Methods and apparatus for ai / ml based bfr enhancements

Abstract

This paper describes systems and methods for using various artificial intelligence (AI) / machine learning (ML) models to assess block error rate (BLER). The generation and use of BLER predictions, as well as the prediction of Layer 1 (L1) reference signal received power (RSRP) for candidate reference signals, are discussed. Various examples of inputs that can be used with these ML models are presented. The predicted block error rate (BFD) can be reported to network nodes based on the AL / ML model before the actual BFD.

Description

Technical Field

[0001] This application relates in general to wireless communication systems, including wireless communication systems capable of performing block error rate prediction. Background Technology

[0002] Wireless mobile communication technologies use various standards and protocols to transmit data between base stations and wireless communication devices. For example, wireless communication system standards and protocols may include, for instance, 3GPP Long Term Evolution (LTE) (e.g., 4G), 3GPP New Radio (NR) (e.g., 5G), and the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standard for Wireless Local Area Networks (WLANs) (often referred to as Wi-Fi within the industry organization). ® ).

[0003] As envisioned by 3GPP, different wireless communication system standards and protocols can use various radio access networks (RANs) for communication between RAN base stations (sometimes also commonly referred to as RAN nodes, network nodes, or simply nodes) and wireless communication equipment called user equipment (UEs). 3GPP RANs can include, for example, Global System for Mobile Communications (GSM), Enhanced Data Rate GSM Evolution (EDGE) RAN (GERAN), Universal Terrestrial Radio Access Network (UTRAN), Evolved Universal Terrestrial Radio Access Network (E-UTRAN), and / or Next Generation Radio Access Network (NG-RAN).

[0004] Each RAN can use one or more Radio Access Technologies (RATs) to perform communication between the base station and the UE. For example, GERAN implements the GSM and / or EDGE RAT, UTRAN implements the Universal Mobile Telecommunications System (UMTS) RAT or other 3GPP RATs, E-UTRAN implements the LTE RAT (sometimes simply referred to as LTE), and NG-RAN implements the NR RAT (this NR RAT is sometimes referred to herein as the 5G RAT, 5G NR RAT, or simply NR). In some deployments, E-UTRAN may also implement the NR RAT. In some deployments, NG-RAN may also implement the LTE RAT.

[0005] The base stations used by a RAN can correspond to that RAN. An example of an E-UTRAN base station is an Evolved Universal Terrestrial Radio Access Network (E-UTRAN) Node B (also commonly referred to as Evolved Node B, Enhanced Node B, eNodeB, or eNB). An example of an NG-RAN base station is a Next Generation Node B (sometimes also called gNode B or gNB).

[0006] The RAN provides communication services to external entities through its connection with the core network (CN). For example, E-UTRAN can utilize the evolved packet core (EPC), while NG-RAN can utilize the 5G core network (5GC).

[0007] 5G NR frequency bands can be divided into two or more distinct frequency ranges. For example, Frequency Range 1 (FR1) may include bands operating at frequencies below 6 GHz, some of which are available for previous standards and can potentially be extended to cover new spectrum offerings from 410 MHz to 7125 MHz. Frequency Range 2 (FR2) may include bands from 24.25 GHz to 52.6 GHz. It should be noted that in some systems, FR2 may also include bands from 52.6 GHz to 71 GHz (or higher). Bands in the millimeter-wave (mmWave) range of FR2 may have smaller coverage areas but potentially higher available bandwidth than bands in FR1. Those skilled in the art will recognize that these frequency ranges, presented by way of example, may change over time or in different regions. Attached Figure Description

[0008] To facilitate the identification of any particular element or action in the discussion, one or more of the most significant digits in the figure reference numerals refer to the figure number in which the element was first introduced.

[0009] Figure 1 Example frameworks for using AI and / or ML in wireless communication system environments are illustrated according to some implementation schemes.

[0010] Figure 2A Two timelines for beam fault detection procedures are illustrated according to some implementation schemes.

[0011] Figure 2B The table illustrates configurations for different frequency ranges.

[0012] Figure 3A A flowchart of a BFR for a primary cell (PCell) is illustrated according to some implementation schemes.

[0013] Figure 3B A flowchart of a BFR for a secondary cell (SCell) is illustrated according to some implementation schemes.

