Adaptive filtering and delay related measurements

Abstract

Systems, methods, apparatuses, and computer program products for positioning data densification. A method may include receiving, from a network element, an adaptive filtering configuration. The method may also include transmitting a request to the network element for updating the adaptive filtering configuration. The method may further include receiving, from the network element in response to the request, the updated adaptive filtering configuration.

Description

ADAPTIVE FILTERING AND DELAY RELATED MEASUREMENTSCROSS-REFERENCE TO RELATED APPLICATION

[0001] This application claims the benefit of US provisional application No. 63 / 703857, filed October 4, 2024. The content of which are hereby incorporated by reference in their entirety.FIELD:

[0002] Some example embodiments may generally relate to mobile or wireless telecommunication systems, such as Long Term Evolution (LTE) or fifth generation (5G) new radio (NR) access technology, or 5G beyond, or sixth generation (6G) access technology, or other communications systems. For example, certain example embodiments may relate to adaptive filtering and delay related measurements.BACKGROUND:

[0003] Examples of mobile or wireless telecommunication systems may include the Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access Network (UTRAN), Long Term Evolution (LTE) Evolved UTRAN (E-UTRAN), LTE-Advanced (LTE-A), MulteFire, LTE-A Pro, fifth generation (5G) radio access technology or new radio (NR) access technology and / or sixth generation (6G) radio access technology. Fifth generation (5G) and sixth generation (6G) wireless systems refer to the next generation (NG) of radio systems and network architecture. 5G and 6G network technology is mostly based on new radio (NR) technology, but the 5G / 6G (or NG) network can also build on E-UTRAN radio. It is estimated that NR may provide bitrates on the order of 10-20 Gbit / s or higher, and may support at least enhanced mobile broadband (eMBB) and ultra-reliable low-latency communication (URLLC) as well as massive machine-type communication (mMTC). NR is expected to deliver extreme broadband and ultra-robust, low-latency connectivity and massive networking to support the Internet of Things (loT).SUMMARY:

[0004] Some example embodiments may be directed to a method. The method may include receiving, from a network element, an adaptive filtering configuration. The method may also include reporting, to the network element, inference results, a measurement quantity information, an inference output, or a performance metric based on the adaptive filtering configuration. The method may further include receiving, from the network element, an updated adaptive filtering configuration.

[0005] Other example embodiments may be directed to an apparatus. The apparatus may include at least oneprocessor and at least one memory storing instructions. The instructions, when executed by the at least one processor, cause the apparatus at least to receive, from a network element, an adaptive filtering configuration. The apparatus may also be caused to report, to the network element, inference results, a measurement quantity information, an inference output, or a performance metric based on the adaptive filtering configuration. The apparatus may be caused to receive, from the network element, an updated adaptive filtering configuration.

[0006] Other example embodiments may be directed to an apparatus. The apparatus may include means for receiving, from a network element, an adaptive filtering configuration. The apparatus may also include means for reporting, to the network element, inference results, a measurement quantity information, an inference output, or a performance metric based on the adaptive filtering configuration. The apparatus may further include means for receiving, from the network element, an updated adaptive filtering configuration.

[0007] In accordance with other example embodiments, a non-transitory computer readable medium may be encoded with instructions that may, when executed in hardware, perform a method. The method may include receiving, from a network element, an adaptive filtering configuration. The method may also include reporting, to the network element, inference results, a measurement quantity information, an inference output, or a performance metric based on the adaptive filtering configuration. The method may further include receiving, from the network element, an updated adaptive filtering configuration.

[0008] Other example embodiments may be directed to a computer program product that performs a method. The method may include receiving, from a network element, an adaptive filtering configuration. The method may also include reporting, to the network element, inference results, a measurement quantity information, an inference output, or a performance metric based on the adaptive filtering configuration. The method may further include receiving, from the network element, an updated adaptive filtering configuration.

[0009] Other example embodiments may be directed to an apparatus that may include circuitry configured to receive, from a network element, an adaptive filtering configuration. The apparatus may also include circuitry configured to report, to the network element, inference results, a measurement quantity information, an inference output, or a performance metric based on the adaptive filtering configuration. The apparatus may further include circuitry configured to receive, from the network element, an updated adaptive filtering configuration.

[0010] Some example embodiments may be directed to a method. The method may include receiving, from a network element, an adaptive filtering configuration. The method may also include transmitting a request to the network element for updating the adaptive filtering configuration. The method may further include receiving, from the network element in response to the request, the updated adaptive filtering configuration.

[0011] Other example embodiments may be directed to an apparatus. The apparatus may include at least one processor and at least one memory storing instructions. The instructions, when executed by the at least one processor, cause the apparatus at least to receive, from a network element, an adaptive filtering configuration.The apparatus may also be caused to transmit a request to the network element for updating the adaptive filtering configuration. The apparatus may further be caused to receive, from the network element in response to the request, the updated adaptive filtering configuration.

[0012] Other example embodiments may be directed to an apparatus. The apparatus may include means for receiving, from a network element, an adaptive filtering configuration. The apparatus may also include means for transmitting a request to the network element for updating the adaptive filtering configuration. The apparatus may further include means for receiving, from the network element in response to the request, the updated adaptive filtering configuration.

[0013] In accordance with other example embodiments, a non-transitory computer readable medium may be encoded with instructions that may, when executed in hardware, perform a method. The method may include receiving, from a network element, an adaptive filtering configuration. The method may also include transmitting a request to the network element for updating the adaptive filtering configuration. The method may further include receiving, from the network element in response to the request, the updated adaptive filtering configuration.

[0014] Other example embodiments may be directed to a computer program product that performs a method. The method may include receiving, from a network element, an adaptive filtering configuration. The method may also include transmitting a request to the network element for updating the adaptive filtering configuration. The method may further include receiving, from the network element in response to the request, the updated adaptive filtering configuration.

[0015] Other example embodiments may be directed to an apparatus that may include circuitry configured to receive, from a network element, an adaptive filtering configuration. The apparatus may also include circuitry configured to transmit a request to the network element for updating the adaptive filtering configuration. The apparatus may further include circuitry configured to receive, from the network element in response to the request, the updated adaptive filtering configuration.

[0016] Some example embodiments may be directed to a method. The method may include transmitting, to a user equipment, an adaptive filtering configuration. The method may also include receiving, from the user equipment, inference results, a measurement quantity information, an inference output, or a performance metric based on the adaptive filtering configuration. The method may further include transmitting to the user equipment, an updated adaptive filtering configuration.

[0017] Other example embodiments may be directed to an apparatus. The apparatus may include at least one processor and at least one memory storing instructions. The instructions, when executed by the at least one processor, cause the apparatus at least to transmit, to a user equipment, an adaptive filtering configuration. Theapparatus may also be caused to receive, from the user equipment, inference results, a measurement quantity information, an inference output, or a performance metric based on the adaptive filtering configuration. The apparatus may further be caused to transmit to the user equipment, an updated adaptive filtering configuration.

