, and UE capabilities may be relevant factors. In some cases, the monitoring may be based on an output of a CSI reconstruction model at the UE. The CSI reconstruction model used at the UE may be the same as the CSI reconstruction model (e.g., a decoder) used at the network side, may be a reference CSI reconstruction model (e.g., a reference decoder) provided to the UE by the network, or may be a proxy CSI reconstruction model (e.g., that acts as proxy for a decoder at the network) that is developed at the UE side.
[0031] In some cases, the monitoring may leverage direct estimation of a key performance indicator (KPI) (e.g., that is based on a squared generalized cosine similarity (SGCS) calculation), without using a reconstruction of a target CSI at the UE side.
[0032] In some cases, the monitoring may use estimates of monitoring outputs that are other than intermediate KPIs, without using a reconstruction of a target CSI at the UE side.
[0033] In some cases, the monitoring may be based on a precoded reference signal (e.g., a channel state information reference signal (CSI-RS), a demodulation reference signal (DMRS)) that is transmitted from the network to the UE that is based on an output of the CSI reconstruction model (e.g., the decoder) used at the network.
[0034] In some cases, the monitoring may be based on an output of the CSI reconstruction model (e.g., the decoder) at the network that is indicated to the UE by the network using an eT2 codebook or some other eT2-like high resolution codebook.
[0035] FIG. 2 illustrates an example of CSI compression and decompression.
[0036] In some wireless communication systems, a CSI two-sided AI / ML model encoder (e g., as described in FIG. 1) may be configured through the use of various 54898-6248-3268 1 P70857WO1configuration parameters, such as input / dimensionality parameters, output parameters and size parameters, etc. For example, input size / dimensionality parameters may include a number of layers, a number of sub-bands, and a number of transmit (Tx) ports. The output parameters may include a number of floating numbers flowing out of the two-sided AI / ML model which is determined by the compression ratio. Additionally or alternatively, the configurations may include a number of bits per floating number. The payload size that will be transmitted may depend on a compression ratio and quantization levels used for CSI compression. In various cases, the CSI AI / ML model decoder (e.g., as described in FIG. 1) will need to know the configurations used by the encoder in order to successfully recover the CSI.
[0037] For example, at a UE, CSI feedback 204 and a configuration 202 may be passed to an encoder 206 of a two-sided AI / ML model sited at the UE used for CSI compression. Then, the two-sided AI / ML model encoder 206 may pass a float (e g., a bitstream) of the encoded CSI feedback 204 to a sigmoid function 208 and subsequently quantization 210 may be performed on the output of the sigmoid function 208. As such, an AI / ML compressed CSI feedback (the pay load of bits 212) may be achieved. The AI / ML compressed CSI feedback (in the form of the payload of bits 212) may be transmitted over a wireless channel 214 to the base station. Additionally, the configuration 202 and quantization 210 level used for the performed quantization 210 for compression at the two-sided AI / ML model encoder may be transmitted to the base station. Then, the base station may perform de-quantization 216 (based on the transmitted quantization 210 level) and perform an inverse NL 218 on the result of the de-quantization 216. The result may be passed to a decoder 220 of the two-sided AI / ML model sited at the base station which may decompress the result of the inverse NL 218 using the transmitted configuration 202. As a result, the decoder 220 may output an estimate of CSI feedback 222 (e.g., a recovered CSI feedback).
[0038] Embodiments herein introduce an encoder / decoder AI / ML model pair for operating under dynamic configurations. As a result, embodiments herein using the dynamic configuration may achieve an optimal tradeoff between signaling overhead (e.g.. payload size) and performance under various different channels and noise conditions. For example, at high signal-to-noise ratio (SNR) conditions, a large number of quantization levels may be used to preserve the fidelity of the CSI to achieve the precoding gains. In some other examples, when the channel conditions indicate that a64898-6248-3268 1 P70857WO1low-rank channel may be supported and an SNR is low, the CSI compression and quantization may be more aggressive. As such, it may be beneficial to know how compressible the channel is.
[0039] The compressibility of the channel may depend on the measure of entropy of the channel. For example, the more entropy the channel has (e.g., the more uncertainty’ in the channel), the less compressible it is, which will result in a larger payload. Embodiments herein correspondingly introduce mechanisms for measuring a channel entropy and guiding an adaptation of configuration parameters used by an AI / ML model for CSI compression / decompression in an adaptive fashion.
[0040] In some embodiments, a PSE value may be calculated. For example, the PSE value, in the context of wireless channels, measures the uncertainty in the distribution of power across the frequency and spatial components of a signal, which is directly related to how predictable or random the channel's frequency response is. When applied to wireless channel compression, the PSE value may help to determine which parts of the channel are more concentrated (e.g., having a low entropy) and which parts are more spread out (e.g., having a high entropy).
[0041] In some cases, the PSE value may indicate that the channel has low power spectral entropy (e.g., a low PSE value). For example, when the PSE value is low it may be that the channel’s power is concentrated in a few frequencies, meaning that the wireless channel has a relatively simple frequency structure. This scenario occurs in situations where the channel is sparse (e.g., line-of-sight, limited scattering), which is common in urban macrocell environments or in systems with highly directional beamforming (e g., massive MIMO). In some other cases, the PSE value may indicate that the channel has a high power spectral entropy (e.g., a high PSE value). For example, when the PSE is high it may be that the channel’s power is more evenly distributed across many' frequencies, suggesting a complex or highly random channel. This often happens in scenarios with high mobility,, urban microcells, or faded signals with many multipath components, where the channel’s response is unpredictable or rapidly changing over time. Variations in the PSE value may indicate events of propagation conditions changing and may trigger AI / ML monitoring events.
[0042] In various embodiments, dynamic CSI compression / decompression may leverage calculated values of a PSE and / or temporal variations in these PSE values. By doing so, a UE and / or a network may adaptively adjust a compression / decompression74898-6248-3268 1 P70857WO1process, thereby optimizing a balance between feedback overhead and accuracy in representing a channel state.