[0014] Figure 4A An example of a legacy implementation of the BFR according to some implementation schemes is shown.

[0015] Figure 4B Examples are shown where, according to some implementation schemes, a UE can use AI / ML to predict BFD before it occurs.

[0016] Figure 4C Examples of implementations are illustrated, in which the UE can use AI / ML to predict some BFIs after detecting one or more real BFIs.

[0017] Figure 5 An example flowchart of a UE-side process for BFD prediction, as illustrated in the embodiments of this document, is provided.

[0018] Figure 6A An example is shown where the UE is configured to perform BLER prediction at a future time.

[0019] Figure 6B An example is shown where the UE is configured to predict the BLER value of the RS based on samples from another BFD-RS.

[0020] Figure 6C An example is illustrated where, according to some implementation schemes, a UE is configured to predict the BLER value of a BFD-RS set for a TRP point based on the actual values ​​of one or more BFD-RS sets for other TRP points in a multi-TRP scenario.

[0021] Figure 6D An example of AI / ML block diagram 618 for predicting BLER values ​​is shown.

[0022] Figure 7 Two example triggered events are illustrated using BLER prediction for event triggering according to some implementation schemes.

[0023] Figure 8A Example timelines are shown for triggering BFD using predicted BLER according to some implementation schemes.

[0024] Figure 8B Example timelines are shown for triggering BFD using a certain actual BLER and a certain predicted BLER according to some implementation schemes.

[0025] Figure 9A Example BFRs with an octet Ci field and truncated BFR MAC CEs are illustrated according to some implementation schemes.

[0026] Figure 9B Example BFRs with an octet Ci field and truncated BFR MAC CEs are illustrated according to some implementation schemes.

[0027] Figure 10 Examples of UE methods according to some implementation schemes are provided.

[0028] Figure 11 The methods for network nodes according to some implementation schemes are illustrated.

[0029] Figure 12 An example architecture of a wireless communication system according to the implementation scheme disclosed herein is illustrated.

[0030] Figure 13 A system for performing signaling transfer between a wireless device and a network device according to an embodiment disclosed herein is illustrated. Detailed Implementation

[0031] Various implementations are described with respect to the UE. However, references to the UE are provided for illustrative purposes only. The example implementations can be used with any electronic components that can establish a connection to a network and utilize hardware, software, and / or firmware configurations for exchanging information and data with the network. Therefore, the UE as described herein is used to represent any suitable electronic component.

[0032] Frameworks for Artificial Intelligence / Machine Learning in Wireless Communication Systems Figure 1 An example framework 100 for using AI and / or ML in a wireless communication system environment is illustrated. The discussion in this paper involves the use of AI / ML models (sometimes referred to simply as "models" in this paper).

[0033] Framework 100 includes data collection functionality 102, model training functionality 104, management functionality 106, inference / prediction functionality 108, and model storage functionality 110.

[0034] As shown in the figure, the data collection function 102 can provide training data 112 to the model training function 104, monitoring data 114 to the management function 106, and / or inference / prediction data 116 to the inference / prediction function 108. The model training function 104 can provide trained / updated model signaling 124 to the model storage function 110. The management function 106 can provide performance feedback / retraining request signaling 122 to the model training function 104, model transfer / delivery request signaling 128 to the model storage function 110, and / or selection / (de)activation / toggle / rollback signaling 120 to the inference / prediction function 108. The inference / prediction function 108 can provide output monitoring signaling 118 to the management function 106. The model storage function 110 can provide model transfer / delivery / transfer delivery signaling 126 to the inference / prediction function 108.

[0035] In framework 100, an AI / ML model can be trained at model training function 104 based on training data 112 received from data collection function 102. Once trained, the model can be provided to model storage function 110.

[0036] When the model is to be used, it is provided from the model storage functionality 110 to the inference / prediction functionality 108. The data collection functionality 102 may also provide inference / prediction data 116 (e.g., input data) to the inference / prediction functionality 108. The inference / prediction functionality 108 can then perform inference by applying the inference / prediction data 116 to the model. This inference may be reported to functionalities outside the framework 100 for further use.