[0018] Other example embodiments may be directed to an apparatus. The apparatus may include means for transmitting, to a user equipment, an adaptive filtering configuration. The apparatus may also include means for receiving, from the user equipment, inference results, a measurement quantity information, an inference output, or a performance metric based on the adaptive filtering configuration. The apparatus may further include means for transmitting to the user equipment, an updated adaptive filtering configuration.

[0019] In accordance with other example embodiments, a non-transitory computer readable medium may be encoded with instructions that may, when executed in hardware, perform a method. The method may include transmitting, to a user equipment, an adaptive filtering configuration. The method may also include receiving, from the user equipment, inference results, a measurement quantity information, an inference output, or a performance metric based on the adaptive filtering configuration. The method may further include transmitting to the user equipment, an updated adaptive filtering configuration.

[0020] Other example embodiments may be directed to a computer program product that performs a method. The method may include transmitting, to a user equipment, an adaptive filtering configuration. The method may also include receiving, from the user equipment, inference results, a measurement quantity information, an inference output, or a performance metric based on the adaptive filtering configuration. The method may further include transmitting to the user equipment, an updated adaptive filtering configuration.

[0021] Other example embodiments may be directed to an apparatus that may include circuitry configured to transmitting, to a user equipment, an adaptive filtering configuration. The method may also include receiving, from the user equipment, inference results, a measurement quantity information, an inference output, or a performance metric based on the adaptive filtering configuration. The method may further include transmitting to the user equipment, an updated adaptive filtering configuration.

[0022] Some example embodiments may be directed to a method. The method may include transmitting, to a user equipment, an adaptive filtering configuration. The method may also include receiving, from the user equipment based on the adaptive filtering configuration, a request for updating the adaptive filtering configuration. The method may further include transmitting, to the user equipment in response to the request, an updated adaptive filtering configuration.

[0023] Other example embodiments may be directed to an apparatus. The apparatus may include at least one processor and at least one memory storing instructions. The instructions, when executed by the at least one processor, cause the apparatus at least to transmit, to a user equipment, an adaptive filtering configuration. Theapparatus may also be caused to receive, from the user equipment based on the adaptive filtering configuration, a request for updating the adaptive filtering configuration. The apparatus may further be caused to transmit, to the user equipment in response to the request, an updated adaptive filtering configuration.

[0024] Other example embodiments may be directed to an apparatus. The apparatus may include means for transmitting, to a user equipment, an adaptive filtering configuration. The apparatus may also include means for receiving, from the user equipment based on the adaptive filtering configuration, a request for updating the adaptive filtering configuration. The apparatus may further include means for transmitting, to the user equipment in response to the request, an updated adaptive filtering configuration.

[0025] In accordance with other example embodiments, a non-transitory computer readable medium may be encoded with instructions that may, when executed in hardware, perform a method. The method may include transmitting, to a user equipment, an adaptive filtering configuration. The method may also include receiving, from the user equipment based on the adaptive filtering configuration, a request for updating the adaptive filtering configuration. The method may further include transmitting, to the user equipment in response to the request, an updated adaptive filtering configuration.

[0026] Other example embodiments may be directed to a computer program product that performs a method. The method may include transmitting, to a user equipment, an adaptive filtering configuration. The method may also include receiving, from the user equipment based on the adaptive filtering configuration, a request for updating the adaptive filtering configuration. The method may further include transmitting, to the user equipment in response to the request, an updated adaptive filtering configuration.

[0027] Other example embodiments may be directed to an apparatus that may include circuitry configured to transmit, to a user equipment, an adaptive filtering configuration. The apparatus may also include circuitry configured to receive, from the user equipment based on the adaptive filtering configuration, a request for updating the adaptive filtering configuration. The apparatus may further include circuity configured to transmit, to the user equipment in response to the request, an updated adaptive filtering configuration.BRIEF DESCRIPTION OF THE DRAWINGS:

[0028] For proper understanding of example embodiments, reference should be made to the accompanying drawings, wherein:

[0029] FIG. 1 illustrates a changing data function of reference signal received power (RSRP) error of beam prediction.

[0030] FIG. 2 illustrates an example signal flow diagram, according to certain example embodiments.

[0031] FIG. 3 illustrates an example signal flow diagram, according to certain example embodiments.

[0032] FIG. 4 illustrates an example signal flow diagram, according to certain example embodiments.

[0033] FIG. 5 illustrates an example flow diagram of a method, according to certain example embodiments.

[0034] FIG. 6 illustrates an example flow diagram of another method, according to certain example embodiments.

[0035] FIG. 7 illustrates an example flow diagram of another method, according to certain example embodiments.

[0036] FIG. 8 illustrates an example flow diagram of another method, according to certain example embodiments.

[0037] FIG. 9 illustrates a set of apparatuses, according to certain example embodiments.DETAILED DESCRIPTION:

[0038] It will be readily understood that the components of certain example embodiments, as generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. The following is a detailed description of some example embodiments of systems, methods, apparatuses, and computer program products for adaptive filtering and delay related measurements. For example, certain example embodiments may relate to adaptive filtering and delay related measurements for a user equipment-sided (UE-sided) model with performance monitoring.

[0039] The features, structures, or characteristics of example embodiments described throughout this specification may be combined in any suitable manner in one or more example embodiments. For example, the usage of the phrases “certain embodiments,” “an example embodiment,” “some embodiments,” or other similar language, throughout this specification refers to the fact that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment. Thus, appearances of the phrases “in certain embodiments,” “an example embodiment,” “in some embodiments,” “in other embodiments,” or other similar language, throughout this specification do not necessarily refer to the same group of embodiments, and the described features, structures, or characteristics may be combined in any suitable manner in one or more example embodiments. Further, the terms “base station”, “cell”, “node”, “gNB”, “network” or other similar language throughout this specification may be used interchangeably.

[0040] As used herein, “at least one of the following: ” and “at least one of ” and similar wording, where the list of two or more elements are joined by “and” or “or,” mean at least any one of the elements, or at least any two or more of the elements, or at least all the elements.

[0041] In the specifications of the 3rdGeneration Partnership Project (3GPP), artificial intelligence / machinelearning (AI / ML) beam management may include spatial domain beam prediction (BM-Case1) and time domain beam prediction (BM-Case2). BM-Case1 may include predicting the best Tx / Rx beams in different spatial locations, whereas BM-Case2 may include predicting the most likely beam to use for a next time instant(s).

[0042] For a user equipment-sided (UE-sided) model and network-sided (NW-sided) model, an AI / ML model may be trained under specific UE and NW configurations and scenarios. For instance, for a given trained model (e.g., UE-sided model or NW-sided model), if the input distribution has been changed such as, for example, when there is a measurement error, the AI / ML model may experience measurement error in an inference operation. The error may result in a low accuracy of inference output. Thus, during a performance monitoring phase, if model performance is not satisfactory, the NW may configure the UE to deactivate the channel state information report configuration (CSI-ReportConfig) or switch to another functionality (e.g., NW sends a new CSI- ReportConfig). Alternatively, the NW may configure the UE to switch back to a legacy operation when the predicted results are poor. Additionally, life cycle management (LCM) operations (e.g., deactivation / switch to other functionality or switch back to legacy operations) may be costly. Furthermore, when measurement error occurs, the errors may affect input distribution, the accuracy of predicted results may be low. Thus, certain example embodiments described herein may assist LCM operations including, for example, the NW does not need to configure the UE to switch to another CSI-ReportConfig, or switch back to legacy operations all the time.