[0043] A smoothness or sparsity of CSI samples, as quantified by the CSI samples’ calculated PSE value, can vary significantly due to changes in the radio frequency (RF) environment (e.g.. mobility, interference, etc.). By dynamically adjusting the compression process based on the calculated PSE value of the channel, the system may reduce feedback overhead by compressing the CSI samples more aggressively when the channel is smooth and predictable. Additionally, the system may enhance reconstruction accuracy by compressing less aggressively when the channel is complex and less predictable (e.g., a higher PSE value), ensuring higher fidelity in the reconstructed CSI.
[0044] In some embodiments, a PSE value may be calculated based on a power profile of a channel. A CSI channel may be converted to a power profile using discrete Fourier transform (DFT). For example, consider a MIMO channel with a number of Tx antenna ports Nt, and a number of carriers in the frequency domain Nc, that is H̃ ∈ ℂN×N. In order to derive the power profile of the channel in the angular space (e.g., spatial frequencies) and the temporal delay space (e g., frequencies) a two dimensional DFT (2D DFT) may be used. For example, the 2D DFT H = FdH̃FaHmay be used, where Fdand Faare Nc× Ncand Nt× NtDFT matrices. As a result, the CSI channel estimates (e.g., H̃ ∈ ℂN×N) may be converted to the power profile through the use of 2D DFT processing.
[0045] FIG. 3 illustrates an example of performing 2D DFT 306 to generate a power profile 304 based on a MIMO channel 302, according to embodiments herein. For example, the MIMO channel 302 corresponding to a number of Tx antenna ports and a number of carriers may have 2D DFT 306 performed on it to generate a power profile 304.
[0046] In some embodiments, to calculate the PSE value of the channel, a first step may include obtaining the channel’s frequency response CSI, at the UE, from a reference signal (e.g., transmitted by a base station) or, at the base station, from the recovered CSI feedback. For example, a channel matrix may be obtained (e.g., H[ / c][m]) across the subcarrier domain k and spatial Tx antenna port m. In a second step, the channel may be transformed to an angular domain and a temporal delay domain. For example, a transformed matrix may be obtained across angular domain i and delay domain j according to H[i][j] = FdH̃FaH. In a third step, a normalized power profile (e.g.. a power84898-6248-3268 1 P70857WO1spectral density (PSD) profile) of the transformed matrices may be computed. For example, a normalized power profile may be computed according to the equation:P[i][j] = |H[i][j]|2 / (ΣiΣj|H[i][j]|2). In a fourth step, the PSE value may be computed. For example, the PSE value may be computed based on the normalized power profile using the equation PSE = ΣiΣjP[i][j]log2(P[i][j]).
[0047] FIG. 4 illustrates an example flow diagram 400 for dynamic CSI compression using a PSE value, according to embodiments herein.
[0048] The example flow diagram 400 for dynamic CSI compression using the PSE value begins with the base station 402 sending 406 a reference signal to the UE 404. Additionally, the base station 402 sends 408 an initial compression configuration to the UE 404 including compression parameters. For example, the compression configuration may include parameters such as a default compression ratio, one or more thresholds for corresponding PSE values (for the UE to adjust its compression factor based on), specific frequency bands or spatial dimensions to compress, and / or instructions for calculating the PSE value (e.g.. time and / or frequency resolution). In some other examples, the compression configuration may include PSE value thresholds that CSI compression may be performed based off of (e.g., a stronger compression is applied for a PSE value below S'E’Threshoid and a weaker compression is applied for a PSE value above / ’67 / ihreshoid) Subsequently, the UE 404 generates a CSI estimate 410 (e g., CSI samples in the spatial-frequency domain) based on the reference signal received from the base station 402.
[0049] Then, the UE 404 performs a PSE value computation 412 of the CSI estimate 410 (e.g., the CSI samples in the spatial-frequency domain). The computed PSE value (e.g., PSE[t] ) is used by the UE 404 as a metric to adjust 414 the compression process.
[0050] For example, if the PSE value has a low value / does not meet a threshold (corresponding to a case of relatively low channel entropy), the CSI samples may be understood as relatively smooth and / or sparse, suggesting relatively high correlation in the channel. As such, the UE 404 may adjust 414 its use of the encoder 416 used for CSI compression to apply a relatively stronger compression as fewer dominant features can represent the CSI effectively. If the PSE value has a relatively high value / meets a threshold (corresponding to a case of relatively high channel entropy), the CSI samples may be understood as relatively less smooth or less sparse, suggesting a relatively higher complexity. As such, the UE 404 may adjust 414 its use of the encoder 416 used for CSI94898-6248-3268 1 P70857WO1compression to apply a relatively milder compression to retain critical details and minimize reconstruction error. The adjustment of the encoder 416 may be understood as identifying a specific compression profile at the UE 404 based on the PSE value and the compression configuration and inputting the compression profile at the encoder 416.
[0051] Accordingly, the UE 404 provides the CSI estimate 410 to the encoder 416 of the AI / ML model for CSI compression that is sited at the UE 404. The encoder 416 may be adjusted according to a result of the PSE value computation (e.g., according to the identified compression profile based on the calculated PSE). The encoder 416 then uses the CSI estimate 410 to generate AI / ML compressed CSI feedback 420 (e.g., a bitstream). The UE 404 provides the AI / ML compressed CSI feedback 420 to the base station 402. Additionally, the UE 404 provides PSE data 418 (e.g., data corresponding to the compression profile used for the CSI compression) to the base station 402. The PSE data 418 may include, for example, the PSE value and / or other indicators derived from the PSE value, such as a compression factor and quantization levels. Note that the PSE data 418 may assist the base station 402 in recovering the CSI from the AI / ML compressed CSI feedback 420.
[0052] Accordingly, the base station 402 provides the AI / ML compressed CSI feedback 420 as received from the UE 404 to a decoder 422 of the AI / ML model for CSI decompression that is sited at the base station 402. In some cases, the base station 402 may identify a compression profile based on the PSE data 418. Accordingly, using the AI / ML compressed CSI feedback 420 and the identified compression profile, the decoder 422 generates recovered CSI feedback. Subsequently, the base station 402 uses the recovered CSI feedback for a computation of the PSE value 424. Note that the PSE value generated from the computation of the PSE value 424 at the base station 402 may be understood as a network-side PSE value, while the PSE data 418 corresponds to a UE-side PSE value that is computed at the UE 404.
