Performance monitoring output and report configuration for ai / ML based CSI prediction
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2026-02-04
- Publication Date
- 2026-08-13
Smart Images
Figure US2026013806_13082026_PF_FP_ABST
Abstract
Description
PERFORMANCE MONITORING OUTPUT AND REPORT CONFIGURATION FOR AI / ML BASED CSI PREDICTIONTECHNICAL FIELD
[0001] This application relates generally to wireless communication systems, including systems implementing AI / ML models.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), 3GPP 6G Radio, 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), and / or 6G RAT.
[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), and 6G RAN implements 6G RAT. In certain deployments, the E-UTRAN may also implement NR RAT. In certain deployments, NG-RAN may also implement LTE RAT. In certain deployments, a 6G RAN may also implement NR RAT.14916-3339-7133,1 P70868WO1
[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). One example of a 6G RAN base station is a 6G NodeB.
[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), and a 6G RAN may utilize a 6G Core Network (6GC).BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS
[0007] 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.
[0008] FIG. 1A and FIG. IB illustrate example CSI-RS set configurations for performance monitoring, according to embodiments herein.
[0009] FIG. 2 illustrates an example of an aperiodic CSI report triggered by a DCI trigger, according to embodiments herein.
[0010] FIG. 3 illustrates an example of a DCI triggering multiple AP CSI-RS resource set transmissions, according to embodiments herein.
[0011] FIG. 4 illustrates an example of event driven reporting for an output of performance monitoring, according to embodiments herein.
[0012] FIG. 5 is a flowchart of a method of a UE, according to certain embodiments.
[0013] FIG. 6 is a flowchart of a method of a base station, according to certain embodiments.
[0014] FIG. 7 illustrates an example architecture of a wireless communication sy stem, according to embodiments disclosed herein.
[0015] FIG. 8 illustrates a system for performing signaling between a wireless device and a network device, according to embodiments disclosed herein.DETAILED DESCRIPTION24916-3339-7133,1 P70868WO1
[0016] 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.
[0017] Channel State Information Prediction
[0018] Various embodiments related to performance monitoring for artificial intelligence and / or machine learning (AI / ML) models are discussed herein. In some examples, performance monitoring for AI / ML models for channel state information (CSI) feedback prediction (e.g., temporal CSI feedback prediction) are discussed. Note that as used herein, the terms CSI " and “CSI feedback" may be used interchangeably.
[0019] With respect to performance monitoring for functionality-based lifecycle management (LCM) for CSI prediction cases using UE-side AI / ML models, various aspects may be considered.
[0020] In a first such aspect (i.e., Type 1), a UE calculates inferencing performance metric(s) for the AI / ML model for CSI prediction. Then, the UE reports performance monitoring output based on those inferencing performance metric(s) that facilitates, as needed, a functionality fallback decision (e.g., to a CSI feedback mechanism that does not use AI / ML model inferencing) at the network side. Details of the performance monitoring output may be defined in some instances. The network may configure threshold criteria for such a use of UE-side performance monitoring. The network makes decision(s) with respect to functionality fallback operation (or not).
[0021] In a second aspect (i.e., Type 2), a UE reports predicted CSI and / or corresponding ground-truth CSI to the network. The network uses this information to calculate inferencing performance metric(s) for the AI / ML model. Then, the network makes decision(s) with respect to functionality fallback operation (or not).
[0022] In a third aspect (i.e., Type 3), a UE calculates inferencing performance metric(s) for the AI / ML model. The UE then reports the inferencing performance metric(s) to the network. The network then makes decision(s) with respect to functionality fallback operation (or not) (e.g., fallback to legacy CSI reporting).
[0023] Corresponding to one or more of these aspects, it may be that functionality selection / activation / deactivation / switching as defined for other UE-side use cases can be 34916-3339-7133,1 P70868WO1reused, if applicable. Further, details for the configuration of and procedure for performance monitoring may vary. Details for the configuration of channel state information reference signal(s) (CSI-RS(s)) that are used / measured as part of the performance monitoring may vary.