[0043] According to certain example embodiments, the performance monitoring phase may refer to a process of tracking the behavior of the deployed AI / ML model. For instance, assuming that the AI / ML model is deployed, a UE may predict the best downlink (DL) transmission (TX) channel state information reference signal (CSI-RS) beam in a codebook of 64 using a subset of reference signal received power (RSRP) measurements (16) of that codebook. In the inference stage, the UE may measure the 16 RSRP values and predict the best CSI-RS beam in the superset, which reduces the number of measurements that the UE needs to perform by 75%. However, the UE may not have knowledge of whether the AI / ML model is making a good decision or a bad decision. Thus, in performing the monitoring phase / instance, the BS may transmit all CSI-RS beams, and the UE may measure all 64 RSRP values. The UE may also predict and calculate, with the 16 RSRP values, the performance of the AI / ML model by comparing with the ground truth (RSRP of all 64 beams) using a performance monitoring metric(s).

[0044] According to certain example embodiments, the performance monitoring metrics may include, but not limited to, for example: a beam prediction accuracy to find the rank of the strongest ground truth beam in the predicted strong set of beams; RSRP difference, where the RSRP difference is between the best ground truth beam and the predicted beam by the AI / ML model; and a threshold, which may be set to these matrices and used to decide whether the AI / ML model is doing well or not well.

[0045] As described herein, certain example embodiments may provide procedures for adaptive filtering configuration to assist in LCM operations, wherein the NW may configure the UE to perform a filtering operation before configuring the UE to deactivate the current CSI-ReportConfig or switch back to legacy operation mode. The adaptive filtering configuration may include a UE-specific sliding window size (e.g., M = 3) or time duration (e.g., 60 ms) where the UE averages the instantaneous RSRP measurements to obtain filtered RSRP. In certain example embodiments, when the input distribution has a measurement error during the inference phase, the RSRP error of beam prediction may become much lower with the help of L1 -filtering.

[0046] In L1 -filtering inputs may be measured a particular point such as, for example, point A. Exact filtering may be implementation dependent, and how the measurements are actually executed in the physical layer by an implementation may not be constrained by the standard (i.e., the model does not state a specific sampling rate or if the sampling is periodic or not). Instead, the standard specifies the performance object and reporting rate at point B in the model.

[0047] FIG. 1 illustrates a changing data function of RSRP error of beam prediction. For instance, the RSRP error of beam prediction may include an RSRP difference between the best DL transmission (TX) beam and the predicted DL TX beam. In the example of FIG. 1, AI / ML beam prediction may be considered for the case of Set B which is a subset of Set A, wherein Set B includes 8 beams, and Set A includes 32 beams, and the AI / ML model may predict the Top-1 beam ID in Set A for BM-Case1 (spatial domain beam prediction).

[0048] According to certain example embodiments, the AI / ML models may be trained with and without measurement error. Additionally, the error distribution may include, for example, a normal distributed error (AWGN sigma = -+~6 dB), which may be considered with input distribution.

[0049] As illustrated in FIG. 1 , the AI / ML models may be trained without error at input; however, during an inference phase, the AI / ML model may be impacted by measurement error, and other AI / ML models may be trained with an error at input. Additionally, the AI / ML model may have an impact of measurement error during the inference phase.

[0050] As further illustrated in FIG. 1 , the RSRP error of beam prediction (e.g., RSRP difference between the best DL TX beam and the predicted DL TX beam) may be significantly reduced when L1 -filtering is applied. For example, in one instance, L1 -filtering may be performed with a sliding window size 3 (measurements averaged over 3x40 ms).

[0051] In view of the drawbacks that may occur due to measurement error, certain example embodiments may enable the NW to configure the UE to apply L1 -filtering if the accuracy of a beam prediction output in terms of a performance metric. For example, L1 -filtering may be applied when the beam prediction accuracy is lower than an expected threshold, or an RSRP difference is higher than an expected threshold during a performancemonitoring operation.

[0052] According to certain example embodiments, for UE assisted performance monitoring, the UE may calculate a performance metric and trigger event-based UE-assisted performance monitoring. For example, event-based UE-assisted performance monitoring may be triggered when the prediction accuracy (e.g., beam prediction accuracy; finding the rank of the strongest ground truth beam ID in the predicted strong set of beams) is less than a predefined threshold, or the RSRP difference (e.g., RSRP gap between the best ground truth beam and the predicted beam by the AI / ML model) is greater than a predefined threshold. Additionally, the UE may send a request for more measurements to perform L1 -filtering. According to other example embodiments, a timeRestricitonForChannelMeasurements parameter may be extended in a CSI-ReportConfig to include the number of RSRP measurements related to L1 -filtering. For instance, in certain example embodiments, the NW may send the timeRestrictionForChannelMeasurements parameter in a CSI-ReportConfig message to configure L1 -filtering in radio resource control (RRC). In other example embodiments, the requirements in CSI-RS based L1-RSRP reporting may be enhanced. For example, the parameter to define the latest measurements (e.g., parameter) may be redefined when the timeREstrictionForChannelMeasurements parameter is configured for L1 -filtering in RRC.

[0053] FIG. 2 illustrates an example signal flow diagram, according to certain example embodiments. In particular, FIG. 2 illustrates NW-sided performance monitoring where the NW updates an adaptive filtering configuration to the UE. For example, the NW may configure L1 -filtering at the UE by, for example, configuring more measurements at the UE (e.g., configuring the UE to perform more measurements). In certain example embodiments, the UE may be configured to send predicted output. The predicted output may include, but not limited to, for example, predicted CRI, predicted SSBRI, or precited CRI, and predicted RSRP to NW. The NW may configure the UE to send measurements including, for example, a non-zero power CSI-RS (NZP-CSI-RS) resource set for measurements.

[0054] As illustrated in FIG. 1 , the NW may configure the UE with adapti ve_filteri ng_config (by default: no filter) in RRC configuration. Then, during the performance monitoring phase, the NW may check the predicted output with measured beams, and calculate a performance metric. If the calculated performance metric such as, for example, beam prediction accuracy, is lower than a threshold, or the L1-RSRP difference (e.g., filtered (L1- RSRP) difference between the best ground truth DL TX beam and the predicted best DL TX beam) is higher than a threshold, the NW may update the adaptive_filtering_config to the UE to apply L1 -filtering through a medium access control control element (MAC-CE) or RRC.