[0053] In some cases, the base station 402 compares the network-side PSE value with the expected (e.g.. expected based on the UE-side PSE value) and / or historical PSE values for monitoring purposes. In some cases, this monitoring will result in an adaption of the active compression configuration by the base station 402. If the base station 402 detects discrepancies or environmental changes (e.g., mobility, interference) based on the PSE value generated from the computation of the PSE value 424 or recovered CSI quality, the base station 402 may (e.g., dynamically) generate 426 an updated104898-6248-3268 1 P70857WO1compression configuration that is more optimal for the environment that the UE 404 is in. In some other cases, the base station 402 may determine a second compression profile based on the PSE value generated from the computation of the PSE value 424 and the compression configuration.
[0054] Accordingly, the base station 402 transmits 428 the adjusted / updated compression configuration or indication of the second compression profile to the UE 404. This may include, for example, updated thresholds for PSE-based compression (e.g., for autonomous UE configuration change), and / or a request for new / updated compression ratios and / or number of quantization levels. In some instances, if the base station 402 detects discrepancies in the PSE value (e.g., consecutive PSE values or an abnormal PSE value), the base station 402 may signal the UE 404 to adjust the compression parameters dynamically in subsequent transmissions to optimize performance.
[0055] It should be understood that the process illustrated in flow diagram 400 repeats, enabling the system to adapt dynamically to changing channel conditions. For example, the UE 404 performs 430 CSI compression on subsequent CSI estimations from subsequent reference signals. The performed CSI compression is based on the adjusted / updated compression configuration or indicated compression profiles until the compression configuration or compression profile needs further adjusting and updating. The need for adjusting and updating of the compression configurating and / or the compression profile is indicated by detected discrepancies in the PSE value (e.g., consecutive PSE values or abnormal PSE value).
[0056] Embodiments herein using dynamic CSI compression / decompression using the PSE value include increased environment adaptivity as the system dynamically responds to changing channel conditions, ensuring efficient resource utilization. Additionally, dynamic CSI compression / decompression using the PSE value reduces overhead, as the dynamic CSI compression avoids unnecessary feedback in smooth and predictable scenarios, reducing signaling load. Further, dynamic CSI compression / decompression using the PSE value includes enhanced robustness as it maintains a high accuracy in challenging RF environments by adapting compression levels. In some examples, the compression levels may be understood as the compression profiles discussed herein.
[0057] An example of dynamic CSI compression based on a PSE value is now discussed.114898-6248-3268 1 P70857WO1
[0058] In some embodiments, a UE and the network may agree on initial compression parameters for a compression configuration initially sent from the network to the UE. The network may set thresholds for the PSE value to guide the compression levels. For example, a low PSE value threshold may be PSELow: 0.3 and a high PSE value threshold may be PSEHigh: 0.7. The network may signal a compression configuration including various levels of compression based on the PSE value thresholds such as Fl, F2, and / or F3.
[0059] The dynamic nature of an environment experienced by the UE may be assumed. For example, the UE may move from an open environment with a highly correlated channel to an urban environment with multipath effects in the channel.
[0060] At a first time, (e.g., time to) assume that a UE is in a non-complex (e.g., open) environment and that the channel accordingly exhibits smooth PSE characteristics (corresponding to a low PSE value). For example, the PSE value of the channel may be calculated at 0.25 (e.g., PSE(to) =. 025). This PSE value is below the threshold PSELow. This high correlation in the CSI samples suggest that fewer coefficients are needed to represent the channel. Accordingly, the UE compresses the CSI heavily, reducing the feedback data size (e.g., using compression profile Fl in the compression configuration). Then, the UE transmits the highly compressed CSI to the network as well as data corresponding to the compression profile Fl. The network identifies a compression profile based on the data corresponding to the compression profile and recovers the CSI based on the identified compression profile. Further, the network confirms the quality of the recovered CSI (e.g.. through PSE values calculated at the network).
[0061] At a second time, (e.g., time ti) assume that the UE is transitioning between environments and that the channel accordingly exhibits some, but not an overly large amount of, randomness / complexity (corresponding to a medium PSE value). For example, the PSE value of the channel may be calculated at 0.5 (e.g., PSE(ti) = 0.5). This PSE value is between the threshold PSELOW and the threshold PSEHigh. This suggests a moderate correlation in CSI samples of the channel. Accordingly, the UE applies an intermediate level CSI compression, balancing overhead and accuracy (e.g., using compression profile F2 in the compression configuration). Then, the UE transmits the moderately compressed CSI with data corresponding to the compression profile (e.g., indicating the PSE value). The network may identify a compression profile based on the124898-6248-3268 1 P70857WO1data corresponding to the compression profile and may adjust CSI recovering parameters based on the identified compression profile.
[0062] At a third time (e.g., time t2), assume that the UE is in a complex (e.g., very urban) environment and thus that the channel is complex (corresponding to a high PSE value). For example, the PSE value of the channel may be.85 (e.g., PSE(t2) =.85). This PSE value is above the threshold PSEHigh. This suggests low correlation in CSI samples due to multipath effects. Accordingly, the UE reduces the level CSI compression used still further in order to retain detailed channel information (e.g., using compression profile F3 in the compression configuration). The UE transmits this lightly compressed CSI with data corresponding to the compression profile to the network. Then, the network uses the data corresponding to the compression profile to identify a compression profile at the network. Accordingly, a recovered CSI is generated at a decoder based on the identified compression profile. Note that the identified compression profile may ensure accurate recovering of the CSI.
[0063] FIG. 5 illustrates a method 500 of a UE, according to embodiments herein. The illustrated method 500 includes receiving 502, from a base station, a first CSI compression configuration and a first reference signal. The method 500 further includes generating 504 first CSI feedback based on the first reference signal received from the base station. The method 500 further includes generating 506 a first PSE value corresponding to a distribution of power of the first reference signal across a frequency domain and a spatial domain. The method 500 further includes determining 508, using the CSI compression configuration, based on the first PSE value, a first compression profile for the first CSI feedback. The method 500 further includes applying 510 the first CSI feedback and the first compression profile at a first encoder of a first AI / ML model that is at the UE to generate first compressed CSI feedback, wherein the first encoder generates the first compressed CSI feedback according to the first compression profile for the first CSI feedback. The method 500 further includes sending 512, to the base station, the first compressed CSI feedback and first data corresponding to the compression profile.