[0024] The inferencing performance metric(s) used may include, for example, intermediate key inferencing performance metric(s) (KPI(s)) (e.g., a normalized mean squared error (NMSE) metric type and / or a squared generalized cosine similarity' (SGCS) metric type).
[0025] UE report types may include, for example, a periodic reporting type, a semi-persistent reporting ty pe, an aperiodic reporting type, and / or an event driven reporting ty pe, as the case may be. Down selection may also be used.
[0026] Corresponding to such aspects, it is contemplated that a UE may make decision(s) within the same functionality with respect to model selection, activation, deactivation, and / or switching operation that is transparent to the network.
[0027] In various wireless communication systems, performance monitoring for CSI prediction includes high level procedures for network side performance monitoring and UE side performance monitoring. Embodiments disclosed herein provide UE reporting for performance monitoring. For example, certain embodiments provide performance monitoring output and / or event definition for Type 1 performance monitoring. Certain such embodiments include metric and / or threshold configuration to the UE. In addition, or in other embodiments, periodic, aperiodic, and / or event-driven reporting are disclosed for Type 1, Type 2, and / or Type 3 performance monitoring.
[0028] Type 1 Performance Monitoring Metric
[0029] In certain embodiments, a performance monitoring output comprises a prediction accuracy. In one such embodiment, the prediction accuracy is based on the SGCS between a predicted precoding matrix indicator (PMI) and a ground truth PMI (i.e., the difference between predicted PMI and measured or non-predicted PMI). For example, a UE may use a UE-side model to predict a future channel directly and then calculates the predicted PMI based on the predicted channel. Such a method may provide better performance (e g., as compared to using the UE-side model to predict future PMI directly using past PMI as a model input).
[0030] In one embodiment that calculates the predicted PMI based on the predicted channel, the predicted PMI is the eigen-vector of the predicted channel, and the ground 44916-3339-7133,1 P70868WO1truth PMI calculated via a measured channel in a prediction window is the eigen-vector of the measured channel. Such an embodiment may be useful, for example, when CSI prediction is followed by Al based CSI compression (i.e., no codebook based compression is used).
[0031] In another embodiment that calculates the predicted PMI based on the predicted channel, the predicted PMI is calculated based on a configured codebook used to feedback the predicted channel (i.e., same codebook that is used in inference for feedback), and the ground truth PMI calculated via a measured channel in a prediction window is also based on the same configured codebook. The configured codebook can be the same as a configured codebook for an inference result report (e.g., including type-1, type-2 and e-type 2, and Doppler codebook).
[0032] In another embodiment that calculates the predicted PMI based on the predicted channel, the predicted PMI is calculated based on a configured codebook that is separate from (i.e., different than) a configured codebook for an inference feedback codebook configuration. For example, the configured codebook for the predicted PMI can have a higher accuracy than the configured codebook for inference feedback.
[0033] In another embodiment that calculates the predicted PMI based on the predicted channel, when the predicted PMI is compressed using Al based CSI compression, the CSI prediction and CSI compression performance is monitored jointly (e.g., performance monitoring of chained Al models).
[0034] In certain embodiments where the prediction accuracy is based on the SGCS between a predicted PMI and a ground truth PMI, a UE uses a UE-side model to predict future PMI directly using past PMI as a model input. In one such embodiment, the predicted PMI is the eigen-vector (i.e., the Al model input is a past eigen-vector of the measurement window), and the ground truth PMI is the eigen-vector of the measured channel in the prediction window. In another embodiment, the predicted PMI is the configured codebook used to feedback the predicted channel, and the PMI calculated via measured channel in the prediction window is also the same configured codebook.
[0035] In certain embodiments, the prediction accuracy is based on the NMSE between the predicted channel and the measured channel in a prediction window. Such an embodiment may be used, for example, when the UE-side model predicts a future channel directly and the ground truth is the channel measurement in the prediction window.54916-3339-7133,1 P70868WO1
[0036] Type 1 Performance Monitoring Output
[0037] In certain embodiments, accuracy is defined by the percentage of a metric (e.g., SGCS or NMSE) that is below a predetermined threshold. In certain such embodiments, the network may configure an evaluation window with a predetermined default value (e.g.. indicated in a standard specification). When the UE determines multiple predicted PMI, the UE may either determine a separate metric for each predicted PMI within the evaluation window or determine an average metric for the predicted PMI within the evaluation window.