[0055] As illustrated in FIG. 2, at 210, the NW 205 transmits a configuration with CSI-ReportConfig_x to the UE 200 to enable the UE 200 to perform bream prediction (e.g., predicting a DL TX beam). At 215, the NW 205transmits a configuration with CSI-ReportConfig_y to the UE 200 instructing the UE 200 to report beam measurements to the NW 205. At 220, the NW 205 transmits a configuration to the UE 200 to enable the UE 200 to transmit reports of the beam prediction and beam measurement based on CSI-ReportConfig_x and CSI- ReportConfig_y. At 225, the NW 205 configures the UE 200 with an adaptive_filtering_configuration to enable the UE 200 to perform filtering operations before the UE 200 is configured to deactivate a current functionality (e.g., current CSI-ReportConfig), or switch back to performing operations under the legacy mode. According to certain example embodiments, rather than being configured with the adaptive filtering configuration, the UE 200 may be configured with a default configuration where no filter is applied. According to some example embodiments, the NW 205 may configure the UE 200 with the adaptive_filtering_config via RRC signaling.

[0056] At 230, the UE 200 performs an inference operation (e.g., running the trained model) of AI / ML BM with a default filtering configuration. The inference may correspond to feeding RSRP measurements into an AI / ML model to calculate the output (prediction) which is the strongest set of beams / RS / CRI IDs. Additionally, at 230, the AI / ML model inference may be performed for measurements which are not filtered, which is in contrast to 260 described below, where the AI / ML model inference is performed for RSRP measurements which were filtered. At 235, the UE 200 transmits a report of the quantity regarding inference results obtained at operation 230. In certain example embodiments, the inference results may include predicted-CRI and / or predicted RSRP. At 240, the UE 200 transmits a report of the measurement quantity to the NW 205. In certain example embodiments, the measurement quantity may include, for example, L1-RSRP of the whole Set A, or L1-RSRP of a subset of Set A.

[0057] At 245, the NW 205 carries out performance monitoring by determining a performance metric based on the measurement quantity report received from the UE 200. In certain example embodiments, the performance monitoring may be performed by determining a performance metric. The performance metric may include, for example, beam prediction accuracy, or an L1-RSRP difference. In certain example embodiments, if the beam prediction accuracy is lower than a threshold, or the L1-RSRP difference is higher than a threshold, the NW 205 may, at 250, determine filtering configurations for the UE 200, and may, at 255, update the adaptive_filtering_config to the UE 200 to apply L1 -filtering. According to certain example embodiments, the filtering configuration (e.g., adaptive filtering configuration) may include UE-specific sliding window size (e.g., M = 3) or time duration (e.g., 60 ms) where the UE averages the instantaneous RSRP measurements to obtain filtered RSRP. The update of the adaptive_filtering_config may be performed via MAC-CE or RRC.

[0058] At 260, the UE 200 performs another inference for AI / ML BM with the indicated filtering configuration (e.g., updated adaptive filtering configuration). At 265, the UE 200 transmits a quantity report to the NW 205 regarding the inference results from operation 260. According to certain example embodiments, the results may include, for example, predicted-CRI and / or predicted RSRP. At 270, the NW 205 transmits an indication to theUE 200 of a default filtering configuration. In other words, the NW 205 may disable the adaptive filtering performed at the UE 200 by configuring the UE 200 back to the default mode with no filter (e.g., no filtering is applied at the UE-side for RSRP measurements).

[0059] FIG. 3 illustrates an example signal flow diagram, according to certain example embodiments. In particular, FIG. 3 illustrates UE-assisted NW side performance monitoring where the UE 300 performs AI / ML beam prediction, and calculates a performance metric. As illustrated in FIG. 3, the UE may send the calculated performance metric (e.g., beam prediction accuracy, or L1-RSRP difference, hypothetical block error rate (BLER), or other metrics). The UE 300 may also compare the calculated performance metric with a predefined threshold, and report the event-based performance monitoring to the NW 305.

[0060] As illustrated in FIG. 3, operations 310-330 are similar to operations 210-230 in FIG. 2 and, thus, the description of operations 310-330 may be similar to that of operations 210-230. At 335, the UE 300 calculates a performance metric based on the inference AI / ML BM with a default filtering configuration. In certain example embodiments, the performance metric may include, for example, beam prediction accuracy, or an L1-RSRP difference. In certain example embodiments, if the beam prediction accuracy is lower than a threshold, or the L1-RSRP difference is higher than a threshold, other performance metrics (e.g., hypothetical BLER; metric different from the beam prediction accuracy or L1-RSRP difference) may be considered. At 340, the UE 300 transmits a report of event-based performance monitoring to the NW 305. Here, the UE 300 may send the performance monitoring report to the NW 305 if an event is detected in the UE side. For instance, an example event may be where the beam prediction accuracy is less than a threshold or the L1-RSRP difference is greater than a threshold (same conditions in operation 335). If the condition becomes true, the UE 300 may send the performance monitoring report. If the condition is not true, the UE 300 may not send any report.

[0061] At 345, the UE 300 triggers more measurement requests from the NW 305 to perform L1-RSRP filtering. The trigger may be initiated because the UE 300 knows of some performance degradation from operation 335. For example, the UE may ask / request the NW 305 for more measurements to calculate the performance metric and perform L1 -filtering with a sliding window. In certain example embodiments, the measurement request may be triggered via MAC-CE or RRC. In response to the trigger / request, at 350, the NW 305 determines filtering configurations for the UE 300, and may, at 355, update the adaptive_filtering_config to the UE 300 to apply L1- filtering. According to certain example embodiments, the update of the adaptive_filtering_config may be performed via MAC-CE or RRC.

[0062] At 360, the UE 300 performs another inference for AI / ML BM with the indicated filtering configuration (e.g., updated adaptive filtering configuration). At 365, the UE 300 transmits a quantity report to the NW 305 regarding the inference results from operation 360. According to certain example embodiments, the results mayinclude, for example, predicted-CRI and / or predicted RSRP. At 370, the UE 300 calculates a performance metric and checks the performance metric against a threshold. For example, the during the check, the UE 300 may determine if the beam prediction accuracy is greater than a threshold. If the beam prediction accuracy is greater than a threshold, it may be an indication of high accuracy. At 375, the UE 300 reports event-based performance monitoring to the NW 305. At 380, the NW 305 transmits an indication to the UE 300 of a default filtering configuration. In other words, the NW 305 may disable the adaptive filtering performed by the UE 300 by configuring the UE 300 back to the default mode with no filter.

[0063] FIG. 4 illustrates an example signal flow diagram, according to certain example embodiments. In particular, FIG. 4 illustrates UE-assisted NW side performance monitoring where the UE 400 may trigger more measurement requests if the performance metric is below a predefined threshold. However, in some example embodiments, it may be possible for the NW 405 to configure the UE 400 to apply L1 -filtering as well, if the UE 400 transmits the performance metric to the NW 405 and the NW 405 compares the performance metric with a threshold. As described herein, the performance metric may include, for example, bream prediction accuracy, or an L1-RSRP difference. Thus, in certain example embodiments, the NW 405 may configure the UE 400 to apply L1 -filtering when the beam prediction accuracy is less than a threshold. Additionally, when the beam prediction accuracy is less than a threshold, the NW 405 may update the adapti ve_fi Iteri n g_co nfig with L1 -filtering to the UE 400.