[0064] In some embodiments of the method 500, the first CSI compression configuration comprises one or more of a compression ratio, one or more PSE value thresholds, an indication of the frequency domain, an indication of the spatial domain, and instructions for generating the first PSE value.134898-6248-3268 1 P70857WO1
[0065] In some embodiments of the method 500, the first CSI compression configuration includes a PSE value threshold that specifies use of a plurality of defined compression profiles, and wherein the UE determines the first compression profile for the first CSI feedback by comparing the first PSE value to the PSE value threshold to identify a corresponding one of the plurality of defined compression profiles as the first compression profile.
[0066] In some embodiments of the method 500, when the first PSE value does not meet a PSE value threshold, the UE identifies a relatively stronger compression profile of a plurality of defined profiles as the first compression profile, and when the first PSE value meets the PSE value threshold, the UE identifies a relatively weaker compression profile of the plurality of defined profiles as the first compression profile.
[0067] In some embodiments of the method 500, the first data corresponding to the first compression profile comprises one or more of a PSE value, a compression level, and a quantization level.
[0068] In some embodiments, the method 500 further comprises determining, using the first CSI compression configuration, based on a second PSE value for a second reference signal received from the base station, a second compression profile for second CSI feedback for the second reference signal, applying the second CSI feedback and the second PSE value at the first encoder of the first AI / ML model that is at the UE to generate second compressed CSI feedback, wherein the first encoder generates the second compressed CSI feedback according to the second compression profile for the second CSI feedback, and sending, to the base station, the second compressed CSI feedback and second data corresponding to the second compression profile.
[0069] In some embodiments, the method 500 further comprises receiving a second CSI compression configuration, determining, using the second CSI compression configuration, based on a second PSE value for a second reference signal that is received from the base station, a second compression profile for the second CSI feedback for the second reference signal, applying, using the second CSI compression configuration, the second CSI feedback and the second PSE value at the first encoder of the first AI / ML model that is at the UE to generate second compressed CSI feedback, wherein the first encoder generates the second compressed CSI feedback according to the second compression profile for the second CSI feedback, and sending, to the base station, the144898-6248-3268 1 P70857WO1second compressed CSI feedback and second data corresponding to the second compression profile.
[0070] In some embodiments of the method 500, generating the first PSE value comprises generating frequency response CSI using the first reference signal, generating a transformed matrix based on the frequency response CSI across an angular domain and a temporal delay domain, computing a normalized power profile based on the transformed matrix, and computing the first PSE value based on the normalized power profile.
[0071] FIG. 6 illustrates a method 600 of a base station, according to embodiments herein. The illustrated method 600 includes sending 602, to a UE, a first reference signal and a first CSI compression configuration. The method 600 further includes receiving 604, from the UE, compressed CSI feedback and data corresponding to a first compression profile used by the UE to generate the compressed CSI feedback. The method 600 further includes identifying 606 the first compression profile by applying the data corresponding to the compression profile with the first CSI compression configuration. The method 600 further includes applying 608 the compressed CSI feedback and the first compression profile at a first decoder of a first AI / ML model that is at the base station to generate recovered CSI feedback, wherein the decoder generates the recovered CSI feedback according to the first compression profile.
[0072] In some embodiments, the method 600 further comprises generating a PSE value corresponding to a distribution of power of the recovered CSI feedback across a frequency domain and a spatial domain, identifying based on the PSE value, an adjustment for the first compression profile, adjusting the first compression profile according to the adjustment, and sending, to the UE, and indication of the adjustment to the first compression profile. In some such embodiments, generating the PSE value comprises generating frequency response CSI using the recovered CSI feedback, generating a transformed matrix based on the frequency response CSI across an angular domain and a temporal delay domain, computing a normalized power profile based on the transformed matrix, and computing the PSE value based on the normalized power profile.
[0073] In some embodiments, the method 600 further comprises generating, at the base station, a PSE value based on the recovered CSI feedback, generating a second CSI compression configuration based on the PSE value, and sending, to the UE, the second154898-6248-3268 1 P70857WO1CSI compression configuration. Some such embodiments further comprise detecting a channel anomaly in the PSE value, and wherein generating the second CSI compression configuration is further based on the channel anomaly. In some other such embodiments, generating the PSE value comprises generating frequency response CSI using the recovered CSI feedback, generating a transformed matrix based on the frequency¬ response CSI across an angular domain and a temporal delay domain, computing a normalized power profile based on the transformed matrix, and computing the PSE value based on the normalized power profile.
[0074] In some embodiments of the method 600, the first CSI compression configuration comprises one or more of a compression ratio, one or more PSE value thresholds, an indication of a frequency domain, an indication of a spatial domain, and instructions for generating a PSE value.
[0075] In some embodiments of the method 600, when a first PSE value does not meet a PSE value threshold, the base station identifies a relatively stronger compression profile of a plurality of defined profiles as the first compression profile, and when the first PSE value meets the PSE value threshold, the base station identifies a relatively weaker compression profile of the plurality of defined profiles as the first compression profile.
[0076] FIG. 7 illustrates an example architecture of a wireless communication system 700, according to embodiments disclosed herein. The following description is provided for an example wireless communication system 700 that operates in conjunction with the LTE system standards and / or 5G or NR system standards as provided by 3GPP technical specifications.
[0077] As shown by FIG. 7, the wireless communication system 700 includes UE 702 and UE 704 (although any number of UEs may be used). In this example, the UE 702 and the UE 704 are illustrated as smartphones (e.g., handheld touchscreen mobile computing devices connectable to one or more cellular networks), but may also comprise any mobile or non-mobile computing device configured for wireless communication.