[0038] For example, FIG. 1 A and FIG. IB illustrate example CSI-RS set configurations for performance monitoring, according to embodiments herein. In the illustrated examples, at a monitoring periodicity 102, a UE measures CSI-RS 104 transmitted by a base station (e.g., gNB) within a measurement window 106 and uses the measurements and a UE-side AI / ML model to determine predicted CSI 110 and corresponding predicted PMI within a prediction window 108. To determine ground truth, the UE may also measure CSI-RS in the prediction window 108. The prediction window 108 is separated from the measurement window 106 by a gap DI and ends at a time D2 after the measurement window 106.
[0039] In FIG. 1 A, the UE is configured to determine two predicted PMIs and to calculate a first metric 114a for each of three instances of the first predicted PMI within the evaluation window 112 and a second metric 114b for each of three instances of the second predicted PMI within the evaluation window 112. Typically, a closer prediction has better prediction accuracy than a longer prediction. Thus, a separate threshold can be configured by the network for each predicted PMI. Each predicted PMI metric is counted within the evaluation window 112. In the illustrated example, per predicted PMI, two out of three SGCS metric calculations for the first metric 114a are lower than a first configured threshold (illustrated with an “X”), and the corresponding performance monitoring output 116 indicates a ‘‘fail” as a CSI prediction accuracy indicator (PAI) for the first predicted PMI (also illustrated with an “X”). On the other hand, three out of three SGCS metric calculations for the second metric 114b are higher than a second configured threshold (which may be the same as or different than the first configured threshold), and the corresponding performance monitoring output 118 indicates a “pass” as the CSI-PAI for the second predicted PMI. Thus, the report is for each predicted PMI.64916-3339-7133,1 P70868WO1
[0040] In FIG. IB. the UE is configured to determine an average metric 120 across multiple predicted PMIs in the evaluation window 112. The performance monitoring output 122 is based on the averaged SGCS below a threshold in the evaluation window 112. For example, one average metric 120 is calculated per monitoring instance (e.g., per prediction window 108). In the illustrated example, two out of the three average metric 120 in the evaluation window 112 is lower than the configured threshold (illustrated with an “X”). Thus, the performance monitoring output 122 is generated as a “faiF’ for all the predicted PMI within the evaluation window 112 (also illustrated with an “X”).
[0041] The illustrated examples in FIG. 1A and / or FIG. IB evaluate each monitoring instance / metric within the evaluation window. In certain embodiments, one threshold is configured for each metric. For example, if an SGCS threshold is 0.9, then the monitoring output indicates an error when one calculated metric is 0.8.
[0042] In other embodiments, a threshold is configured as a percentage of error within the evaluation window. For example, if an evaluation window includes three monitoring instances or metrics, then a second threshold of two means that when two out of three metrics have an error then monitoring output generates a negative output (i.e., indicating an error).
[0043] In other embodiments, the UE averages the metrics across the evaluation window and compares the average to one threshold configured by the network. For example, within an evaluation window with three metric values calculated as 0.9, 0.8 and 0.85, the average is 0.85. If the threshold configured by the network is 0.9, then 0.85<0.9 and the monitoring output is negative.
[0044] In certain embodiments, the monitoring output can be a binary value (e.g., 1 / 0 or Yes / No) or an output value (e.g., 0.85 or two out of three errors).
[0045] Periodic / Semi-Persistent Reporting
[0046] In some embodiments, performance monitoring Type 1, Type 2, and / or Type 3 may support reusing a CSI framework for configuration of a monitoring result report in Layer 1 (LI) signaling. In one such embodiment, one or more dedicated resource set(s) for monitoring and a report configuration for monitoring are configured in a dedicated CSI report configuration used for monitoring. An explicit linkage may be configured in the dedicated report to associate the performance monitoring report and the corresponding inference operation. For example, the inference report configuration identifier (ID) is associated in the report for monitoring. In addition, or in other74916-3339-7133,1 P70868WO1embodiments, the CSI-RS configuration may include an explicit link between the CSI-RS in the measurement window in the inference report and the CSI-RS in the prediction window in the monitoring report.