[0064] As illustrated in FIG. 4, operations 410-430 are similar to operations 210-230 in FIG. 2 and, thus, the description of operations 410-430 may be similar to that of operations 210-230. At 435, the UE 400 calculates a performance metric based on the inference AI / ML BM with a default filtering configuration from operation 430. At 440, the UE 400 transmits a report of an inference output and performance metric to the NW 405. At 445, the NW 405 evaluates the performance metric. For example, the NW 405 evaluates whether the beam prediction accuracy is less than a threshold or whether the L1-RSRP difference is greater than a threshold. At 450, if the performance metric is poor (e.g., after comparing the performance metric with the predefined threshold), the NW 405 determines filtering configurations for the UE 400, and may, at 455, update the adaptive_filtering_config to the UE 400 to apply L1 -filtering. According to certain example embodiments, the update of the adaptive_filtering_config may be performed via MAC-CE or RRC.

[0065] At 460, the UE 400 performs another inference for AI / ML BM with the indicated filtering configurationfe.g., updated adaptive filtering configuration). At 465, the UE 400 transmits a quantity report to the NW 405 regarding the inference results from operation 460. According to certain example embodiments, the results may include, for example, predicted-CRI and / or predicted RSRP. At 470, the UE 400 calculates a performance metric, and at 475, the UE 400 reports the inference from operation 465 and the performance metric calculated at operation 470 to the NW 405. At 480, the NW 405 transmits an indication to the UE 400 of a defaultfiltering configuration. In other words, the NW 305 may disable the adaptive filtering performed by the UE 500 by configuring the UE 300 back to the default mode with no filter.

[0066] In certain example embodiments, for BM-Case2, the UE may be capable of performing L1-RSRP measurements based on the configured CSI-RS resource for L1-RSRP computation. Additionally, the UE physical layer may be capable of reporting L1-RSRP measured over the measurement period ofr^Ll—RSRP_Measurement_Period_CSI—RS (ms). The Value T _R RP_Measurement_PeriOd_CSI—RS defined as shown in Table 1 :Table 1 : Measurement Period for FR2

[0067] As shown in Table 1 , the value of TL1-RSRP Measurement Period cS]-RSmay be defined for periodic and semi-persistent CSI-RS, where M=1 if the higher layer parameter timeRestrictionForChannelMeasurement is configured, and M=3 otherwise. When the UE is configured with the higher layer parameter L1 -filtering, M may be determined based on values provide din the higher layer parameter timeRestrictionForChannelMeasurement, where it also provides more measurements for L1 -filtering.

[0068] As shown in Table 1 , for aperiodic CSI-RS resources, if the UE is configured with the higher layer parameter L1 -filtering, M=1 , and otherwise, M may be determined based on values provided in the higher layer parameter timeRestrictionForChannelMeasurement, where it also provides more measurements for L1 -filtering.

[0069] FIG. 5 illustrates an example flow diagram of a method, according to certain example embodiments. In an example embodiment, the method of FIG. 5 may be performed by a network entity, or a group of multiple network elements in a 3GPP system, such as LTE or 5G-NR. For instance, in an example embodiment, the method of FIG. 5 may be performed by a UE, similar to one of apparatuses 10 or 20 illustrated in FIG. 9.

[0070] As illustrated in FIG. 5, the method may include, at 500 receiving, from a network element, an adaptive filtering configuration. The method may also include, at 505, reporting, to the network element, inference results,a measurement quantity information, an inference output, or a performance metric based on the adaptive filtering configuration. The method may further include, at 510, receiving, from the network element, an updated adaptive filtering configuration.

[0071] According to certain example embodiments, the adaptive filtering configuration may include a default filtering configuration. According to some example embodiments, the default filtering configuration indicates no filtering configuration is configured or applied. According to other example embodiments, the updated adaptive filtering configuration indicates more measurements for a layer-1 filtering need to be provided. According to further example embodiments, the adaptive filtering configuration or the updated adaptive filtering configuration comprises an indication indicating a number of measurements related to layer-1 filtering.

[0072] In certain example embodiments, the adaptive filtering configuration or the updated adaptive filtering configuration may be carried in a medium access control control element or a radio resource control. In some example embodiments, the method may further include performing an inference based on the updated adaptive filtering configuration. In other example embodiments, the method may include performing another inference based on the adaptive filtering configuration, and reporting, to the network element, inference results or a measurement quantity information.

[0073] According to certain example embodiments, the method may further include reporting a performance metric based on the default filtering configuration. According to some example embodiments, the method may also include reporting the performance metric based on the updated adaptive configuration. According to certain example embodiments, the performance metric may include a beam prediction accuracy or a layer-1 reference signal received power difference. According to further example embodiments, the inference results may include a predicted channel state information reference signal resource indicator or a predicted reference signal received power value, and the measurement quantity information may include a layer 1 reference signal received power of a set of beams, or a layer 1 reference signal received power of a subset of the set of beams.

[0074] FIG. 6 illustrates an example flow diagram of a method, according to certain example embodiments. In an example embodiment, the method of FIG. 6 may be performed by a network entity, or a group of multiple network elements in a 3GPP system, such as LTE or 5G-NR. For instance, in an example embodiment, the method of FIG. 6 may be performed by a UE, similar to one of apparatuses 10 or 20 illustrated in FIG. 9.

[0075] As illustrated in FIG. 6, the method may include, at 600, receiving, from a network element, an adaptive filtering configuration. The method may also include, at 605, transmitting a request to the network element for updating the adaptive filtering configuration. The method may further include, at 610, receiving, from the network element in response to the request, the updated adaptive filtering configuration.

[0076] According to certain example embodiments, the method may also include determining, based on theadaptive filtering configuration, a performance metric that is below a first threshold or above a second threshold. According to some example embodiments, the method may further include performing an inference based on the updated adaptive filtering configuration or the adaptive filtering configuration. According to other example embodiments, the adaptive filtering configuration comprises a default filtering configuration.

[0077] In certain example embodiments, the default filtering configuration indicates no filtering configuration is configured or applied. In some example embodiments, the updated adaptive filtering configuration indicates more measurements for a layer-1 filtering need to be provided. In other example embodiments, the adaptive filtering configuration or the updated adaptive filtering configuration may include an indication indicating a number of measurements related to layer-1 filtering. In further example embodiments, the adaptive filtering configuration or the updated adaptive filtering configuration may be carried in a medium access control control element or a radio resource control.

[0078] According to certain example embodiments, the request for updating the adaptive filtering configuration may be carried in a medium access control control element or a radio resource control. According to some example embodiments, the method may also include reporting, to the network element, inference results or a measurement quantity information from performing the inference. According to further example embodiments, the method may include reporting, to the network element, event-based performance monitoring.