[0078] The UE 702 and UE 704 may be configured to communicatively couple with a RAN 706. In embodiments, the RAN 706 may be NG-RAN, E-UTRAN, etc. The UE 702 and UE 704 utilize connections (or channels) (shown as connection 708 and connection 710, respectively) with the RAN 706, each of which comprises a physical communications interface. The RAN 706 can include one or more base stations (such as164898-6248-3268 1 P70857WO1base station 712 and base station 714) that enable the connection 708 and connection 710.
[0079] In this example, the connection 708 and connection 710 are air interfaces to enable such communicative coupling, and may be consistent with RAT(s) used by the RAN 706, such as, for example, an LTE and / or NR.
[0080] In some embodiments, the UE 702 and UE 704 may also directly exchange communication data via a sidelink interface 716. The UE 704 is shown to be configured to access an access point (shown as AP 718) via connection 720. By way of example, the connection 720 can comprise a local wireless connection, such as a connection consistent with any IEEE 802.11 protocol, wherein the AP 718 may comprise a Wi-Fi® router. In this example, the AP 718 may be connected to another network (for example, the Internet) without going through a CN 724.
[0081] In embodiments, the UE 702 and UE 704 can be configured to communicate using orthogonal frequency division multiplexing (OFDM) communication signals with each other or with the base station 712 and / or the base station 714 over a multicarrier communication channel in accordance with various communication techniques, such as. but not limited to, an orthogonal frequency division multiple access (OFDMA) communication technique (e.g., for downlink communications) or a single carrier frequency division multiple access (SC-FDMA) communication technique (e g., for uplink and ProSe or sidelink communications), although the scope of the embodiments is not limited in this respect. The OFDM signals can comprise a plurality of orthogonal subcarriers.
[0082] In some embodiments, all or parts of the base station 712 or base station 714 may be implemented as one or more software entities running on server computers as part of a virtual network. In addition, or in other embodiments, the base station 712 or base station 714 may be configured to communicate with one another via interface 722. In embodiments where the wireless communication system 700 is an LTE system (e.g., when the CN 724 is an EPC), the interface 722 may be an X2 interface. The X2 interface may be defined between two or more base stations (e.g., two or more eNBs and the like) that connect to an EPC, and / or between two eNBs connecting to the EPC. In embodiments where the wireless communication system 700 is an NR system (e.g., when CN 724 is a 5GC), the interface 722 may be an Xn interface. The Xn interface is defined between two or more base stations (e g., two or more gNBs and the like) that connect to174898-6248-3268 1 P70857WO15GC, between a base station 712 (e.g., a gNB) connecting to 5GC and an eNB, and / or between two eNBs connecting to 5GC (e.g.. CN 724).
[0083] The RAN 706 is shown to be communicatively coupled to the CN 724. The CN 724 may comprise one or more network elements 726, which are configured to offer various data and telecommunications services to customers / subscribers (e.g., users of UE 702 and UE 704) who are connected to the CN 724 via the RAN 706. The components of the CN 724 may be implemented in one physical device or separate physical devices including components to read and execute instructions from a machine-readable or computer-readable medium (e.g., a non-transitory machine-readable storage medium).
[0084] In embodiments, the CN 724 may be an EPC, and the RAN 706 may be connected with the CN 724 via an SI interface 728. In embodiments, the SI interface 728 may be split into two parts, an SI user plane (Sl-U) interface, which carries traffic data between the base station 712 or base station 714 and a serving gateway (S-GW), and the SI -MME interface, which is a signaling interface between the base station 712 or base station 714 and mobility management entities (MMEs).
[0085] In embodiments, the CN 724 may be a 5GC. and the RAN 706 may be connected with the CN 724 via an NG interface 728. In embodiments, the NG interface 728 may be split into two parts, an NG user plane (NG-U) interface, which carries traffic data between the base station 712 or base station 714 and a user plane function (UPF), and the SI control plane (NG-C) interface, which is a signaling interface between the base station 712 or base station 714 and access and mobility management functions (AMFs).
[0086] Generally, an application server 730 may be an element offering applications that use internet protocol (IP) bearer resources with the CN 724 (e.g., packet switched data services). The application server 730 can also be configured to support one or more communication services (e.g., VoIP sessions, group communication sessions, etc.) for the UE 702 and UE 704 via the CN 724. The application server 730 may communicate with the CN 724 through an IP communications interface 732.
[0087] FIG. 8 illustrates a system 800 for performing signaling 834 between a wireless device 802 and a network device 818, according to embodiments disclosed herein. The system 800 may be a portion of a wireless communications system as herein described. The wireless device 802 may be, for example, a UE of a wireless communication system.184898-6248-3268 1 P70857WO1The network device 818 may be, for example, a base station (e.g., an eNB or a gNB) of a wireless communication system.
[0088] The wireless device 802 may include one or more processor(s) 804. The processor(s) 804 may execute instructions such that various operations of the wireless device 802 are performed, as described herein. The processor(s) 804 may include one or more baseband processors implemented using, for example, a central processing unit (CPU), a digital signal processor (DSP), an application specific integrated circuit (ASIC), a controller, a field programmable gate array (FPGA) device, another hardware device, a firmware device, or any combination thereof configured to perform the operations described herein.
[0089] The wireless device 802 may include a memory 806. The memory 806 may be a non-transitory computer-readable storage medium that stores instructions 808 (which may include, for example, the instructions being executed by the processor(s) 804). The instructions 808 may also be referred to as program code or a computer program. The memory 806 may also store data used by, and results computed by, the processor(s) 804.
[0090] The wireless device 802 may include one or more transceiver(s) 810 that may include radio frequency (RF) transmitter circuitry and / or receiver circuitry that use the antenna(s) 812 of the wireless device 802 to facilitate signaling (e.g., the signaling 834) to and / or from the wireless device 802 with other devices (e.g., the network device 818) according to corresponding RATs.