[0047] Other embodiments may use one or more joint resource sets and a report configuration for monitoring and inference reporting. Within the monitoring report configuration, the CSI-RS set(s) for the measurement window in inference and the CSI-RS set(s) for monitoring are configured. The report for performance monitoring and inference may also be configured.
[0048] In certain embodiments, a report quantity includes, for example, the metric, a monitoring output (i.e., result such as '‘pass” or “fail”), ground truth PMI, and / or other information in (e.g., in reportConfig) as discussed herein.
[0049] Example Aperiodic Reporting for Type 2 and Type 3 Monitoring
[0050] FIG. 2 illustrates an example of an aperiodic (AP) CSI report triggered by a downlink control information (DCI) trigger, according to embodiments herein. As shown, a UE measures CSI-RS 202 from base station (e g., gNB) in a measurement window and uses a UE-side AI / ML model to determine predicted CSI 204 in a prediction window. A DCI (i.e., in a physical downlink control channel (PDCCH)) triggers an AP CSI report and the corresponding AP CSI-RS transmission. Each DCI triggers a performance metric report 206 (e.g., SGCS, NMSE). The triggered monitoring report is an offset slot after the AP-CSI-RS resource in a time domain. The offset value is configurable in the CSI report.
[0051] Example Aperiodic Reporting for Type 1 Monitoring
[0052] FIG. 3 illustrates an example of a DCI triggering multiple AP CSI-RS resource set transmissions, according to embodiments herein. In particular. FIG. 3 shows the example CSI-RS set configuration for performance monitoring shown in FIG. 1 A, wherein for Type 1 performance monitoring where performance monitoring outputs 116, 118 is calculated based on multiple metrics 114a, 114b, a DCI can trigger multiple AP CSI-RS resource sets transmission and the corresponding report. Each DCI triggers one performance output report (results based on evaluation window 112). The triggered monitoring report may be offset in slot after the last AP CSI-RS resource in the time domain. In certain such embodiments, the offset value is configurable in the CSI report.
[0053] Example Event Driven Reporting for Type 1 Monitoring84916-3339-7133,1 P70868WO1
[0054] FIG. 4 illustrates an example of event driven reporting for an output of performance monitoring, according to embodiments herein. In particular. FIG. 4 shows the example CSI-RS set configuration for performance monitoring shown in FIG. 1A, wherein an event triggered report is used for the monitoring outputs 116, 118. As compared to FIG. 3, the example illustrated in FIG. 4 describes an event definition based on a performance monitoring output. In one embodiment (e.g., corresponding to Type 1 performance monitoring output discussed herein), the event is triggered when any monitoring output (i.e., the performance monitoring output 11 ) is below a configured threshold or all monitoring outputs are below a configured threshold (i.e., if both the performance monitoring output 116 and the performance monitoring output 118 are below the threshold value). In another embodiment, an event is defined as the monitoring output being below a configured threshold.
[0055] FIG. 5 is a flowchart of a method 500 of a UE, according to certain embodiments. In block 502, the method 500 includes receiving, at the UE from a base station, first configuration information for reporting a CSI prediction and second configuration information for a performance monitoring report, wherein the first configuration information is linked to the second configuration information by an inference report configuration ID. In block 504, the method 500 includes determining, at the UE, a non-predicted PMI based on one or more CSI reference signal measured by the UE in a prediction window. In block 506, the method 500 includes determining, using an AI / ML model at the UE, a predicted PMI based on the second configuration information and a CSI prediction performed by the UE using a channel measurement of the one or more CSI reference signal corresponding to the first configuration information. In block 508, the method 500 includes calculating, at the UE, a prediction accuracy value based on the non-predicted PMI and the predicted PMI. In block 510, the method 500 includes transmitting, from the UE to the base station based on the second configuration information, the performance monitoring report comprising the prediction accuracy value.
