Data input distribution metric for event monitoring and detection in channel state information compression artificial intelligence / machine learning models
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-02-06
- Publication Date
- 2026-08-13
Smart Images

Figure CN2025075916_13082026_PF_FP_ABST
Abstract
Description
DATA INPUT DISTRIBUTION METRIC FOR EVENT MONITORING AND DETECTION IN CHANNEL STATE INFORMATION COMPRESSION ARTIFICIAL INTELLIGENCE / MACHINE LEARNING MODELSTECHNICAL 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 ) .
[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 3GPP 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, 5G NR 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.
[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 a flow diagram for communications between a base station and a UE corresponding to the use of network-side SGCS-based monitoring of an AI / ML model for CSI compression and decompression.
[0011] FIG. 3 illustrates a flow diagram for communications between a base station and a UE corresponding to the use of UE-side SGCS-based monitoring of an AI / ML model for CSI compression and decompression.
[0012] FIG. 4 illustrates an example of performing 2D DFT to generate a power profile based on a MIMO channel, according to embodiments herein.
[0013] FIG. 5 illustrates a flow diagram for communications between a base station and a UE corresponding to PSE based AI / ML model monitoring event detection for CSI feedback, according to embodiments herein.
[0014] FIG. 6 illustrates a method of a UE, according to embodiments herein.
[0015] FIG. 7 illustrates a method of a base station, according to embodiments herein.
[0016] FIG. 8 illustrates a method of a base station, according to embodiments herein.
[0017] FIG. 9 illustrates a method of a UE, according to embodiments herein.
[0018] FIG. 10 illustrates an example architecture of a wireless communication system, according to embodiments disclosed herein.
[0019] FIG. 11 illustrates a system for performing signaling between a wireless device and a network device, according to embodiments disclosed herein.DETAILED DESCRIPTION
[0020] 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.
[0021] 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.
[0022] 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.
[0023] Accordingly, in various wireless communication systems, artificial intelligence (AI) / machine 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.
[0024] FIG. 1 illustrates a diagram 100 showing an example of a two-sided artificial intelligence / machine learning model (AI / ML) model 102 for CSI compression and decompression, according to embodiments discussed herein. The AI / ML model 102 includes the (logical) UE side 104 (aportion of the AI / ML model 102 that exists at a UE 106) and the (logical) network side 108 (aportion of the AI / ML model 102 that exists at, for example, a base station of a network 110) , as illustrated.
[0025] 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) .
[0026] The bitstream 118 is then transmitted from the UE 106 to the network 110.
[0027] 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.
[0028] 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.
[0029] 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.
[0030] The output 120 may correspondingly be referred to variously herein as “decoded, ” “decompressed, ” “recovered, ” etc.
[0031] 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.
[0032] 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.
[0033] 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.
[0034] 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.
[0035] 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.
[0036] 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.
[0037] 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.
[0038] FIG. 2 illustrates a flow diagram 200 for communications between a base station 202 and a UE 204 corresponding to the use of network-side SGCS-based monitoring of an AI / ML model for CSI compression and decompression. Preliminarily, the base station 202 sends 206 the UE 204 a reference signal. The UE 204 generates ground-truth CSI 208 based on its measurement of this reference signal.
[0039] The UE 204 then provides the ground-truth CSI 208 to an encoder 210 of the AI / ML model for CSI compression that is sited at the UE 204. The encoder 210 uses the ground-truth CSI 208 to generate AI / ML compressed CSI feedback 212 (e.g., a bitstream) .
[0040] The UE 204 then sends 214 the ground-truth CSI 208 and the AI / ML compressed CSI feedback 212 to the base station 202, as illustrated.
[0041] In some examples, an eT2 codebook or an eT2-like high resolution codebook (which may be even more accurate than an eT2 codebook) is used to report the ground-truth CSI 208 to the base station 202. With respect to a reporting mode used, in some cases one or both of per sample reporting and / or reporting of a number of monitored samples may be used. Note that a determination of a type of KPI to calculate (e.g., SGCS or normalized mean square error (NMSE) ) using ground-truth CSI 208 may turn at least in part on the reporting mode (s) so used. (Note that FIG. 2 assumes the case of SGCS use, as will be shown) . Note that, due to the nature of the ground-truth CSI 208 as measuring the reference signal as impacted by the channel between the base station 202 and the UE 204, the ground-truth CSI 208 is highly reliable in view of any presently applicable environmental factors.
[0042] The base station 202 provides the AI / ML compressed CSI feedback 212 as received from the UE 204 to a decoder 216 of the AI / ML model for CSI compression that is sited at the base station 202. Using the AI / ML compressed CSI feedback 212, the decoder 216 generates recovered CSI 218.
[0043] The base station 202 then calculates a KPI using both the received ground-truth CSI 208 (which is understood in context as a “target” CSI that represents the actual channel estimation performed by the UE 204) and the AI / ML compressed CSI feedback 212 (which is the result of encoding / compression and then decoding / decompression of the ground-truth CSI 208) . Based on the result of the KPI calculation, the base station 202 can evaluate the accuracy of the AI / ML model that uses the encoder 210 and the decoder 216 for CSI compression and decompression.
[0044] In the case of FIG. 2, this KPI calculation takes the form of an SGCS calculation 220 that results in an indication of the amount of similarity between the recovered CSI 218 and the ground-truth CSI 208. Based on the amount of similarity indicated by the result of the SGCS calculation 220, the base station 202 can evaluate the accuracy of the AI / ML model that uses the encoder 210 and the decoder 216 for CSI compression and decompression.
[0045] FIG. 3 illustrates a flow diagram 300 for communications between a base station 302 and a UE 304 corresponding to the use of UE-side SGCS-based monitoring of an AI / ML model for CSI compression and decompression. Preliminarily, the base station 302 sends 306 the UE 304 a reference signal. The UE 304 generates ground-truth CSI 308 based on its measurement of this reference signal.
[0046] The UE 304 then provides the ground-truth CSI 308 to an encoder 310 of the AI / ML model for CSI compression that is sited at the UE 304. The encoder 310 uses the ground-truth CSI 308 to generate AI / ML compressed CSI feedback 312 (e.g., a bitstream) .