[0091] The wireless device 802 may include one or more antenna(s) 812 (e.g., one, two, four, or more). For embodiments with multiple antenna(s) 812, the wireless device 802 may leverage the spatial diversity of such multiple antenna(s) 812 to send and / or receive multiple different data streams on the same time and frequency resources. This behavior may be referred to as, for example, multiple input multiple output (MIMO) behavior (referring to the multiple antennas used at each of a transmitting device and a receiving device that enable this aspect). MIMO transmissions by the wireless device 802 may be accomplished according to precoding (or digital beamforming) that is applied at the wireless device 802 that multiplexes the data streams across the antenna(s) 812 according to known or assumed channel characteristics such that each data stream is received with an appropriate signal strength relative to other streams and at a desired location in the spatial domain (e.g., the location of a receiver associated with that data stream). Certain embodiments may use single user MIMO (SU-MIMO) methods (where194898-6248-3268 1 P70857WO1the data streams are all directed to a single receiver) and / or multi user MIMO (MU-MIMO) methods (where individual data streams may be directed to individual (different) receivers in different locations in the spatial domain).
[0092] In certain embodiments having multiple antennas, the wireless device 802 may implement analog beamforming techniques, whereby phases of the signals sent by the antenna(s) 812 are relatively adjusted such that the (joint) transmission of the antenna(s) 812 can be directed (this is sometimes referred to as beam steering).
[0093] The wireless device 802 may include one or more interface(s) 814. The interface(s) 814 may be used to provide input to or output from the wireless device 802. For example, a wireless device 802 that is a UE may include interface(s) 814 such as microphones, speakers, a touchscreen, buttons, and the like in order to allow for input and / or output to the UE by a user of the UE. Other interfaces of such a UE may be made up of transmitters, receivers, and other circuitry (e.g., other than the transceiver(s) 810 / antenna(s) 812 already described) that allow for communication between the UE and other devices and may operate according to known protocols (e.g., Wi-Fi®, Bluetooth®, and the like).
[0094] The wireless device 802 may include a PSE value module 816. The PSE value module 816 may be implemented via hardware, software, or combinations thereof. For example, the PSE value module 816 may be implemented as a processor, circuit, and / or instructions 808 stored in the memory 806 and executed by the processor(s) 804. In some examples, the PSE value module 816 may be integrated within the processor(s) 804 and / or the trans ceiver(s) 810. For example, the PSE value module 816 may be implemented by a combination of software components (e.g., executed by a DSP or a general processor) and hardware components (e.g., logic gates and circuitry) within the processor(s) 804 or the transceiver(s) 810.
[0095] The PSE value module 816 may be used for various aspects of the present disclosure, for example, aspects of FIG. 4 and FIG. 5. For example, the PSE value module 816 may configure the wireless device 802 to receive, from a network device 818, a first CSI compression configuration and a first reference signal; generate first CSI feedback based on the first reference signal received from the network device 818; generate a first PSE value corresponding to a distribution of power used by a first reference signal across a frequency domain and a spatial domain; determine, using the CSI compression configuration, based on the first PSE value, a first compression profile204898-6248-3268 1 P70857WO1for the first CSI feedback; apply the first CSI feedback and the first compression profile at a first encoder of a first AI / ML model that is at the wireless device 802 to generate first compressed CSI feedback, wherein the first encoder generates the first compressed CSI feedback according to the first compression profile for the first CSI feedback; and send, to the network device 818, the first compressed CSI feedback and data corresponding to the compression profile.
[0096] The network device 818 may include one or more processor(s) 820. The processor(s) 820 may execute instructions such that various operations of the network device 818 are performed, as described herein. The processor(s) 820 may include one or more baseband processors implemented using, for example, a CPU, a DSP, an ASIC, a controller, an FPGA device, another hardware device, a firmware device, or any combination thereof configured to perform the operations described herein.
[0097] The network device 818 may include a memory 822. The memory 822 may be a non-transitory computer-readable storage medium that stores instructions 824 (which may include, for example, the instructions being executed by the processor(s) 820). The instructions 824 may also be referred to as program code or a computer program. The memory 822 may also store data used by, and results computed by, the processor(s) 820.
[0098] The network device 818 may include one or more transceiver(s) 826 that may include RF transmitter circuitry' and / or receiver circuitry that use the antenna(s) 828 of the network device 818 to facilitate signaling (e.g., the signaling 834) to and / or from the network device 818 with other devices (e.g., the wireless device 802) according to corresponding RATs.
[0099] The network device 818 may include one or more antenna(s) 828 (e.g., one. two, four, or more). In embodiments having multiple antenna(s) 828, the network device 818 may perform MIMO, digital beamforming, analog beamforming, beam steering, etc., as has been described.
[0100] The network device 818 may include one or more interface(s) 830. The interface(s) 830 may be used to provide input to or output from the network device 818. For example, a network device 818 that is a base station may include interface(s) 830 made up of transmitters, receivers, and other circuitry (e.g., other than the transceiver(s) 826 / antenna(s) 828 already described) that enables the base station to communicate with other equipment in a core network, and / or that enables the base station to communicate with external networks, computers, databases, and the like for purposes of operations,214898-6248-3268 1 P70857WO1administration, and maintenance of the base station or other equipment operably connected thereto.
[0101] The network device 818 may include a PSE value module 832. The PSE value module 832 may be implemented via hardware, software, or combinations thereof. For example, the PSE value module 832 may be implemented as a processor, circuit, and / or instructions 824 stored in the memory 822 and executed by the processor(s) 820. In some examples, the PSE value module 832 may be integrated within the processor(s) 820 and / or the transceiver(s) 826. For example, the PSE value module 832 may be implemented by a combination of software components (e.g., executed by a DSP or a general processor) and hardware components (e.g.. logic gates and circuitry) within the processor(s) 820 or the transceiver(s) 826.
[0102] The PSE value module 832 may be used for various aspects of the present disclosure, for example, aspects of FIG. 4 and FIG. 6. For example, the PSE value module 832 may configure the network device 818 to sending, to a wireless device 802, a first reference signal and a first CSI compression configuration; receive, from the wireless device 802, compressed CSI feedback and data corresponding to a first compression profile used by the wireless device 802 to generate the compressed CSI feedback; identify the first compression profile by applying the data corresponding to the compression profile with the CSI configuration; and apply the compressed CSI feedback and the first compression profile at a first decoder of a first AI / ML model that is at the network device 818 to generate recovered CSI feedback, wherein the decoder generates the recovered CSI feedback according to the first compression profile.