[0056] In certain embodiments of the method 500, the prediction accuracy value is based on an SGCS between the predicted PMI and the non-predicted PMI, and wherein the AI / ML model at the UE directly determines a predicted channel and calculates the predicted PMI based on the predicted channel. In certain such embodiments, the predicted PMI is calculated based on a configured codebook used in inference feedback94916-3339-7133,1 P70868WO1of the predicted channel, and wherein the non-predicted PMI is calculated via a measured channel in the prediction window using the configured codebook. In other embodiments, the predicted PMI is calculated based on a first configured codebook that is different than a second configured codebook used in inference feedback of the predicted channel.
[0057] In certain embodiments of the method 500, the prediction accuracy value is based on an SGCS between the predicted PMI and the non-predicted PMI, and the AI / ML model at the UE directly determines the predicted PMI using a past PMI as a model input. In certain such embodiments, the predicted PMI is based on a configured codebook used to feedback a predicted channel, and wherein the non-predicted PMI is calculated via a measured channel in the prediction window using the configured codebook.
[0058] FIG. 6 is a flowchart of a method 600 of a base station, according to certain embodiments. In block 602, the method 600 includes sending, to a UE from the base station, configuration information comprising first configuration information for reporting a CSI prediction and second configuration information for a performance monitoring report, wherein the first configuration information is linked to the second configuration information by an inference report ID. In block 604, the method 600 includes receiving, from the UE, the performance monitoring report comprising a prediction accuracy value. In block 606, the method 600 includes determining, based on the prediction accuracy value, a fallback decision indicating whether or not the UE is to provide CSI feedback using AI / ML inferencing. In block 608, the method 600 includes transmitting, from the base station the UE, the fallback decision.
[0059] In certain embodiments of the method 600, the prediction accuracy value is based on a non-PMI and a predicted PMI, the non-predicted PMI is based on one or more CSI reference signal measured at the UE in a prediction window, and the predicted PMI is generated by an AI / ML model at the UE based on the second configuration information and a CSI prediction performed by the UE using a channel measurement of the one or more CSI reference signal corresponding to the first configuration information.
[0060] In certain embodiments of the method 600, the prediction accuracy value is based on an SGCS between the predicted PMI and the non-predicted PMI, and the AI / ML model at the UE directly determines a predicted channel and calculates the104916-3339-7133,1 P70868WO1predicted PMI based on the predicted channel. In certain such embodiments, the predicted PMI is calculated based on a configured codebook used in inference feedback of the predicted channel, and the non-predicted PMI is calculated via a measured channel in the prediction window using the configured codebook. In other embodiments, the predicted PMI is calculated based on a first configured codebook that is different than a second configured codebook used in inference feedback of the predicted channel.
[0061] In certain embodiments of the method 600, the prediction accuracy value is based on an SGCS between the predicted PMI and the non-predicted PMI, and the AI / ML model at the UE directly determines the predicted PMI using a past PMI as a model input. In certain such embodiments, the predicted PMI is based on a configured codebook used to feedback a predicted channel, and wherein the non-predicted PMI is calculated via a measured channel in the prediction window using the configured codebook.
[0062] 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.
[0063] 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.
[0064] 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 as base station 712 and base station 714) that enable the connection 708 and connection 710.
[0065] 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.114916-3339-7133,1 P70868WO1
[0066] 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.
[0067] 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.
[0068] 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 to 5GC, 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).
[0069] 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 UE124916-3339-7133,1 P70868WO1702 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).
[0070] 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).
[0071] 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).
[0072] 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.
[0073] 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. The network device 818 may be, for example, a base station (e.g., an eNB or a gNB) of a wireless communication system.
[0074] 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 unit134916-3339-7133,1 P70868WO1(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.
[0075] 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.
[0076] 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.
[0077] 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 (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).
[0078] In certain embodiments having multiple antennas, the wireless device 802 may implement analog beamforming techniques, whereby phases of the signals sent by the144916-3339-7133,1 P70868WO1antenna(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).
[0079] 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).