[0037] The management function 106 manages the overall operation of the framework 100. Management decisions may be based on monitoring data 114 received at the management function 106 from the data collection function 102 and / or output monitoring signaling 118 received from the inference / prediction function 108. The management function 106 may, for example, provide training data 112 to the model training function 104 to notify the model training function 104 of the performance of the trained model and / or request retraining of the current model. The management function 106 may, for example, provide model transfer / delivery request signaling 128 to the model storage function 110 to control the transfer to the inference / prediction function 108 and the use of the model at the inference / prediction function. The management function 106 may, for example, control the inference / prediction function 108 by selecting / (de)activating / toggling / rollback signaling 120 to indicate the model to be used and / or the method of using the current model, etc.

[0038] Use cases of artificial intelligence / machine learning in wireless communication systems Regarding wireless communication systems, various use cases have been identified for studying useful applications of AI / ML models in categories related to physical layer (PHY) considerations. One such case is investigating the use of AI / ML models in channel state information (CSI) feedback environments with the aim of achieving CSI feedback enhancement. For example, CSI timing prediction using AI / ML models could be considered.

[0039] Another scenario involves beam management considerations. For example, layer 1 (L1) beam temporal / spatial prediction using AI / ML models could be considered.

[0040] Another scenario involves enhancing localization accuracy through the use of AI / ML models.

[0041] Regarding the use of AI / ML within wireless communication systems, various possible levels of UE / base station cooperation exist. For example, in some cases, there may be no cooperation between the UE and the base station regarding the use of ML models. In other cases, there may be signaling-based cooperation between the UE and the base station, but no ML model transfer between the base station and the UE (in which case auxiliary information may be used for ML model selection purposes, for example). In still other cases, there may be signaling-based cooperation between the UE and the base station, which includes the transfer of ML models used between the UE and the base station. At least some of the embodiments discussed herein apply to, for example, signaling-based cooperation scenarios (with or without model transfer).

[0042] Proposals for wireless communication systems may involve situations using AI / ML to enhance mobility. These situations can be divided into various sub-topics. For example, a first such sub-topic could be about AI / ML-based radio resource management (RRM) predictions, such as predictions of future L1 and / or Layer 3 (L3) measurements based on historical measurements. In such cases, the intention might be to reduce UE measurement workload and / or reduce latency in triggering measurement events.

[0043] In another example, another such sub-topic could be about AI / ML-based target cell selection, such as predicting and notifying the network which cell and / or beam and / or when to handover. In such cases, the intention might be to allow the UE not to report all its locally useful observations about the handover to the network, thereby helping the UE stay within given power and / or memory and / or privacy constraints.

[0044] In another example, another subtopic could be about AI / ML-based fault avoidance, such as predicting and notifying the network of potential future radio link failures (RLF) / handover failures (HOF). In such cases, the intention might be to enable the network to proactively avoid RLFs, rather than reacting only after an RLF has occurred (based on some existing passive mechanisms).

[0045] Other use cases for beneficial applications of AI / ML include, but are not limited to, AI / ML-based UE trajectory prediction, AI / ML-based discontinuous reception (DRX) adaptation, AI / ML-based slicing / QoE mechanisms, and / or AI / ML-based cell reselection mechanisms.

[0046] Therefore, it can be seen that there are multiple proposals to explore AI / ML-based mobility enhancement. This paper discusses details of various implementation schemes for such AI / ML-based mobility enhancement.

[0047] In some implementations described herein, the UE may use an ML model trained at the UE based on its mobility and mobility-related information. In some cases, the UE may inform the network of its predictions of the optimal target cell and / or beam for a regular HO (House of Interest) based on its use of the ML model. In some cases, the UE may inform the network of its predictions of a list of candidate cells for a Conditional Handover (CHO) recommendation / rejection based on its use of the ML model. In some cases, the UE may be able to predict an impending RLF (Restricted Life Failure) based on its use of the ML model and notify the network in advance.

[0048] Furthermore, Beam Failure Recovery (BFR) has been introduced in NR for coverage enhancement. Some implementations described in this paper involve using AI / ML to enhance BFR. For example, a UE can use AI / ML to enhance BFR.