[0047] The UE 304 then sends 314 the AI / ML compressed CSI feedback 312 to the base station 202, as illustrated.
[0048] The base station 302 provides the AI / ML compressed CSI feedback 312 as received from the UE 304 to a decoder 316 of the AI / ML model for CSI compression that is sited at the base station 302. Using the AI / ML compressed CSI feedback 312, the decoder 316 generates recovered CSI 318.
[0049] The base station 302 then sends 320 the recovered CSI 318 to the UE 304. In some examples, an eT2 codebook or an eT2-like high resolution codebook (which may be even more accurate than an eT2 codebook) is used to report the recovered CSI 318 to the base station 202. With respect to a reporting mode used, in some cases one or both of per sample reporting and / or reporting of a number of monitored samples may be used. Note that a determination of a type of KPI to calculate (e.g., SGCS or NMSE) using the recovered CSI 318 may turn at least in part on the reporting mode (s) so used. (Note that FIG. 3 assumes the case of SGCS use, as will be shown) .
[0050] The UE 304 then calculates a KPI using both the received ground-truth CSI 308 (which is understood in context as a “target” CSI that represents the actual channel estimation performed by the UE 304) and the AI / ML compressed CSI feedback 312 as received from the base station 302 (which is the result of encoding / compression and then decoding / decompression of the ground-truth CSI 308) . The UE then sends the result of the KPI calculation to the base station 302. Based on the result of the KPI calculation, the base station 302 can evaluate the accuracy of the AI / ML model for CSI compression that uses the encoder 310 and the decoder 316.
[0051] In the case of FIG. 3, this KPI calculation takes the form of an SGCS calculation 322 that results in an indication of the amount of similarity between the recovered CSI 318 and the ground-truth CSI 308. The UE 304 then sends 324 SGCS feedback 326 (the result of the SGCS calculation 322) to the base station 302, as illustrated. Based on the amount of similarity indicated by the SGCS feedback 326, the base station 302 can evaluate the accuracy of the AI / ML model for CSI compression that uses the encoder 310 and the decoder 316.
[0052] It can be seen that examples according to FIG. 2 and FIG. 3 act to provide some indication of relative similarity between unmodified CSI and recovered CSI corresponding to the use of an AI / ML model for CSI compression. While such indications are intermediately useful for evaluating a generalized accuracy corresponding to the case of AI / ML model use as a compared to a case of direct CSI reporting from the UE to the base station, the inherently relative nature of these KPIs does not ultimately quantify, in absolute terms, various applicable effects of the use of the AI / ML model. For example, a metric for a relative similarity between unmodified CSI and recovered CSI as determined according to the KPI calculations discussed in FIG. 2 and FIG. 3 does not provide any absolute understanding of an amount of a capacity loss due to the use of the AI / ML model and / or an amount of throughput loss experienced due to the use of the AI / ML model.
[0053] However, the use of KPIs and ground truth CSI for AI / ML based compression and decompression and for AI / ML monitoring as illustrated in FIG. 2 and FIG. 3 may introduce excessive overhead signaling and computational complexity from the computation and signaling of the KPIs and of the ground truth CSI. Similarly, there may be high signaling overhead from signaling the recovered CSI back to the UE as illustrate din FIG. 2 and FIG. 3.
[0054] Embodiments herein introduce details for detecting AI / ML monitoring events without using ground truth CSI data or excessive overhead signaling from the signaling of the KPIs and the ground truth CSI. For example, various embodiments herein relate to the use of CSI distribution based monitoring that focuses on the statistical or semantic properties of input or output CSI samples to detect a monitoring event. The CSI reflects the state of the wireless channel, which is influenced by the environment (e.g., movement of objects, user mobility) and the system configuration (e.g., antenna array changes, beamforming adjustments) . Any significant change in the environment or configuration / scenario alters the statistical or semantic properties of the CSI samples. As a result, by continuously monitoring how these properties evolve over time according to embodiments herein, sudden deviations or trends may be detected, signaling a monitoring event.
[0055] As has been described, performing monitoring operations may be “expensive” due to the necessity of signaling the ground truth CSI and / or the assumption of the availability of the ground truth CSI. However, embodiments described herein act to reduce the frequency of such monitoring procedures. For example, embodiments herein introduce the use of an indication of an event change that indicates that the AI / ML model has drifted or the input data distribution to the AI / ML model has drifted that acts as a trigger-gate for the use of more expensive procedures (e.g., procedures that use signaling of ground truth CSI) .
[0056] Embodiments herein introduce and utilize a power spectral entropy (PSE) value as a statistical measure of the similarity of an input data distribution. By monitoring the PSE values (e.g., over time by confirming a similarity between PSE values (e.g., consecutive PSE values or present and past PSE values) ) , circumstances where there is no need to employ the monitoring procedures illustrated in FIG. 2 and FIG. 3 (that are based on e.g., monitoring KPIs and the availability / signaling of the ground truth data) can be identified. Further, in the event that, when the computation and / or monitoring of the PSE value (s) indicates an event change, the KPI based monitoring procedures may be initiated. Note that the computation of the PSE is inexpensive, thus reducing computation complexity and overhead.
[0057] In some cases, CSI compression techniques may be used to reduce the amount of data needed to represent the channel. Compression is particularly important for high-dimensional CSI, where each signal path (or antenna port) is represented by multiple parameters (e.g., amplitude, phase, and frequency components) . Efficient compression can dramatically reduce the number of bits needed to describe the channel's state without sacrificing performance. Since the AI / ML model for CSI feedback performs compression, a value that measures the compressibility of the channel may be understood as a good value to compare the similarity of the input data distributions.
[0058] 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) .
[0059] 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 change and may trigger AI / ML monitoring events.
[0060] 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 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 may be used, where Fd and Fa are Nc × Nc and Nt × Nt DFT matrices. As a result, the CSI channel estimates (e.g., ) may be converted to the power profile through the use of 2D DFT processing.