[0079] FIG. 7 illustrates an example flow diagram of a further method, according to certain example embodiments. In an example embodiment, the method of FIG. 7 may be performed by a network entity, or a group of multiple network elements in a 3GPP system, such as LTE or 5G-NR. For instance, in an example embodiment, the method of FIG. 7 may be performed by a NW or gNB, similar to one of apparatuses 10 or 20 illustrated in FIG. 9.

[0080] As illustrated in FIG. 7, the method may include, at 700, transmitting, to a user equipment, an adaptive filtering configuration, The method may also include, at 705, receiving, from the user equipment, inference results, a measurement quantity information, an inference output, or a performance metric based on the adaptive filtering configuration. The method may further include, at 710, transmitting to the user equipment, an updated adaptive filtering configuration.

[0081] According to certain example embodiments, the method may also include determining, based on the inference results or the measurement quantity information, a performance metric. According to some example embodiments, the method may further include updating the adaptive filtering configuration based on whether the performance metric is below a first threshold or above a second threshold. According to other example embodiments, the adaptive filtering configuration may include a default filtering configuration. According to further example embodiments, under the default filtering configuration, no filtering is configured or applied.

[0082] In certain example embodiments, the updated filtering configuration may indicate more measurements for a layer-1 filtering need to be provided. In some example embodiments, the adaptive filtering configuration or the updated configured filtering configuration may include an indication indicating a number of measurements related to layer-1 filtering. In other example embodiments, the adaptive filtering configuration or the updated adaptive filtering configuration may be carried in a medium access control control element or a radio resource control. In further example embodiments, the method may also include receiving, from the user equipment, inference results , a measurement quantity information, an inference output or a performance metric after receiving the adaptive filtering configuration or the updated adaptive filtering configuration.

[0083] According to certain example embodiments, the inference results may include a predicted channel state information reference signal resource indicator or a predicted reference signal received power value. According to some example embodiments, the measurement quantity information may include a layer-1 reference signal received power of a set of beams, or a layer 1 reference signal received power of a subset of the set of beams. According to other example embodiments, the method may also include receiving, from the user equipment, another inference output and another performance metric.

[0084] FIG. 8 illustrates an example flow diagram of a further method, according to certain example embodiments. In an example embodiment, the method of FIG. 8 may be performed by a network entity, or a group of multiple network elements in a 3GPP system, such as LTE or 5G-NR. For instance, in an example embodiment, the method of FIG. 8 may be performed by a NW or gNB, similar to one of apparatuses 10 or 20 illustrated in FIG. 9.

[0085] As illustrated in FIG. 8, the method may include, at 800, transmitting, to a user equipment, an adaptive filtering configuration. The method may also include, at 805, receiving, from the user equipment based on the adaptive filtering configuration, a request for updating the adaptive filtering configuration. The method may further include, at 810, transmitting, to the user equipment in response to the request, an updated adaptive filtering configuration.

[0086] According to certain example embodiments, the method may also include determining, in response to the request, an adaptive filtering configuration. According to some example embodiments, the method may further include updating, in response to the request, the adaptive filtering configuration. According to other example embodiments, the adaptive filtering configuration may include a default filtering configuration. According to further example embodiments, the default filtering configuration may include no filtering configuration is configured or applied.

[0087] In certain example embodiments, the updated adaptive filtering configuration may indicate more measurements a layer-1 filtering need to be provided. In some example embodiments, the adaptive filteringconfiguration or the updated adaptive filtering configuration may include an indication indicating a number of measurements related to layer-1 filtering. In other example embodiments, the adaptive filtering configuration or the updated adaptive filtering configuration may be carried in a medium access control control element or a radio resource control. In further example embodiments, the request for updating the adaptive filtering configuration is carried in a medium access control control element or a radio resource control.

[0088] According to certain example embodiments, the method may also include receiving, from the user equipment, a report comprising inference results or a measurement quantity information after receiving the adaptive filtering configuration. According to some example embodiments, the inference results may include a predicted channel state information reference signal resource indicator or a predicted reference signal received power value. According to other example embodiments, the measurement quantity information may include a layer-1 reference signal received power of a set of beams, or a layer-1 reference signal received power of a subset of the set of beams.

[0089] FIG. 9 illustrates a set of apparatuses 10 and 20 according to certain example embodiments. In certain example embodiments, apparatuses 10 and 20 may be elements in a communications network or associated with such a network. For example, apparatus 10 may be a UE, or other similar radio communication computer device, and apparatus 20 may be a BS, gNB, LMF, network, or other similar computing device.

[0090] In some example embodiments, apparatuses 10 and 20 may include one or more processors, one or more computer-readable storage medium (for example, memory, storage, or the like), one or more radio access components (for example, a modem, a transceiver, or the like), and / or a user interface. In some example embodiments, apparatuses 10 and 20 may be configured to operate using one or more radio access technologies, such as GSM, LTE, LTE-A, NR, 5G, WLAN, WiFi, NB-loT, Bluetooth, NFC, MulteFire, and / or any other radio access technologies. It should be noted that one of ordinary skill in the art would understand that apparatuses 10 and 20 may include components or features not shown in FIG. 9.

[0091] As illustrated in the example of FIG. 9, apparatuses 10 and 20 may include or be coupled to a processor 12 and 22 for processing information and executing instructions or operations. Processors 12 and 22 may be any type of general or specific purpose processor. In fact, processors 12 and 22 may include one or more of general-purpose computers, special purpose computers, microprocessors, DSPs, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), and processors based on a multi-core processor architecture, as examples. While a single processor 12 and 22 is shown in FIG. 9, multiple processors may be utilized according to other example embodiments. For example, it should be understood that, in certain example embodiments, apparatuses 10 and 20 may include two or more processors that may form a multiprocessor system (e.g., in this case processors 12 may represent a multiprocessor) that may support multiprocessing.According to certain example embodiments, the multiprocessor system may be tightly coupled or loosely coupled (e.g., to form a computer cluster).

[0092] Processors 12 and 22 may perform functions associated with the operation of apparatuses 10 and 20 including, as some examples, precoding of antenna gain / phase parameters, encoding and decoding of individual bits forming a communication message, formatting of information, and overall control of the apparatuses 10 and 20, including processes and examples illustrated in FIGs. 1-8.

[0093] Apparatuses 10 and 20 may further include or be coupled to a memories 14 and 24 (internal or external), which may be respectively coupled to processors 12 and 24 for storing information and instructions that may be executed by processors 12 and 24. Memories 14 and 24 may be one or more memories and of any type suitable to the local application environment, and may be implemented using any suitable volatile or nonvolatile data storage technology such as a semiconductor-based memory device, a magnetic memory device and system, an optical memory device and system, fixed memory, and / or removable memory. For example, memories 14 and 24 can be comprised of any combination of random access memory (RAM), read only memory (ROM), static storage such as a magnetic or optical disk, hard disk drive (HDD), or any other type of non-transitory machine or computer readable media. The instructions stored in memories 14 and 24 may include program instructions or computer program code that, when executed by processors 12 and 22, enable the apparatuses 10 and 20 to perform tasks as described herein.