[0103] Embodiments contemplated herein include an apparatus comprising means to perform one or more elements of the method 500. This apparatus may be. for example, an apparatus of a UE (such as a wireless device 802 that is a UE, as described herein).
[0104] Embodiments contemplated herein include one or more non -transitory computer-readable media comprising instructions to cause an electronic device, upon execution of the instructions by one or more processors of the electronic device, to perform one or more elements of the method 500. This non-transitory computer-readable media may be, for example, a memory' of a UE (such as a memory' 806 of a wireless device 802 that is a UE, as described herein).
[0105] Embodiments contemplated herein include an apparatus comprising logic, modules, or circuitry' to perform one or more elements of the method 500. This apparatus224898-6248-3268 1 P70857WO1may be, for example, an apparatus of a UE (such as a wireless device 802 that is a UE, as described herein).
[0106] Embodiments contemplated herein include an apparatus comprising: one or more processors and one or more computer-readable media comprising instructions that, when executed by the one or more processors, cause the one or more processors to perform one or more elements of the method 500. This apparatus may be, for example, an apparatus of a UE (such as a wireless device 802 that is a UE, as described herein).
[0107] Embodiments contemplated herein include a signal as described in or related to one or more elements of the method 500.
[0108] Embodiments contemplated herein include a computer program or computer program product comprising instructions, wherein execution of the program by a processor is to cause the processor to carry out one or more elements of the method 500. The processor may be a processor of a UE (such as a processor(s) 804 of a wireless device 802 that is a UE, as described herein). These instructions may be, for example, located in the processor and / or on a memory’ of the UE (such as a memory 806 of a wireless device 802 that is a UE. as described herein).
[0109] Embodiments contemplated herein include an apparatus comprising means to perform one or more elements of the method 600. This apparatus may be. for example, an apparatus of a base station (such as a network device 818 that is a base station, as described herein).
[0110] Embodiments contemplated herein include one or more non-transitory computer-readable media comprising instructions to cause an electronic device, upon execution of the instructions by one or more processors of the electronic device, to perform one or more elements of the method 600. This non-transitor ’ computer-readable media may be. for example, a memory of a base station (such as a memory 822 of a network device 818 that is a base station, as described herein).
[0111] Embodiments contemplated herein include an apparatus comprising logic, modules, or circuitry to perform one or more elements of the method 600. This apparatus may be, for example, an apparatus of a base station (such as a network device 818 that is a base station, as described herein).
[0112] Embodiments contemplated herein include an apparatus comprising: one or more processors and one or more computer-readable media comprising instructions that, when executed by the one or more processors, cause the one or more processors to 234898-6248-3268 1 P70857WO1perform one or more elements of the method 600. This apparatus may be, for example, an apparatus of a base station (such as a network device 818 that is a base station, as described herein).
[0113] Embodiments contemplated herein include a signal as described in or related to one or more elements of the method 600.
[0114] Embodiments contemplated herein include a computer program or computer program product comprising instructions, wherein execution of the program by a processing element is to cause the processing element to carry out one or more elements of the method 600. The processor may be a processor of a base station (such as a processor(s) 820 of a network device 818 that is a base station, as described herein). These instructions may be, for example, located in the processor and / or on a memory' of the base station (such as a memory 822 of a network device 818 that is a base station, as described herein).
[0115] For one or more embodiments, at least one of the components set forth in one or more of the preceding figures may be configured to perform one or more operations, techniques, processes, and / or methods as set forth herein. For example, a baseband processor as described herein in connection with one or more of the preceding figures may be configured to operate in accordance with one or more of the examples set forth herein. For another example, circuitry associated with a UE, base station, network element, etc. as described above in connection with one or more of the preceding figures may be configured to operate in accordance with one or more of the examples set forth herein.
[0116] Any of the above described embodiments may be combined with any other embodiment (or combination of embodiments), unless explicitly stated otherwise. The foregoing description of one or more implementations provides illustration and description, but is not intended to be exhaustive or to limit the scope of embodiments to the precise form disclosed. Modifications and variations are possible in light of the above teachings or may be acquired from practice of various embodiments.
[0117] Embodiments and implementations of the sy stems and methods described herein may include various operations, which may be embodied in machine-executable instructions to be executed by a computer system. A computer system may include one or more general-purpose or special-purpose computers (or other electronic devices). The computer system may include hardware components that include specific logic for244898-6248-3268 1 P70857WO1performing the operations or may include a combination of hardware, software, and / or firmware.
[0118] It should be recognized that the systems described herein include descriptions of specific embodiments. These embodiments can be combined into single systems, partially combined into other systems, split into multiple systems or divided or combined in other ways. In addition, it is contemplated that parameters, attributes, aspects, etc. of one embodiment can be used in another embodiment. The parameters, attributes, aspects, etc. are merely described in one or more embodiments for clarity, and it is recognized that the parameters, attributes, aspects, etc. can be combined with or substituted for parameters, attributes, aspects, etc. of another embodiment unless specifically disclaimed herein.
[0119] It is well understood that the use of personally identifiable information should follow privacy policies and practices that are generally recognized as meeting or exceeding industry or governmental requirements for maintaining the privacy of users. In particular, personally identifiable information data should be managed and handled so as to minimize risks of unintentional or unauthorized access or use, and the nature of authorized use should be clearly indicated to users.
[0120] Although the foregoing has been described in some detail for purposes of clarity, it will be apparent that certain changes and modifications may be made without departing from the principles thereof. It should be noted that there are many alternative ways of implementing both the processes and apparatuses described herein. Accordingly, the present embodiments are to be considered illustrative and not restrictive, and the description is not to be limited to the details given herein, but may be modified within the scope and equivalents of the appended claims.254898-6248-3268 1 P70857WO1
Claims
CLAIMS1. A method of a user equipment (UE), comprising:receiving, from a base station, a first channel state information (CSI) compression configuration and a first reference signal;generating first CSI feedback based on the first reference signal received from the base station;generating a first power spectral entropy (PSE) value corresponding to a distribution of power of the first reference signal across a frequency domain and a spatial domain;determining, using the first CSI compression configuration, based on the first PSE value, a first compression profile for the first CSI feedback;applying the first CSI feedback and the first compression profile at a first encoder of a first artificial intelligence (AI) / machine learning (ML) model that is at the UE to generate first compressed CSI feedback, wherein the first encoder generates the first compressed CSI feedback according to the first compression profile for the first CSI feedback; andsending, to the base station, the first compressed CSI feedback and first data corresponding to the first compression profile.