[0061] FIG. 4 illustrates an example of performing 2D DFT 406 to generate a power profile 404 based on a MIMO channel 402, according to embodiments herein. For example, the MIMO channel 402 corresponding to a number of Tx antenna ports and a number of carriers may have 2D DFT 406 performed on it to generate a power profile 404.
[0062] 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., ) across the sub-carrier 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 In a third step, a normalized power profile (e.g., a power spectral density (PSD) profile) of the transformed matrices may be computed. For example, a normalized power profile may be computed according to the equation: 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=∑i∑jP [i] [j] log2 (P [i] [j] ) .
[0063] In some embodiments, the PSE value may indicate the smoothness, sparsity and / or correlation of the channel. For example, in the spatial-frequency domain, smoothness or correlation in CSI samples may indicate how coherent or predictable the wireless channel is across space and frequency. A low PSE value may suggest a more predictable (e.g., smooth / correlated) channel, meaning power is concentrated in a smaller number of dominant components. A high PSE value indicates a less predictable (e.g., less smooth, less correlated) channel, meaning power is distributed more evenly across components. In some instances, when transformed to the delay-beam domain, the sparsity of CSI samples reflects the channel's structure, such as multipath delays and angular spread of signals. A lower PSE value may imply a higher sparsity in the delay-beam domain, which simplifies the representation of CSI samples and enhances the efficiency of AI / ML-based compression. The wireless channel's behavior directly affects the PSE of CSI feedback samples.
[0064] In some embodiments, environmental changes such as mobility, obstructions, and interference can alter the smoothness or sparsity of the CSI samples. For example, at the UE, monitoring the PSE value of the input CSI feedback may detect changes in the RF environment in real time. At the network, tracking the PSE value of recovered CSI after decompression may help to assess the quality of the feedback and detect anomalies in the channel (e.g., in the CSI samples) or in the compression process.
[0065] In some embodiments, for AI / ML monitoring event detection, a PSE metric may be introduced to evaluate the difference in PSE values between two consecutive time points (e.g., D (t) = PSE (t) -PSE (t-1) ) , where PSE (t) is the PSE of the current CSI sample and PSE (t-1) is the PSE of the previous CSI sample) . In some instances, D (t) may capture a temporal change in the smoothness or sparsity of CSI samples. By analyzing the temporal differences in D (t) , monitoring events can be identified.
[0066] In some cases, a long-short term memory (LSTM) model can be used for anomaly detection in the temporal domain. For example, if the changes in D (t) are small as a UE slowly moves from one environment to another, the LSTM model may detect an anomaly in the channel when the UE is fully in the second environment due to changes in channel parameters, overhead, etc. In some cases, an LSTM model may be framed under reinforcement learning where the neural network learns to detect anomalies of PSE values' temporal variations given real time feedback (e.g., based on UE feedback) . In some cases, an LSTM model and reinforcement learning may be combined for anomaly detection in the temporal domain. Note that LSTM models are able to learn temporal dependencies and capturing trends or patterns in sequential data at an advanced level, thus making them well-suited for analyzing PSE temporal variations. Reinforcement learning models are able to perform dynamic real-time decision-making based on feedback from the environment at an advanced level and as such may adapt to changing conditions, such as UE feedback in a dynamic wireless network.
[0067] Additionally, in some cases, the changes in the PSE values may indicate when a user (e.g., a UE) transitions from a first scenario / environment to a second scenario / environment. For example, a user may transition from a static environment to a dynamic environment (e.g., moving from indoors to outdoors) . There may be a sharp increase in the change of the PSE value (or D (t) ) due to the sudden introduction of mobility and varying multipath effects. In another example, an obstacle may block the direct path between the transmitter and receiver, causing a switch from line-of-sight (LOS) operation to non-line-of-sight (NLOS) operation for the UE. As such, there may be a noticeable spike in the change of the PSE value (or D (t) ) as the PSE shifts due to altered multipath contributions. As a result, AI / ML monitoring may be triggered.
[0068] In some embodiments, AI / ML monitoring instructions may be detected based on the PSE value (or D (t) ) discussed herein (e.g., being high or low) . The AI / ML monitoring instructions may be detected at the network or at the UE and may be signaled to the UE and / or to the network respectively. For example, the network may decide to initiate a monitoring procedure with KPIs and requiring ground truth CSI. The network may decide to signal to the UE to de-activate the AI / ML model. The network may decide to signal to the UE to switch to another AI / ML model (e.g., a second AI / ML model) . The network may initiate retraining procedures of the AI / ML model based on current conditions. The network may also reconfigure parameters of the AI / ML model. Other example detected AI / ML monitoring events are not precluded.
[0069] FIG. 5 illustrates a flow diagram 500 for communications between a base station 502 and a UE 504 corresponding to PSE based AI / ML model monitoring event detection for CSI feedback, according to embodiments herein.
[0070] Preliminarily, the base station 502 sends 506 the UE 504 a reference signal. The UE 504 generates a CSI estimation 508 (e.g., CSI feedback) based on its measurement of this reference signal.
[0071] The UE 504 uses the CSI estimation 508 for a PSE computation 510 (e.g., either a PSE value or D (t) discussed herein) . Then, the UE 504 uses an anomaly detector 514 on the computed PSE value to detect any anomalies in the PSE value (e.g., analyzing D (t) , checking if the PSE value is abnormal, using an LSTM model) . In some cases, the UE 504 reports 518 the result of the PSE computation 510 and reports 520 detected anomalies from the anomaly detector 514 to the base station 502. In some other cases, the UE only reports 518 the result of the PSE computation 510 to the base station 502. Further, the UE 504 provides the CSI estimation 508 to an encoder 512 of the AI / ML model for CSI compression that is sited at the UE 504. The encoder 512 uses the CSI estimation 508 to generate AI / ML compressed CSI feedback 516 (e.g., a bitstream) . The UE 504 provides the AI / ML compressed CSI feedback 516 to the base station 502.