[0049] Beam Fault Detection (BFD) Figure 2A Two timelines (first timeline 202 and second timeline 204) are illustrated for the beam fault detection process. For various wireless systems, beam fault detection can be considered as a combined Layer 1 / Layer 2 (L1 / L2) process.

[0050] L1 provides a Media Access Control (MAC) layer indication of a Beam Failure Instance (BFI). If the assumed block error rate (BLER) of the Physical Downlink Control Channel (PDCCH) is worse than the threshold Qout (i.e., q0) for resources in the resource set configured for BFD, L1 triggers the Beam Failure Indication (BFI) and transmits it to the MAC.

[0051] In some cases, both the synchronization signal block (SSB) and the CSI reference signal (RS) can be configured in q0, where the maximum possible number of q0 is relative to each frequency range. For example, Figure 2B Table 206 illustrates configurations indicating different frequency ranges. As shown, in the first frequency range 208 (e.g., FR1 less than or equal to 3 GHz), the maximum number L of candidate SSBs per half-frame is... max It can be 4, and the maximum number (N) of Radio Link Monitoring Reference Signal (RLM-RS) resources. RLM The maximum number of candidate SSBs per half-frame is 2. In the second frequency range 210 (e.g., FR1 greater than 3 GHz), L max It can be 8, and the maximum number (N) of Radio Link Monitoring Reference Signal (RLM-RS) resources. RLM The maximum number of candidate SSBs per half-frame is 4. In the third frequency range 212 (e.g., FR2), L maxIt can be 64, and the maximum number (N) of Radio Link Monitoring Reference Signal (RLM-RS) resources. RLM () can be 8.

[0052] Furthermore, in some cases, q0 can be explicitly configured in Radio Resource Control (RRC), or if q0 is not configured in RRC, it can be implicitly determined by the Transmit Configuration Indication (TCI) status of the active PDCCH. In some such cases, the two BFD-RS sets can be configured in Multiple Transmit / Receive Point (TRP) Beam Failure Recovery (BFR).

[0053] Returning to the BFD, which is considered an L1 / L2 process, in some wireless systems, the MAC layer starts a timer once it receives a BFI, and the MAC layer increments the counter by 1 for each BFI. In some cases, if no beam fault instance is received at the MAC and the timer expires, the MAC layer can reset BFI_COUNTER and assume that no beam fault instance exists. For example, in Figure 2A In the second timeline 204, the first BFI is received and the counter is set to 1. Then, the timer expires and the count is reset to 0. In other cases, when a certain threshold of the BFI is reached, for example, when BFI_COUNTER is greater than or equal to beamFailureInstanceMaxCount, the MAC can trigger a beam failure and initiate a recovery process. For example, in Figure 2A In the first timeline 202, multiple BFIs are received. When the count reaches a threshold, the MAC can trigger a beam fault and initiate a recovery process.

[0054] Beam Fault Recovery (BFR) In some wireless systems, in the case of beam failure recovery (BFR), the UE is configured with a set of resources (q1) for the recovery process in BeamFailureRecoveryConfig. When the L1 reference signal received power (RSRP) of any resource in q1 is greater than a threshold (e.g., Qin_LR), the PHY layer can transmit the corresponding resource index to the MAC layer.

[0055] Figure 3AA flowchart 302 for BFR for a primary cell (PCell) is illustrated according to some implementation schemes. For PCell BFR, UE 304 may perform a random access channel (RACH) procedure on the best candidate beam selected during BFD. In some examples, if the best beam is located within any beam configured in the beam failure recovery configuration, UE 304 may select a contention-free random access (CFRA) RACH procedure 306; otherwise, UE 304 selects a contention-based random access (CBRA) RACH procedure 308.

[0056] For example, a counter can track L1 beam failure instance indications. Once the maximum count threshold is reached, PCellBFR operation 310 is triggered. If the optimal beam is within any beam configured in the beam failure recovery configuration, UE 304 transmits a BFR-specific preamble 312 to network node 316, and the network node transmits UE-specific downlink control information (DCI) 314 to UE 304. If the optimal beam is outside any beam configured in the beam failure recovery configuration, UE 304 transmits a random access preamble 318 to network node 316. Network node 316 transmits a random access response 320 to UE 304. UE 304 transmits a scheduled transmission 322 to network node 316, and network node 316 transmits a contention resolution 324 to UE 304.