2. The method of claim 1, wherein the first CSI compression configuration comprises one or more of a compression ratio, one or more PSE value thresholds, an indication of the frequency domain, an indication of the spatial domain, and instructions for generating the first PSE value.
3. The method of claim 1, wherein the first CSI compression configuration includes a PSE value threshold that specifies use of a plurality of defined compression profiles, and wherein the UE determines the first compression profile for the first CSI feedback by comparing the first PSE value to the PSE value threshold to identify a corresponding one of the plurality' of defined compression profiles as the first compression profile.
4. The method of claim 1, wherein:when the first PSE value does not meet a PSE value threshold, the UE identifies a relatively stronger compression profile of a plurality of defined profiles as the first compression profile; and264898-6248-3268 1 P70857WO1when the first PSE value meets the PSE value threshold, the UE identifies a relatively weaker compression profile of the plurality of defined profiles as the first compression profile.
5. The method of claim 1, wherein the first data corresponding to the first compression profile comprises one or more of a PSE value, a compression level, and a quantization level.
6. The method of claim 1, further comprising:determining, using the first CSI compression configuration, based on a second PSE value for a second reference signal received from the base station, a second compression profile for second CSI feedback for the second reference signal;applying the second CSI feedback and the second PSE value at the first encoder of the first AI / ML model that is at the UE to generate second compressed CSI feedback, wherein the first encoder generates the second compressed CSI feedback according to the second compression profile for the second CSI feedback; andsending, to the base station, the second compressed CSI feedback and second data corresponding to the second compression profile.
7. The method of claim 1, further comprising:receiving a second CSI compression configuration;determining, using the second CSI compression configuration, based on a second PSE value for a second reference signal that is received from the base station, a second compression profile for a second CSI feedback for the second reference signal;applying, using the second CSI compression configuration, the second CSI feedback and the second PSE value at the first encoder of the first AI / ML model that is at the UE to generate second compressed CSI feedback, wherein the first encoder generates the second compressed CSI feedback according to the second compression profile for the second CSI feedback; andsending, to the base station, the second compressed CSI feedback and second data corresponding to the second compression profile.
8. The method of claim 1, wherein generating the first PSE value comprises:generating frequency response CSI using the first reference signal;274898-6248-3268 1 P70857WO1generating a transformed matrix based on the frequency response CSI across an angular domain and a temporal delay domain;computing a normalized power profile based on the transformed matrix; and computing the first PSE value based on the normalized power profile.
9. A method of a base station, comprising:sending, to a user equipment (UE), a first reference signal and a first channel state information (CSI) compression configuration;receiving, from the UE, compressed CSI feedback and data corresponding to a first compression profile used by the UE to generate the compressed CSI feedback; identifying the first compression profile by applying the data corresponding to the first compression profile with the first CSI compression configuration; andapplying the compressed CSI feedback and the first compression profile at a first decoder of a first artificial intelligence (AI) / machine learning (ML) model that is at the base station to generate recovered CSI feedback, wherein the decoder generates the recovered CSI feedback according to the first compression profile.
10. The method of claim 9, further comprising:generating a power spectral entropy (PSE) value corresponding to a distribution of power of the recovered CSI feedback across a frequency domain and a spatial domain;identifying based on the PSE value, an adjustment for the first compression profile;adjusting the first compression profile according to the adjustment; and sending, to the UE, and indication of the adjustment to the first compression profile.
11. The method of claim 10, wherein generating the PSE value comprises:generating frequency response CSI using the recovered CSI feedback; generating a transformed matrix based on the frequency response CSI across an angular domain and a temporal delay domain;computing a normalized power profile based on the transformed matrix; and computing the PSE value based on the normalized power profile.284898-6248-3268 1 P70857WO112. The method of claim 9, further comprising:generating, at the base station, a power spectral entropy (PSE) value based on the recovered CSI feedback;generating a second CSI compression configuration based on the PSE value; and sending, to the UE, the second CSI compression configuration.
13. The method of claim 12, further comprising detecting a channel anomaly in the PSE value, and wherein generating the second CSI compression configuration is further based on the channel anomaly.
14. The method of claim 12, wherein generating the PSE value comprises:generating frequency response CSI using the recovered CSI feedback; generating a transformed matrix based on the frequency response CSI across an angular domain and a temporal delay domain;computing a normalized power profile based on the transformed matrix; and computing the PSE value based on the normalized power profile.
15. The method of claim 9, wherein the first CSI compression configuration comprises one or more of a compression ratio, one or more power spectral entropy (PSE) value thresholds, an indication of a frequency domain, an indication of a spatial domain, and instructions for generating a PSE value.
16. The method of claim 9. wherein:when a first power spectral entropy (PSE) value does not meet a PSE value threshold, the base station identifies a relatively stronger compression profile of a plurality of defined profiles as the first compression profile; andwhen the first PSE value meets the PSE value threshold, the base station identifies a relatively weaker compression profile of the plurality of defined profiles as the first compression profile.
17. An apparatus comprising means to perform the method of any of claim 1 to claim 16.
18. A computer-readable media comprising instructions to cause an electronic device, upon execution of the instructions by one or more processors of the electronic device, to perform the method of any of claim 1 to claim 16.294898-6248-3268 1 P70857WO119. An apparatus comprising logic, modules, or circuitry to perform the method of any of claim 1 to claim 16.
20. A baseband processor for a user equipment (UE) that is configured to cause the UE to perform one or more elements of any one of claim 1 to claim 9.
21. A baseband processor for a base station that is configured to cause the base station to perform one or more elements of any one of claim 9 to claim 16.304898-6248-3268 1 P70857WO1