[0072] Accordingly, the base station 502 provides the AI / ML compressed CSI feedback 516 as received from the UE 504 to a decoder 522 of the AI / ML model for CSI decompression that is sited at the base station 502. Using the AI / ML compressed CSI feedback 516, the decoder 522 generates recovered CSI feedback 532 and the base station 502 uses it for a computation of the PSE 524. In some cases, the base station 502 detects 526 AI / ML monitoring events based on the computation of the PSE 524 and anomalies detected in the result of the computation of the PSE 524 (e.g., an abnormal PSE value, spikes in a difference in consecutive PSE value, D (t) , using an LSTM model) and generates an AI / ML model use instruction based on the detected AI / ML monitoring events. In some other cases, the base station 502 detects 526 AI / ML monitoring events based on the reported PSE and the reported detected anomalies received from the UE 504 and generates an AI / ML model use instruction based on the detected AI / ML monitoring events.
[0073] Subsequently, in some instances, the base station 502 utilizes 530 the AI / ML model use instruction at the base station 502 (e.g., configure the decoder of the AI / ML model based on the AI / ML model use instruction) . In some other cases, the base station 502 signals 528 the AI / ML model use instruction to the UE 504 for the UE 504 to utilize (e.g., configure the encoder of the AI / ML model) .
[0074] FIG. 6 illustrates a method 600 of a UE, according to embodiments herein. The illustrated method 600 includes generating 602 CSI feedback based on a reference signal received from a base station. The method 600 further include generating 604, at the UE, a first PSE value corresponding to a distribution of power of the reference signal across a frequency domain and a spatial domain used. The method 600 further includes applying 606 the CSI feedback at a first encoder of a first AI / ML model that is at the UE to generate compressed CSI feedback. The method 600 further includes sending 608, to the base station, the compressed CSI feedback and the first PSE value.
[0075] In some embodiments, the method 600 further comprises receiving, from the base station, in response to sending the compressed CSI feedback and the first PSE value, an AI / ML model use instruction, and configuring a use of the first AI / ML model based on the AI / ML model use instruction. In some such embodiments, the AI / ML model use instruction comprises an instruction to initiate monitoring of the AI / ML model that uses KPIs and ground truth CSI feedback, and wherein the configuring the use of the first AI / ML model based on the AI / ML model use instruction comprises initiating the AI / ML monitoring of the AI / ML model that uses the KPIs and the ground truth CSI feedback. In some other such embodiments, the AI / ML model use instruction comprises an instruction to de-activate the first AI / ML model, and wherein the configuring the use of the first AI / ML model based on the AI / ML model use instruction comprises deactivating the first encoder of the first AI / ML model based on the instruction. In yet some other such embodiments, the AI / ML model use instruction comprises an instruction to switch to a second AI / ML model, and wherein configuring the use of the first AI / ML model based on the AI / ML model use instruction comprises deactivating the first encoder of the first AI / ML model. In yet some other such embodiments, the AI / ML model use instruction comprises an instruction to retrain the first AI / ML model based on current conditions, and wherein configuring the use of the first AI / ML model based on the AI / ML model use instruction comprises retraining the first encoder of the first AI / ML model based on the current conditions. In yet some other such embodiments, the AI / ML model use instruction comprises an instruction to reconfigure parameters of the first AI / ML model, and wherein configuring the use of the first AI / ML model based on the AI / ML model use instruction comprises reconfiguring the parameters of the first encoder of the first AI / ML model.
[0076] In some embodiments, the method 600 further comprises detecting a channel anomaly in a temporal domain of the reference signal based on a PSE monitoring procedure that uses a difference between the first PSE value and a second PSE value, and sending, to the base station, the channel anomaly.
[0077] In some embodiments of the method 600, generating the first PSE value comprises generating frequency response CSI using the 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.
[0078] FIG. 7 illustrates a method 700 of a base station, according to embodiments herein. The illustrated method 700 includes sending 702, to a UE, a reference signal. The method 700 further includes receiving 704, from the UE, PSE information, wherein the PSE information corresponds to a distribution of power of the reference signal across a frequency domain and a spatial domain. The method 700 further includes determining 706 an AI / ML model use instruction based on the PSE information. The method 700 further includes sending 708, to the UE, the AI / ML use instruction.
[0079] In some embodiments of the method 700, the PSE information comprises a first PSE value, and wherein determining the AI / ML model use instruction is based on the first PSE value.
[0080] In some embodiments of the method 700, the PSE information comprises a difference between a first PSE value and a second PSE value monitored at the UE, wherein determining the AI / ML model use instruction is based on monitoring the difference between the first PSE value and the second PSE value.
[0081] In some embodiments, the method 700 further comprises configuring a use of a first AI / ML model based on the AI / ML model use instruction. In some such embodiments, the AI / ML model use instruction comprises an instruction to reconfigure parameters of the first AI / ML model.
[0082] In some embodiments of the method 700, the AI / ML model use instruction comprises an instruction to initiate monitoring of the first AI / ML model that uses KPIs and ground truth CSI feedback.
[0083] In some embodiments of the method 700, the AI / ML model use instruction comprises an instruction to de-activate the first AI / ML model.
[0084] In some embodiments of the method 700, the AI / ML model use instruction comprises an instruction to switch to a second AI / ML model.
[0085] In some embodiments of the method 700, the AI / ML model use instruction comprises an instruction to retrain the first AI / ML model based on current conditions.
[0086] In some embodiments, the method 700 further comprises receiving, from the UE, a channel anomaly in a temporal domain of the reference signal based on the PSE information, wherein determining the AI / ML model use instruction is further based on the channel anomaly.
[0087] FIG. 8 illustrates a method 800 of a base station, according to embodiments herein. The illustrated method 800 includes sending 802, to a UE, a reference signal. The method 800 further includes receiving 804, from the UE, compressed CSI feedback. The method 800 further includes applying 806 the compressed CSI feedback at a first decoder of a first AI / ML model that is at the base station to generate recovered CSI feedback. The method 800 further includes generating 808, at the base station, a first PSE value based on the recovered CSI feedback. The method 800 further includes determining 810 an AI / ML model use instruction based on the first PSE value. The method 800 further includes sending 812, to the UE, the AI / ML model use instruction.
[0088] In some embodiments, the method 800 further comprises configuring a use of the first AI / ML model based on the AI / ML model use instruction. In some such embodiments, the AI / ML model use instruction comprises an instruction to initiate AI / ML compression using KPIs and ground truth CSI feedback.