[0094] In certain example embodiments, apparatuses 10 and 20 may further include or be coupled to (internal or external) a drive or port that is configured to accept and read an external computer readable storage medium, such as an optical disc, USB drive, flash drive, or any other storage medium. For example, the external computer readable storage medium may store a computer program or software for execution by processors 12 and 22 and / or apparatuses 10 and 20 to perform any of the methods and examples illustrated in FIGs. 1-8.

[0095] In some example embodiments, apparatuses 10 and 20 may also include or be coupled to one or more antennas 15 and 25 for receiving a downlink signal and for transmitting via an UL from apparatuses 10 and 20. Apparatuses 10 and 20 may further include a transceivers 18 and 28 configured to transmit and receive information. The transceivers 18 and 28 may also include a radio interface (e.g., a modem) coupled to the antennas 15 and 25. The radio interface may correspond to a plurality of radio access technologies including one or more of GSM, LTE, LTE-A, 5G, NR, WLAN, NB-loT, Bluetooth, BT-LE, NFC, RFID, UWB, and the like. The radio interface may include other components, such as filters, converters (for example, digital-to-analog converters and the like), symbol demappers, signal shaping components, an Inverse Fast Fourier Transform (IFFT) module, and the like, to process symbols, such as OFDMA symbols, carried by a downlink or an UL.

[0096] For instance, transceivers 18 and 28 may be configured to modulate information on to a carrier waveformfor transmission by the antennas 15 and 25 and demodulate information received via the antenna 15 and 25 for further processing by other elements of apparatuses 10 and 20. In other example embodiments, transceivers 18 and 28 may be capable of transmitting and receiving signals or data directly. Additionally or alternatively, in some example embodiments, apparatus 10 may include an input and / or output device (I / O device). In certain example embodiments, apparatuses 10 and 20 may further include a user interface, such as a graphical user interface or touchscreen.

[0097] In certain example embodiments, memories 14 and 34 store software modules that provide functionality when executed by processors 12 and 22. The modules may include, for example, an operating system that provides operating system functionality for apparatuses 10 and 20. The memory may also store one or more functional modules, such as an application or program, to provide additional functionality for apparatuses 10 and 20. The components of apparatuses 10 and 20 may be implemented in hardware, or as any suitable combination of hardware and software. According to certain example embodiments, apparatuses 10 and 20 may optionally be configured to communicate each other (in any combination) via a wireless or wired communication links 70 according to any radio access technology, such as NR.

[0098] According to certain example embodiments, processors 12 and 22 and memories 14 and 24 may be included in or may form a part of processing circuitry or control circuitry. In addition, in some example embodiments, transceivers 18 and 28 may be included in or may form a part of transceiving circuitry.

[0099] For instance, in certain example embodiments, apparatus 10 may be controlled by memory 14 and processor 12 to receive, from a network element, an adaptive filtering configuration. Apparatus 10 may also be controlled by memory 14 and processor 12 to report, to the network element, inference results, a measurement quantity information, an inference output, or a performance metric based on the adaptive filtering configuration. Apparatus 10 may further be controlled by memory 14 and processor 12 to receive, from the network element, an updated adaptive filtering configuration.

[0100] For instance, in certain example embodiments, apparatus 10 may be controlled by memory 14 and processor 12 to receive, from a network element, an adaptive filtering configuration. Apparatus 10 may also be controlled by memory 14 and processor 12 to transmit a request to the network element for updating the adaptive filtering configuration. Apparatus 10 may further be controlled by memory 14 and processor 12 to receive, from the network element in response to the request, the updated adaptive filtering configuration.[O1O1] In other example embodiments, apparatus 20 may be controlled by memory 24 and processor 22 to transmit, to a user equipment, an adaptive filtering configuration. Apparatus 20 may also be controlled by memory 24 and processor 22 to receive, from the user equipment, inference results, a measurement quantity information, an inference output, or a performance metric based on the adaptive filtering configuration. Apparatus20 may further be controlled by memory 24 and processor 22 to transmit to the user equipment, an updated adaptive filtering configuration.

[0102] In other example embodiments, apparatus 20 may be controlled by memory 24 and processor 22 to transmit, to a user equipment, an adaptive filtering configuration. Apparatus 20 may also be controlled by memory 24 and processor 22 to receive, from the user equipment based on the adaptive filtering configuration, a request for updating the adaptive filtering configuration. Apparatus 20 may further be controlled by memory 24 and processor 22 to transmit, to the user equipment in response to the request, an updated adaptive filtering configuration.

[0103] In some example embodiments, an apparatus (e.g., apparatus 10 and / or apparatus 20) may include means for performing a method, a process, or any of the variants discussed herein. Examples of the means may include one or more processors, memory, controllers, transmitters, receivers, and / or computer program code for causing the performance of the operations.

[0104] Certain example embodiments may be directed to an apparatus that includes means for performing any of the methods described herein including, for example, means for receiving, from a network element, an adaptive filtering configuration. The apparatus may also include means for reporting, to the network element, inference results, a measurement quantity information, an inference output, or a performance metric based on the adaptive filtering configuration. The apparatus may further include means for receiving, from the network element, an updated adaptive filtering configuration.

[0105] Certain example embodiments may be directed to an apparatus that includes means for performing any of the methods described herein including, for example, means for receiving, from a network element, an adaptive filtering configuration. The apparatus may also include means for reporting, to the network element, inference results, a measurement quantity information, an inference output, or a performance metric based on the adaptive filtering configuration. The apparatus may further include means for receiving, from the network element, an updated adaptive filtering configuration.

[0106] Other example embodiments may be directed to an apparatus that includes means for performing any of the methods described herein including, for example, means for transmitting, to a user equipment, an adaptive filtering configuration. The apparatus may also include means for receiving, from the user equipment based on the adaptive filtering configuration, a request for updating the adaptive filtering configuration. The apparatus may further include means for transmitting, to the user equipment in response to the request, an updated adaptive filtering configuration.

[0107] Other example embodiments may be directed to an apparatus that includes means for performing any of the methods described herein including, for example, means for transmitting, to a user equipment, an adaptivefiltering configuration. The apparatus may also include means for receiving, from the user equipment based on the adaptive filtering configuration, a request for updating the adaptive filtering configuration. The apparatus may further include means for transmitting, to the user equipment in response to the request, an updated adaptive filtering configuration.

[0108] Certain example embodiments described herein provide several technical improvements, enhancements, and / or advantages. For instance, in some example embodiments, it may be possible to configure the UE to apply L1 -filtering with more measurements to significantly improve the accuracy of inference output. Additionally, the NW may not need to configure the UE with new CSI-ReportConfig (new functionality) or configure the UE to fallback to legacy operations.

[0109] A computer program product may include one or more computer-executable components which, when the program is run, are configured to carry out some example embodiments. The one or more computerexecutable components may be at least one software code or portions of it. Modifications and configurations required for implementing functionality of certain example embodiments may be performed as routine(s), which may be implemented as added or updated software routine(s). Software routine(s) may be downloaded into the apparatus.