[0057] Figure 3B A flowchart 326 illustrating a beam fault response (BFR) for a secondary cell (SCell) according to some implementation schemes is shown. After the number of beam fault instances reaches a threshold, a trigger 332 for SCell BFR operation can be determined. For SCell BFR, UE 328 can send a BFR MAC control element (CE) transmission scheme. In some cases, this scheme can be sent via any available uplink permission. For example, UE 328 can detect a beam fault on SCell 334 and detect a good candidate beam. If an available uplink permission exists, the UE can transmit a BFR MAC CE 336 to network node 330, and network node 330 can respond by sending an ACK message 338 to UE 328.

[0058] In other cases, if no uplink permission is available, BFR-SR 340 will be triggered if a BFR scheduling request (SR) is configured. Furthermore, if no uplink permission is available, the RACH procedure may be triggered if BFR-SR is not configured or if BFR-SR transmission fails.

[0059] The implementation schemes described herein provide enhancements to BFR. Some implementation schemes address the following issues with BFR. In some wireless systems, the use of BFR may require the various drawbacks mitigated by the implementation schemes disclosed herein.

[0060] For example, BFR is a passive mechanism rather than an active one. Therefore, the cost after BFD in the PCell is significant for the UE. For example, the UE performs RACH after BFD. In some implementations, AI / ML can be used to trigger BFR reporting in advance. For example, the predicted BLER of BFD RS at a future time can trigger BFR reporting in advance. Network nodes can reconfigure beams in time to avoid RACH.

[0061] Furthermore, BFD is based on the BLER of a configured BFD RS, which may not cover all beam directions. For example, up to two RSs may exist for frequency ranges below 3 GHz, up to four RSs for frequency ranges above 3 GHz in the FR1 band, and up to eight RSs in FR2. In some implementations, the UE can predict the BLER of an RS from other BFD RSs to reduce measurement workload. This can be helpful, especially in battery-constrained situations.

[0062] Additionally, in some cases, the UE may report L1 RSRP values ​​for candidate RSs that exceed a threshold. Therefore, in some such cases, reporting delays may lead to mismatches in link recovery. To overcome this drawback, in some implementations, the UE may be configured to report L1 RSRP predictions at future times to reduce mismatches and / or outdated reporting.

[0063] Figure 4A , Figure 4B and Figure 4C Three different methods for handling beam faults are illustrated. Note that for... Figures 4A to 4C Five BFI thresholds are used to trigger BFD. These thresholds can be larger or smaller depending on the specific implementation desired. Specifically, Figure 4A An example of a legacy implementation of BFR according to some embodiments is illustrated. As shown in timeline 402, in the legacy BFR, the UE can detect five real BFIs 404 between time slots T7 and T12. In some embodiments, the five BFIs may be a threshold that enables the UE to trigger the RACH procedure 406 to recover after a beam failure.

[0064] Figure 4BAn example is illustrated where, according to some implementations, UE 408 can use AI / ML to predict BFD 410 before it occurs. For example, as shown, between time T0 and time T11, UE 408 can predict that BFD 410 can be detected between time T7 and time T12, which may trigger a RACH procedure for recovering from a beam failure. However, because BFD 410 is predicted before BFD 410, the PCell link can still be used to report the predicted BFD. Therefore, UE 408 can report BFR MAC-CE 414 to network node 412. BFR MAC-CE 414 indicates that UE 408 has predicted that BFD 410 will occur in the future. The network node can switch the beam 416 used for the link with UE 408 to avoid BFD 410.

[0065] Figure 4C An example according to some implementation schemes is illustrated, in which UE 418 may use AI / ML to predict some BFIs (e.g., predicted BFI 420) after detecting one or more real BFIs (e.g., real BFI 422). For example, during time T7 to time T9, UE 418 may detect two real BFIs 422. UE 418 may also predict that three more BFIs (e.g., predicted BFI 420) will exist in the following time slot. Therefore, UE 418 may predict that a BFD may occur. After detecting real BFI 422, the PCell link may not be available to report BFR MAC-CE 424. Therefore, UE 418 may report BFR MAC-CE 424 via SCell. Network node 426 may switch the beam used to communicate with UE 418 based on BFR MAC-CE 424.