[0089] In some embodiments of the method 800, the AI / ML model use instruction comprises an instruction to de-activate the first AI / ML model.
[0090] In some embodiments of the method 800, the AI / ML model use instruction comprises an instruction to switch to a second AI / ML model.
[0091] In some embodiments of the method 800, the AI / ML model use instruction comprises an instruction to retrain the first AI / ML model based on current conditions.
[0092] In some embodiments of the method 800, the AI / ML model use instruction comprises an instruction to reconfigure parameters of the first AI / ML model.
[0093] In some embodiments, the method 800 further comprises detecting a channel anomaly in a temporal domain of the reference signal based on a PSE monitoring procedure that uses a difference between the first PSE value and a second PSE value, wherein determining the AI / ML model use instruction is further based on the monitoring procedure.
[0094] In some embodiments of the method 800, generating the PSE value comprises generating frequency response CSI using the 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 PSE value based on the normalized power profile.
[0095] FIG. 9 illustrates a method 900 of a UE, according to embodiments herein. The illustrated method 900 includes generating 902 CSI feedback based on a reference signal received from a base station. The method 900 further includes applying 904 the CSI feedback at a first encoder of a first AI / ML model that is at the UE to generate compressed CSI feedback. The method 900 further includes sending 906, to the base station, the compressed CSI feedback. The method 900 further includes receiving 908, from the base station, an AI / ML use instruction determined at the base station based on PSE information corresponding to a distribution of power of the reference signal across a frequency domain and a spatial domain. The method 900 further includes configuring 910 a use of the first AI / ML model based on the AI / ML model use instruction.
[0096] In some embodiments of the method 900, the AI / ML model use instruction comprises an instruction to initiate AI / ML compression using KPIs and ground truth CSI feedback, and wherein the configuring the use of the first AI / ML model based on the AI / ML model use instruction comprises initiating the AI / ML compression using the KPIs and the ground truth CSI feedback at the first encoder of the first AI / ML model based on the instruction.
[0097] In some embodiments of the method 900, the AI / ML model use instruction comprises an instruction to de-activate the first AI / ML model, and wherein the configuring the use of the first AI / ML model based on the AI / ML model use instruction comprises deactivating the first encoder of the first AI / ML model based on the instruction.
[0098] In some embodiments of the method 900, the AI / ML model use instruction comprises an instruction to switch to a second AI / ML model, and wherein configuring the use of the first AI / ML model based on the AI / ML model use instruction comprises deactivating the first encoder of the first AI / ML model.
[0099] In some embodiments of the method 900, the AI / ML model use instruction comprises an instruction to retrain the first AI / ML model based on current conditions, and wherein configuring the use of the first AI / ML model based on the AI / ML model use instruction comprises retraining the first encoder of the first AI / ML model based on the current conditions.
[0100] In some embodiments of the method 900, the AI / ML model use instruction comprises an instruction to reconfigure parameters of the first AI / ML model, and wherein configuring the use of the first AI / ML model based on the AI / ML model use instruction comprises reconfiguring the parameters of a first encoder of the first AI / ML model.
[0101] FIG. 10 illustrates an example architecture of a wireless communication system 1000, according to embodiments disclosed herein. The following description is provided for an example wireless communication system 1000 that operates in conjunction with the LTE system standards and / or 5G or NR system standards as provided by 3GPP technical specifications.
[0102] As shown by FIG. 10, the wireless communication system 1000 includes UE 1002 and UE 1004 (although any number of UEs may be used) . In this example, the UE 1002 and the UE 1004 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.
[0103] The UE 1002 and UE 1004 may be configured to communicatively couple with a RAN 1006. In embodiments, the RAN 1006 may be NG-RAN, E-UTRAN, etc. The UE 1002 and UE 1004 utilize connections (or channels) (shown as connection 1008 and connection 1010, respectively) with the RAN 1006, each of which comprises a physical communications interface. The RAN 1006 can include one or more base stations (such as base station 1012 and base station 1014) that enable the connection 1008 and connection 1010.
[0104] In this example, the connection 1008 and connection 1010 are air interfaces to enable such communicative coupling, and may be consistent with RAT (s) used by the RAN 1006, such as, for example, an LTE and / or NR.
[0105] In some embodiments, the UE 1002 and UE 1004 may also directly exchange communication data via a sidelink interface 1016. The UE 1004 is shown to be configured to access an access point (shown as AP 1018) via connection 1020. By way of example, the connection 1020 can comprise a local wireless connection, such as a connection consistent with any IEEE 802.11 protocol, wherein the AP 1018 may comprise a router. In this example, the AP 1018 may be connected to another network (for example, the Internet) without going through a CN 1024.
[0106] In embodiments, the UE 1002 and UE 1004 can be configured to communicate using orthogonal frequency division multiplexing (OFDM) communication signals with each other or with the base station 1012 and / or the base station 1014 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.
[0107] In some embodiments, all or parts of the base station 1012 or base station 1014 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 1012 or base station 1014 may be configured to communicate with one another via interface 1022. In embodiments where the wireless communication system 1000 is an LTE system (e.g., when the CN 1024 is an EPC) , the interface 1022 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 1000 is an NR system (e.g., when CN 1024 is a 5GC) , the interface 1022 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 to 5GC, between a base station 1012 (e.g., a gNB) connecting to 5GC and an eNB, and / or between two eNBs connecting to 5GC (e.g., CN 1024) .
[0108] The RAN 1006 is shown to be communicatively coupled to the CN 1024. The CN 1024 may comprise one or more network elements 1026, which are configured to offer various data and telecommunications services to customers / subscribers (e.g., users of UE 1002 and UE 1004) who are connected to the CN 1024 via the RAN 1006. The components of the CN 1024 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) .
[0109] In embodiments, the CN 1024 may be an EPC, and the RAN 1006 may be connected with the CN 1024 via an S1 interface 1028. In embodiments, the S1 interface 1028 may be split into two parts, an S1 user plane (S1-U) interface, which carries traffic data between the base station 1012 or base station 1014 and a serving gateway (S-GW) , and the S1-MME interface, which is a signaling interface between the base station 1012 or base station 1014 and mobility management entities (MMEs) .