[0110] As an example, software or a computer program code or portions of it may be in a source code form, object code form, or in some intermediate form, and it may be stored in some sort of carrier, distribution medium, or computer readable medium, which may be any entity or device capable of carrying the program. Such carriers may include a record medium, computer memory, read-only memory, photoelectrical and / or electrical carrier signal, telecommunications signal, and software distribution package, for example. Depending on the processing power needed, the computer program may be executed in a single electronic digital computer or it may be distributed amongst a number of computers. The computer readable medium or computer readable storage medium may be a non-transitory medium.

[0111] In other example embodiments, the functionality may be performed by hardware or circuitry included in an apparatus (e.g., apparatus 10 or apparatus 20), for example through the use of an application specific integrated circuit (ASIC), a programmable gate array (PGA), a field programmable gate array (FPGA), or any other combination of hardware and software. In yet another example embodiment, the functionality may be implemented as a signal, a non-tangible means that can be carried by an electromagnetic signal downloaded from the Internet or other network.

[0112] According to certain example embodiments, an apparatus, such as a node, device, or a corresponding component, may be configured as circuitry, a computer or a microprocessor, such as single-chip computer element, or as a chipset, including at least a memory for providing storage capacity used for arithmetic operationand an operation processor for executing the arithmetic operation.

[0113] One having ordinary skill in the art will readily understand that the disclosure as discussed above may be practiced with procedures in a different order, and / or with hardware elements in configurations which are different than those which are disclosed. Therefore, although the disclosure has been described based upon these example embodiments, it would be apparent to those of skill in the art that certain modifications, variations, and alternative constructions would be apparent, while remaining within the spirit and scope of example embodiments. Although the above embodiments refer to 5G NR and LTE technology, the above embodiments may also apply to any other present or future 3GPP technology, such as LTE-advanced, and / or fourth generation (4G) technology.

[0114] Partial Glossary:

[0115] 3GPP 3rd Generation Partnership Project

[0116] 5G 5th Generation

[0117] 5GCN 5G Core Network

[0118] 5GS 5G System

[0119] BS Base Station

[0120] CDF Charging Data Function

[0121] CDR Charging Data Record

[0122] CGF Charging Gateway Function

[0123] DL Downlink

[0124] eNB Enhanced Node B

[0125] E-UTRAN Evolved UTRAN

[0126] gNB 5G or Next Generation NodeB

[0127] LTE Long Term Evolution

[0128] NR New Radio

[0129] PRS Positioning Reference Signal

[0130] RSRP Reference Signal Received Power

[0131] UE User Equipment

[0132] UL Uplink

Claims

23CLAIMS1. An apparatus, comprising: at least one processor; and at least one memory storing instructions, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: receive, from a network element, an adaptive filtering configuration; transmit a request to the network element for updating the adaptive filtering configuration; and receive, from the network element in response to the request, the updated adaptive filtering configuration.

2. The apparatus according to claim 1 , wherein the at least one memory stores instructions that when executed by the at least one processor, further cause the apparatus at least to: determine, based on the adaptive filtering configuration, a performance metric that is below a first threshold or above a second threshold.

3. The apparatus according to claims 1 or 2, wherein the at least one memory stores instructions that when executed by the at least one processor, further cause the apparatus at least to: perform an inference based on the updated adaptive filtering configuration or the adaptive filtering configuration.

4. The apparatus according to any of claims 1-3, wherein the adaptive filtering configuration comprises a default filtering configuration.

5. The apparatus according to claims 4, wherein the default filtering configuration indicates no filtering configuration is configured or applied.

6. The apparatus according to any of claims 1-5, wherein the updated adaptive filtering configuration indicates more measurements for a layer-1 filtering need to be provided.

7. The apparatus according to any of claims 1 -6, wherein the adaptive filtering configuration or the updated adaptive filtering configuration comprises an indication indicating a number of measurements related to layer-1 filtering.

8. The apparatus according to any of claims 1 -7, wherein the adaptive filtering configuration or the updated adaptive filtering configuration is carried in a medium access control control element or a radio resource control.

9. The apparatus according to any of claims 1-8, wherein the request for updating the adaptive filtering configuration is carried in a medium access control control element or a radio resource control.

10. The apparatus according to any of claims 1-9, wherein the at least one memory stores instructions that when executed by the at least one processor, further cause the apparatus at least to: report, to the network element, inference results or a measurement quantity information from performing the inference.11 . The apparatus according to any of claims 1 -10, wherein the at least one memory stores instructions that when executed by the at least one processor, further cause the apparatus at least to: report, to the network element, event-based performance monitoring.

12. A apparatus, comprising: at least one processor; and at least one memory storing instructions, wherein the instructions, when executed by the at least one processor, cause the apparatus at least to: transmit, to a user equipment, an adaptive filtering configuration; receive, from the user equipment based on the adaptive filtering configuration, a request for updating the adaptive filtering configuration; and transmit, to the user equipment in response to the request, an updated adaptive filtering configuration.

13. The apparatus according to claim 12, wherein the at least one memory stores instructions that when executed by the at least one processor, further cause the apparatus at least to: determine, in response to the request, an adaptive filtering configuration; and update, in response to the request, the adaptive filtering configuration.

14. The apparatus according to claims 12 or 13, wherein the adaptive filtering configuration comprises a default filtering configuration.

15. The apparatus according to claim 14, wherein the default filtering configuration indicates no filtering configuration is configured or applied.

16. The apparatus according to any of claims 12-15, wherein the updated adaptive filtering configuration indicates more measurements a layer-1 filtering need to be provided.

17. The apparatus according to any of claims 12-16, wherein the adaptive filtering configuration or the updated adaptive filtering configuration comprises an indication indicating a number of measurements related to layer-1 filtering.

18. The apparatus according to any of claims 12-17, wherein the adaptive filtering configuration or the updated adaptive filtering configuration is carried in a medium access control control element or a radio resource control.

19. The apparatus according to any of claims 12-18, wherein the request for updating the adaptive filtering configuration is carried in a medium access control control element or a radio resource control.

20. The apparatus according to any of claims 12-19, wherein the at least one memory stores instructions that when executed by the at least one processor, further cause the apparatus at least to: receive, from the user equipment, a report comprising inference results or a measurement quantity information after receiving the adaptive filtering configuration.21 . The apparatus according to claim 20, wherein the inference results comprise a predicted channel state information reference signal resource indicator or a predicted reference signal received power value, and wherein the measurement quantity information comprises a layer-1 reference signal received power of a set of beams, or a layer-1 reference signal received power of a subset of the set of beams.

22. A method, comprising: receiving, from a network element, an adaptive filtering configuration; transmitting a request to the network element for updating the adaptive filtering configuration; and receiving, from the network element in response to the request, the updated adaptive filtering configuration.2623. A method, comprising: transmitting, to a user equipment, an adaptive filtering configuration; receiving, from the user equipment based on the adaptive filtering configuration, a request for updating the adaptive filtering configuration; and transmitting, to the user equipment in response to the request, an updated adaptive filtering configuration.

Images