[0066] Figure 5 An example flowchart 502 is illustrated according to an embodiment of this document for a UE-side procedure for BFD prediction, such as between UE 504 and network 506. It should be noted that in some embodiments, the UE-side procedure for BFD prediction may also be combined with the use of a UE server 508.

[0067] Flowchart 502 begins with UE 504 generating a UE capability report 510 and sending it to network 506. In some implementations, the UE capability report 510 may include one or more of the following: whether the UE supports time prediction for a BLER of a BFD-RS time prediction; whether the UE supports prediction for a cross-BFD-RS BLER; the maximum number of historical samples / slots available to the UE; the maximum number of samples / slots to be predicted; and / or the maximum number of parallel predictions that the UE can perform.

[0068] Then, network 506 provides training configuration 512 to UE 504. Training configuration 512 may include one or more of the following: the type of ML model to be trained (e.g., a Long Short-Term Memory (LSTM) ML model type, a Recurrent Neural Network (RNN) ML model type, etc.), the layers to be trained and / or one or more specialized ML models to be used; the window length corresponding to the measurement history and / or prediction type (e.g., prediction in the temporal and / or spatial domains, or cross-BFD-RS prediction) to be used with the ML model; and / or the maximum number of parallel predictions that should be provided by UE 504.

[0069] Then, UE 504 performs data collection 514. In some embodiments, this process incorporates generating / training an ML model at UE 504 using the collected data. In some embodiments, UE 504 provides the collected data to UE server 508, such that offline training 516 (e.g., generation of the ML model) occurs instead at UE server 508, and the UE server then provides the thus generated ML model back to UE 504.

[0070] Then UE 504 transmits notification message 518 to network 506. The content of notification message 518 can notify network 506 which ML models (and in at least some cases, the model IDs corresponding to these ML models are available at UE 504).

[0071] The notification message 518 may inform the network 506 which models are available in the UE and their model IDs. Notification message 518 may also inform the network 506 of model suitability conditions, which the network 506 can use to determine which ML model to use at the UE 504. It should be noted that model suitability conditions may include one or more of the following: usage scenario information (e.g., indoor / outdoor), antenna type information, channel type information, UE speed information (e.g., UE travel speed less than 5 km / h (kmph)), UE altitude information (e.g., corresponding to UE movement at an elevation), BFD-RS set, TRP information, etc. The notification message 518 may inform the network 506 of the UE's preferred model ID. It should be noted that notification message 518 may be, for example, part of MAC-CE, part of Uplink Assistance Information (UAI), or as an RRC message (e.g., in...). RRCReconfigurationComplete Provided in the message or a newly provided RRC message.

[0072] Based on notification message 518, network 506 can determine which ML model to activate at UE 504 and can provide UE 504 with activation message 520 commanding UE 504 to activate the selected ML model. Activation message 520 may be provided, for example, as part of DCI, MAC-CE, or RRC message reception.

[0073] Then, UE 504 continues to perform BLER prediction inference 522 according to the network configuration, and detects BFD based on BLER prediction. UE 504 transmits a report 524 for BFR to network 506 based on the actual and / or predicted L1 RSRP.

[0074] It is conceivable that, regarding the UE-side process, UE 504 or network 506 may perform performance monitoring 526 of the ML model. The monitoring metric may be one or both of prediction error and system performance. Based on the results of performance monitoring 526, UE 504 or network 506 may initiate lifecycle monitoring (LCM) signaling 528 for model switching or model deactivation, which then leads to model switching / model deactivation 530 at UE 504. In the case of deactivation, UE 504 and network 506 may then fall back to a non-AI / ML-based measurement reporting solution.

[0075] Details of BFD-RS BLER predictions In some implementations, the UE can be configured to perform any combination of the following implementations for BLER prediction. For example, Figure 6A An example is shown where the UE is configured to perform BLER prediction at a future time.