[0110] In embodiments, the CN 1024 may be a 5GC, and the RAN 1006 may be connected with the CN 1024 via an NG interface 1028. In embodiments, the NG interface 1028 may be split into two parts, an NG user plane (NG-U) interface, which carries traffic data between the base station 1012 or base station 1014 and a user plane function (UPF) , and the S1 control plane (NG-C) interface, which is a signaling interface between the base station 1012 or base station 1014 and access and mobility management functions (AMFs) .
[0111] Generally, an application server 1030 may be an element offering applications that use internet protocol (IP) bearer resources with the CN 1024 (e.g., packet switched data services) . The application server 1030 can also be configured to support one or more communication services (e.g., VoIP sessions, group communication sessions, etc. ) for the UE 1002 and UE 1004 via the CN 1024. The application server 1030 may communicate with the CN 1024 through an IP communications interface 1032.
[0112] FIG. 11 illustrates a system 1100 for performing signaling 1134 between a wireless device 1102 and a network device 1118, according to embodiments disclosed herein. The system 1100 may be a portion of a wireless communications system as herein described. The wireless device 1102 may be, for example, a UE of a wireless communication system. The network device 1118 may be, for example, a base station (e.g., an eNB or a gNB) of a wireless communication system.
[0113] The wireless device 1102 may include one or more processor (s) 1104. The processor (s) 1104 may execute instructions such that various operations of the wireless device 1102 are performed, as described herein. The processor (s) 1104 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.
[0114] The wireless device 1102 may include a memory 1106. The memory 1106 may be a non-transitory computer-readable storage medium that stores instructions 1108 (which may include, for example, the instructions being executed by the processor (s) 1104) . The instructions 1108 may also be referred to as program code or a computer program. The memory 1106 may also store data used by, and results computed by, the processor (s) 1104.
[0115] The wireless device 1102 may include one or more transceiver (s) 1110 that may include radio frequency (RF) transmitter circuitry and / or receiver circuitry that use the antenna (s) 1112 of the wireless device 1102 to facilitate signaling (e.g., the signaling 1134) to and / or from the wireless device 1102 with other devices (e.g., the network device 1118) according to corresponding RATs.
[0116] The wireless device 1102 may include one or more antenna (s) 1112 (e.g., one, two, four, or more) . For embodiments with multiple antenna (s) 1112, the wireless device 1102 may leverage the spatial diversity of such multiple antenna (s) 1112 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 1102 may be accomplished according to precoding (or digital beamforming) that is applied at the wireless device 1102 that multiplexes the data streams across the antenna (s) 1112 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 (where the 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) .
[0117] In certain embodiments having multiple antennas, the wireless device 1102 may implement analog beamforming techniques, whereby phases of the signals sent by the antenna (s) 1112 are relatively adjusted such that the (joint) transmission of the antenna (s) 1112 can be directed (this is sometimes referred to as beam steering) .
[0118] The wireless device 1102 may include one or more interface (s) 1114. The interface (s) 1114 may be used to provide input to or output from the wireless device 1102. For example, a wireless device 1102 that is a UE may include interface (s) 1114 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) 1110 / antenna (s) 1112 already described) that allow for communication between the UE and other devices and may operate according to known protocols (e.g., and the like) .
[0119] The wireless device 1102 may include a PSE value module 1116. The PSE value module 1116 may be implemented via hardware, software, or combinations thereof. For example, the PSE value module 1116 may be implemented as a processor, circuit, and / or instructions 1108 stored in the memory 1106 and executed by the processor (s) 1104. In some examples, the PSE value module 1116 may be integrated within the processor (s) 1104 and / or the transceiver (s) 1110. For example, the PSE value module 1116 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) 1104 or the transceiver (s) 1110.
[0120] The PSE value module 1116 may be used for various aspects of the present disclosure, for example, aspects of FIG. 4, FIG. 5, FIG. 6 and FIG. 9. For example, the PSE value module 1116 may configure the wireless device 1102 to generate CSI feedback based on a reference signal received from a network device 1118; generate, at the wireless device 1102, a first PSE value corresponding to a distribution of power of the reference signal across a frequency domain and a spatial domain used; apply the CSI feedback at a first encoder of a first AI / ML model that is at the wireless device 1102 to generate compressed CSI feedback; and send, to the wireless device 1102, the compressed CSI feedback and the first PSE value. In other examples, the PSE value module 1116 may configure the wireless device 1102 to generate CSI feedback based on a reference signal received from a network device 1118; apply the CSI feedback at a first encoder of a first AI / ML model that is at the wireless device 1102 to generate compressed CSI feedback; send, to the network device 1118, the compressed CSI feedback; receive, from the network device 1118, an AI / ML use instruction determined at the network device 1118 based on PSE information corresponding to a distribution of power of the reference signal across a frequency domain and a spatial domain; and configure a use of the first AI / ML model based on the AI / ML model use instruction.
[0121] The network device 1118 may include one or more processor (s) 1120. The processor (s) 1120 may execute instructions such that various operations of the network device 1118 are performed, as described herein. The processor (s) 1120 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.
[0122] The network device 1118 may include a memory 1122. The memory 1122 may be a non-transitory computer-readable storage medium that stores instructions 1124 (which may include, for example, the instructions being executed by the processor (s) 1120) . The instructions 1124 may also be referred to as program code or a computer program. The memory 1122 may also store data used by, and results computed by, the processor (s) 1120.
[0123] The network device 1118 may include one or more transceiver (s) 1126 that may include RF transmitter circuitry and / or receiver circuitry that use the antenna (s) 1128 of the network device 1118 to facilitate signaling (e.g., the signaling 1134) to and / or from the network device 1118 with other devices (e.g., the wireless device 1102) according to corresponding RATs.
[0124] The network device 1118 may include one or more antenna (s) 1128 (e.g., one, two, four, or more) . In embodiments having multiple antenna (s) 1128, the network device 1118 may perform MIMO, digital beamforming, analog beamforming, beam steering, etc., as has been described.