[0080] The wireless device 802 may include an AI / ML performance monitoring module 816. The AI / ML performance monitoring module 816 may be implemented via hardware, software, or combinations thereof. For example, the AI / ML performance monitoring 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 AI / ML performance monitoring module 816 may be integrated within the processor(s) 804 and / or the transceiver(s) 810. For example, the AI / ML performance monitoring 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.
[0081] The AI / ML performance monitoring module 816 may be used for various aspects of the present disclosure. For example, the AI / ML performance monitoring module 816 may be configured to perform any of the UE-based methods discussed herein.
[0082] 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.
[0083] 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 (which154916-3339-7133,1 P70868WO1may 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.
[0084] 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.
[0085] 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.
[0086] 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, administration, and maintenance of the base station or other equipment operably connected thereto.
[0087] The network device 818 may include an AI / ML performance monitoring module 832. The AI / ML performance monitoring module 832 may be implemented via hardware, software, or combinations thereof. For example, the AI / ML performance monitoring 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 AI / ML performance monitoring module 832 may be integrated within the processor(s) 820 and / or the transceiver(s) 826. For example, the AI / ML performance monitoring 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.
[0088] The AI / ML performance monitoring module 832 may be used for various aspects of the present disclosure. For example, the AI / ML performance monitoring164916-3339-7133,1 P70868WO1module 832 may be configured to perform any of the network-based methods discussed herein.
[0089] Embodiments contemplated herein include an apparatus comprising means to perform one or more elements of any of the UE-based methods discussed herein. This apparatus may be. for example, an apparatus of a UE (such as a wireless device 802 that is a UE, as described herein).
[0090] 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 any of the UE-based methods discussed herein. This non-transitory computer-readable media may be, for example, a memory7of a UE (such as a memory 806 of a wireless device 802 that is a UE. as described herein).
[0091] Embodiments contemplated herein include an apparatus comprising logic, modules, or circuitry7to perform one or more elements of any of the UE-based methods discussed herein. This apparatus may be, for example, an apparatus of a UE (such as a wireless device 802 that is a UE, as described herein).
[0092] 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 any of the UE-based methods discussed herein. This apparatus may be, for example, an apparatus of a UE (such as a wireless device 802 that is a UE, as described herein).
[0093] Embodiments contemplated herein include a signal as described in or related to one or more elements of any of the UE-based methods discussed herein.
[0094] 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 carry7out one or more elements of any of the UE-based methods discussed herein. 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).
[0095] Embodiments contemplated herein include an apparatus comprising means to perform one or more elements of any of the network-based methods discussed herein.174916-3339-7133,1 P70868WO1This 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).
[0096] 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 any of the network-based methods discussed herein. This non-transitory 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).
[0097] Embodiments contemplated herein include an apparatus comprising logic, modules, or circuitry7to perform one or more elements of any of the network-based methods discussed herein. 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).
[0098] 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 any of the network-based methods discussed herein. 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).
[0099] Embodiments contemplated herein include a signal as described in or related to one or more elements of any of the network-based methods discussed herein.
[0100] 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 carry7out one or more elements of any of the network-based methods discussed herein. 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).
[0101] 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 184916-3339-7133,1 P70868WO1may 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.
[0102] 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.
[0103] 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.
[0104] 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.
[0105] 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.194916-3339-7133,1 P70868WO1
[0106] 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.204916-3339-7133,1 P70868WO1
Claims
1. CLAIMS1. A method of a user equipment (UE), comprising:receiving, at the UE from a base station, first configuration information for reporting a channel state information (CSI) prediction and second configuration information for a performance monitoring report, wherein the first configuration information is linked to the second configuration information by an inference report configuration identifier (ID);determining, at the UE, a non-predicted precoder matrix indicator (PMI) based on one or more CSI reference signal measured by the UE in a prediction window;determining, using an artificial intelligence or machine learning (AI / ML) model at the UE, a predicted PMI based on the second configuration information and a CSI prediction performed by the UE using a channel measurement of the one or more CSI reference signal corresponding to the first configuration information;calculating, at the UE, a prediction accuracy value based on the non-predicted PMI and the predicted PME andtransmitting, from the UE to the base station based on the second configuration information, the performance monitoring report comprising the prediction accuracy value.