[0125] The network device 1118 may include one or more interface (s) 1130. The interface (s) 1130 may be used to provide input to or output from the network device 1118. For example, a network device 1118 that is a base station may include interface (s) 1130 made up of transmitters, receivers, and other circuitry (e.g., other than the transceiver (s) 1126 / antenna (s) 1128 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, administration, and maintenance of the base station or other equipment operably connected thereto.
[0126] The network device 1118 may include a PSE value module 1132. The PSE value module 1132 may be implemented via hardware, software, or combinations thereof. For example, the PSE value module 1132 may be implemented as a processor, circuit, and / or instructions 1124 stored in the memory 1122 and executed by the processor (s) 1120. In some examples, the PSE value module 1132 may be integrated within the processor (s) 1120 and / or the transceiver (s) 1126. For example, the PSE value module 1132 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) 1120 or the transceiver (s) 1126.
[0127] The PSE value module 1132 may be used for various aspects of the present disclosure, for example, aspects of FIG. 4, FIG. 5, FIG. 7 and FIG. 8. For example, the PSE value module 1132 may configure the network device 1118 to send, to a wireless device 1102, a reference signal; receive, from the wireless device 1102, PSE information, wherein the PSE information corresponds to a distribution of power of the reference signal across a frequency domain and a spatial domain; determine an AI / ML model use instruction based on the PSE information; and send, to the wireless device 1102, the AI / ML use instruction. In other examples, the PSE value module 1132 may configure the network device 1118 to send, to a wireless device 1102, a reference signal; receive, from the wireless device 1102, compressed CSI feedback; apply the compressed CSI feedback at a first decoder of a first AI / ML model that is at the network device 1118 to generate recovered CSI feedback; generate, at the network device 1118, a first PSE value based on the recovered CSI feedback; determine an AI / ML model use instruction based on the first PSE value; and send, to the wireless device 1102, the AI / ML model use instruction.
[0128] Embodiments contemplated herein include an apparatus comprising means to perform one or more elements of the method 600 and method 900. This apparatus may be, for example, an apparatus of a UE (such as a wireless device 1102 that is a UE, as described herein) .
[0129] 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 and method 900. This non-transitory computer-readable media may be, for example, a memory of a UE (such as a memory 1106 of a wireless device 1102 that is a UE, as described herein) .
[0130] Embodiments contemplated herein include an apparatus comprising logic, modules, or circuitry to perform one or more elements of the method 600 and method 900. This apparatus may be, for example, an apparatus of a UE (such as a wireless device 1102 that is a UE, as described herein) .
[0131] 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 600 and method 900. This apparatus may be, for example, an apparatus of a UE (such as a wireless device 1102 that is a UE, as described herein) .
[0132] Embodiments contemplated herein include a signal as described in or related to one or more elements of the method 600 and method 900.
[0133] 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 600 and method 900. The processor may be a processor of a UE (such as a processor (s) 1104 of a wireless device 1102 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 1106 of a wireless device 1102 that is a UE, as described herein) .
[0134] Embodiments contemplated herein include an apparatus comprising means to perform one or more elements of the method 700 and method 800. This apparatus may be, for example, an apparatus of a base station (such as a network device 1118 that is a base station, as described herein) .
[0135] 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 700 and method 800. This non-transitory computer-readable media may be, for example, a memory of a base station (such as a memory 1122 of a network device 1118 that is a base station, as described herein) .
[0136] Embodiments contemplated herein include an apparatus comprising logic, modules, or circuitry to perform one or more elements of the method 700 and method 800. This apparatus may be, for example, an apparatus of a base station (such as a network device 1118 that is a base station, as described herein) .
[0137] 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 700 and method 800. This apparatus may be, for example, an apparatus of a base station (such as a network device 1118 that is a base station, as described herein) .
[0138] Embodiments contemplated herein include a signal as described in or related to one or more elements of the method 700 and method 800.
[0139] 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 700 and method 800. The processor may be a processor of a base station (such as a processor (s) 1120 of a network device 1118 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 1122 of a network device 1118 that is a base station, as described herein) .
[0140] 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.
[0141] 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.
[0142] Embodiments and implementations of the systems 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 for performing the operations or may include a combination of hardware, software, and / or firmware.
[0143] 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.
[0144] 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.
[0145] 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.
Claims
1.A method of a user equipment (UE) , comprising:generating channel state information (CSI) feedback based on a reference signal received from a base station;generating, at the UE, a first power spectral entropy (PSE) value corresponding to a distribution of power of the reference signal across a frequency domain and a spatial domain used;applying the CSI feedback at a first encoder of a first artificial intelligence (AI) / machine learning (ML) model that is at the UE to generate compressed CSI feedback; andsending, to the base station, the compressed CSI feedback and the first PSE value.2.The method of claim 1 further comprising:receiving, from the base station, in response to sending the compressed CSI feedback and the first PSE value, an AI / ML model use instruction; andconfiguring a use of the first AI / ML model based on the AI / ML model use instruction.3.The method of claim 2, wherein the AI / ML model use instruction comprises an instruction to initiate monitoring of the AI / ML model that uses key performance indicators (KPIs) and ground truth CSI feedback, and wherein the configuring the use of the first AI / ML model based on the AI / ML model use instruction comprises initiating the AI / ML monitoring of the AI / ML model that uses the KPIs and the ground truth CSI feedback.4.The method of claim 2, wherein the AI / ML model use instruction comprises an instruction to de-activate the first AI / ML model, and wherein the configuring the use of the first AI / ML model based on the AI / ML model use instruction comprises deactivating the first encoder of the first AI / ML model based on the instruction.5.The method of claim 2, wherein the AI / ML model use instruction comprises an instruction to switch to a second AI / ML model, and wherein configuring the use of the first AI / ML model based on the AI / ML model use instruction comprises deactivating the first encoder of the first AI / ML model.6.The method of claim 2, wherein the AI / ML model use instruction comprises an instruction to retrain the first AI / ML model based on current conditions, and wherein configuring the use of the first AI / ML model based on the AI / ML model use instruction comprises retraining the first encoder of the first AI / ML model based on the current conditions.7.The method of claim 2, wherein the AI / ML model use instruction comprises an instruction to reconfigure parameters of the first AI / ML model, and wherein configuring the use of the first AI / ML model based on the AI / ML model use instruction comprises reconfiguring the parameters of the first encoder of the first AI / ML model.8.The method of claim 1 further comprising:detecting a channel anomaly in a temporal domain of the reference signal based on a PSE monitoring procedure that uses a difference between the first PSE value and a second PSE value; andsending, to the base station, the channel anomaly.9.The method of claim 1, wherein generating the first PSE value comprises:generating frequency response CSI using the 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; andcomputing the first PSE value based on the normalized power profile.10.A method of a base station, comprising:sending, to a user equipment (UE) , a reference signal;receiving, from the UE, power spectral entropy (PSE) information, wherein the PSE information corresponds to a distribution of power of the reference signal across a frequency domain and a spatial domain;determining an artificial intelligence (AI) / machine learning (ML) model use instruction based on the PSE information; andsending, to the UE, the AI / ML use instruction.11.The method of claim 10, wherein the PSE information comprises a first PSE value, and wherein determining the AI / ML model use instruction is based on the first PSE value.12.The method of claim 10, wherein the PSE information comprises a difference between a first PSE value and a second PSE value monitored at the UE, wherein determining the AI / ML model use instruction is based on monitoring the difference between the first PSE value and the second PSE value.13.The method of claim 10, further comprising configuring a use of a first AI / ML model based on the AI / ML model use instruction.14.The method of claim 13, wherein the AI / ML model use instruction comprises an instruction to reconfigure parameters of the first AI / ML model.15.The method of claim 10, wherein the AI / ML model use instruction comprises an instruction to initiate monitoring of a first AI / ML model that uses key performance indicators (KPIs) and ground truth CSI feedback.16.The method of claim 10, wherein the AI / ML model use instruction comprises an instruction to de-activate a first AI / ML model.17.The method of claim 10, wherein the AI / ML model use instruction comprises an instruction to switch from a first AI / ML model to a second AI / ML model.18.The method of claim 10, wherein the AI / ML model use instruction comprises an instruction to retrain a first AI / ML model based on current conditions.19.The method of claim 10, further comprising receiving, from the UE, a channel anomaly in a temporal domain of the reference signal based on the PSE information, wherein determining the AI / ML model use instruction is further based on the channel anomaly.20.A method of a base station, comprising:sending, to a user equipment (UE) , a reference signal;receiving, from the UE, compressed channel state information (CSI) feedback;applying the compressed CSI feedback 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;generating, at the base station, a first power spectral entropy (PSE) value based on the recovered CSI feedback;determining an AI / ML model use instruction based on the first PSE value; andsending, to the UE, the AI / ML model use instruction.21.The method of claim 20, further comprising configuring a use of the first AI / ML model based on the AI / ML model use instruction.22.The method of claim 21, wherein the AI / ML model use instruction comprises an instruction to initiate AI / ML compression using key performance indicators (KPIs) and ground truth CSI feedback.23.The method of claim 20, wherein the AI / ML model use instruction comprises an instruction to de-activate the first AI / ML model.24.The method of claim 20, wherein the AI / ML model use instruction comprises an instruction to switch to a second AI / ML model.25.The method of claim 20, wherein the AI / ML model use instruction comprises an instruction to retrain the first AI / ML model based on current conditions.26.The method of claim 20, wherein the AI / ML model use instruction comprises an instruction to reconfigure parameters of the first AI / ML model.27.The method of claim 20, further comprising detecting a channel anomaly in a temporal domain of the reference signal based on a PSE monitoring procedure that uses a difference between the first PSE value and a second PSE value, wherein determining the AI / ML model use instruction is further based on the monitoring procedure.28.The method of claim 20, wherein generating the PSE value comprises:generating frequency response CSI using the 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; andcomputing the PSE value based on the normalized power profile.29.A method of a user equipment (UE) , comprising:generating channel state information (CSI) feedback based on a reference signal received from a base station;applying the CSI feedback at a first encoder of a first artificial intelligence (AI) / machine learning (ML) model that is at the UE to generate compressed CSI feedback;sending, to the base station, the compressed CSI feedback;receiving, from the base station, an AI / ML use instruction determined at the base station based on power spectral entropy (PSE) information corresponding to a distribution of power of the reference signal across a frequency domain and a spatial domain; andconfiguring a use of the first AI / ML model based on the AI / ML model use instruction.30.The method of claim 29, wherein the AI / ML model use instruction comprises an instruction to initiate AI / ML compression using key performance indicators (KPIs) and ground truth CSI feedback, and wherein the configuring the use of the first AI / ML model based on the AI / ML model use instruction comprises initiating the AI / ML compression using the KPIs and the ground truth CSI feedback at the first encoder of the first AI / ML model based on the instruction.31.The method of claim 29, wherein the AI / ML model use instruction comprises an instruction to de-activate the first AI / ML model, and wherein the configuring the use of the first AI / ML model based on the AI / ML model use instruction comprises deactivating the first encoder of the first AI / ML model based on the instruction.32.The method of claim 29, wherein the AI / ML model use instruction comprises an instruction to switch to a second AI / ML model, and wherein configuring the use of the first AI / ML model based on the AI / ML model use instruction comprises deactivating the first encoder of the first AI / ML model.33.The method of claim 29, wherein the AI / ML model use instruction comprises an instruction to retrain the first AI / ML model based on current conditions, and wherein configuring the use of the first AI / ML model based on the AI / ML model use instruction comprises retraining the first encoder of the first AI / ML model based on the current conditions.34.The method of claim 29, wherein the AI / ML model use instruction comprises an instruction to reconfigure parameters of the first AI / ML model, and wherein configuring the use of the first AI / ML model based on the AI / ML model use instruction comprises reconfiguring the parameters of a first encoder of the first AI / ML model.35.An apparatus comprising means to perform the method of any of claim 1 to claim 34.36.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 34.37.An apparatus comprising logic, modules, or circuitry to perform the method of any of claim 1 to claim 34.38.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 and claim 29 to claim 34.39.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 10 to claim 28.