2. The method of claim 1, wherein the prediction accuracy value is based on a squared generalized cosine similarity (SGCS) between the predicted PMI and the non-predicted PMI, and wherein the AI / ML model at the UE directly determines a predicted channel and calculates the predicted PMI based on the predicted channel.
3. The method of claim 2, wherein the predicted PMI is calculated based on a configured codebook used in inference feedback of the predicted channel, and wherein the nonpredicted PMI is calculated via a measured channel in the prediction window using the configured codebook.
4. The method of claim 2, wherein the predicted PMI is calculated based on a first configured codebook that is different than a second configured codebook used in inference feedback of the predicted channel.
5. The method of claim 1, wherein the prediction accuracy value is based on a squared generalized cosine similarity (SGCS) between the predicted PMI and the non-predicted 214916-3339-7133,1 P70868WO1PMI, and wherein the AI / ML model at the UE directly determines the predicted PMI using a past PMI as a model input.
6. The method of claim 5, wherein the predicted PMI is based on a configured codebook used to feedback a predicted channel, and wherein the non-predicted PMI is calculated via a measured channel in the prediction window using the configured codebook.
7. A method of a base station, comprising:sending, to a user equipment (UE) from the base station, configuration information comprising:first configuration information for reporting a channel state information (CSI) prediction; andsecond configuration information for a performance monitoring report, wherein the first configuration information is linked to the second configuration information by an inference report configuration identifier (ID);receiving, from the UE, the performance monitoring report comprising a prediction accuracy value;determining, based on the prediction accuracy value, a fallback decision indicating whether or not the UE is to provide CSI feedback using artificial intelligence or machine learning (AI / ML) inferencing; andtransmitting, from the base station the UE, the fallback decision.
8. The method of claim 7, wherein the prediction accuracy value is based on a nonpredicted precoder matrix indicator (PMI) and a predicted PMI, wherein the nonpredicted PMI is based on one or more CSI reference signal measured at the UE in a prediction window, and wherein the predicted PMI is generated by an AI / ML model at the UE based on the second configuration information and a CSI prediction performed by the UE using a channel measurement of the one or more CSI reference signal corresponding to the first configuration information.
9. The method of claim 8, wherein the prediction accuracy value is based on a squared generalized cosine similarity (SGCS) between the predicted PMI and the non-predicted PMI, and wherein the AI / ML model at the UE directly determines a predicted channel and calculates the predicted PMI based on the predicted channel.224916-3339-7133,1 P70868WO110. The method of claim 9, wherein the predicted PMI is calculated based on a configured codebook used in inference feedback of the predicted channel, and wherein the non-predicted PMI is calculated via a measured channel in the prediction window using the configured codebook.
11. The method of claim 9, wherein the predicted PMI is calculated based on a first configured codebook that is different than a second configured codebook used in inference feedback of the predicted channel.
12. The method of claim 8, wherein the prediction accuracy value is based on a squared generalized cosine similarity (SGCS) between the predicted PMI and the non-predicted PMI, and wherein the AI / ML model at the UE directly determines the predicted PMI using a past PMI as a model input.
13. The method of claim 12, wherein the predicted PMI is based on a configured codebook used to feedback a predicted channel, and wherein the non-predicted PMI is calculated via a measured channel in the prediction window using the configured codebook.
14. An apparatus for a user equipment (UE) comprising means to perform the method of any one of claim 1 to claim 6.
15. A computer-readable media comprising instructions to cause a user equipment (UE), upon execution of the instructions by one or more processors of the UE, to perform the method of any one of claim 1 to claim 6.
16. 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 6.
17. An apparatus for a base station comprising means to perform the method of any one of claim 7 to claim 13.
18. A computer-readable media comprising instructions to cause an base station, upon execution of the instructions by one or more processors of the base station, to perform the method of any one of claim 7 to claim 13.234916-3339-7133,1 P70868WO119. 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 7 to claim 13.
20. An apparatus comprising logic, modules, or circuitry to perform the method of any one of claim 1 to claim 13.244916-3339-7133,1 P70868WO1