[0076] In some implementations, the UE can be configured to perform BLER prediction for a configured BFD-RS (explicit case) or an activated PDCCH's TCI (implicit case). The UE can further predict its future BLER based on one or more previous BLER samples. For example, in the illustrated implementation, for an SSB1 configured with BFD-RS, the UE can predict two BLER values ​​in a future time period 602 (e.g., t+4, t+5) based on historical measurements in past time periods 604 (e.g., t, t+1, t+2, t+3), such as... Figure 6A As shown. In some cases, the number of previous samples and predicted samples is configured by the network.

[0077] Figure 6BAn example is illustrated whereby the UE is configured to predict the BLER value of an RS based on samples from another BFD-RS. In the illustrated implementation, the UE may be configured to predict the BLER value of another RS ​​based on BLER samples from one or more BFD-RSs. The UE may predict the BLER value of another RS ​​that is different from the RS associated with the samples. In some cases, the RS may be another configured BFD-RS, thereby providing the benefit of reducing the measurement workload of the UE. For example, the UE may predict the BLER value 606 of BFD-RS 2 based on one or both of the sampled BLER value 610 of BFD-RS 3 and / or the sampled BLER value 608 of BFD-RS 1.

[0078] In some implementations, the predicted RS can be an SSB / CSI-RS that is not configured as a BFD-RS (e.g., a TCI of an activated PDCCH). This can provide the benefit of covering all possible beam spatial directions, thereby mitigating the problem of a small maximum number of BFD-RS.

[0079] In addition, in some cases, the long-term beam correlation (e.g., QCL) between RS and BFD-RS can be configured as auxiliary information by network nodes.

[0080] Figure 6C An example is illustrated where, according to some implementations, a UE is configured to predict the BLER value of a set of BFD-RS for a TRP point based on the actual values ​​of one or more sets of BFD-RS for other TRP points in a multi-TRP scenario. In some implementations, the UE may be configured to perform BLER prediction based on a BLER sample from one BFD-RS set (for one TRP) and predict the BLER value from another BFD-RS set (for another TRP). This can provide the benefit of reducing the UE's measurement workload. For example, the BLER value 612 for BFD-RS set 3 for TRP3 may be predicted based on the actual BLER values ​​from another BFD-RS set for another TRP (e.g., BLER value 614 and / or BLER value 616). In some cases, the TRP deployment geometry may be provided by the network node as supplementary information.

[0081] Furthermore, in other alternative schemes, the UE can be configured to perform BLER prediction based on other measurements. For example, cell L3 measurements, L1 RSRP of the RS, can also be used as auxiliary information and / or as AI / ML input. Figure 6DAn example of an AI / ML block diagram 618 for predicting BLER values ​​is illustrated. As shown, time samples 620 of the BLER of the first BFD-RS, time samples 622 of the BLER of the second BFD-RS, and auxiliary information 624 (e.g., inter-beam correlation, cell RSRP, etc.) can be input into the AI / ML model 626. The AI / ML model 626 can output the predicted BLER 628 of the third BFD-RS.

[0082] Figures 6A to 6D The illustrated implementations can be configured to work together or independently of each other. In some implementations, predicted confidence levels and / or predicted dwell times can be generated.

[0083] When to perform BLER prediction Some implementations support per-serving-cell configurations for continuous, periodic, and event-triggered BLER prediction. In the case of continuous prediction, the UE can begin prediction upon receiving the configuration and continue until the timer expires. In the case of periodic prediction, the UE can utilize another periodic configuration for BLER measurements used for prediction. In the case of event-triggered prediction, various triggering events can be introduced to induce the UE to begin BLER prediction in order to reduce the UE's power consumption when performing BLER prediction.

[0084] Figure 7 Two example triggering events for BLER prediction for event triggering are illustrated according to some implementation schemes. The first triggering event 702 (also referred to as E1) can be when the MAC layer detects at least M consecutive BFIs. M can be a value configured by the RRC. For example, when M=2 and a BFD is determined when five BFIs are received at the MAC layer, the UE can begin prediction when it receives two actual BFIs 704, thus predicting three BFIs 706 after the two actual BFIs 704.

[0085] The second trigger event 702 (also referred to as E2) can be when the BLER configured for BFD-RS is greater than a threshold. Note that the threshold can be less than Qout, allowing prediction to be performed earlier than beam failure. Qout can be a threshold level indicating unreliable downlink radio link reception and can correspond to an asynchronous BLER. In some implementations, Qout can be a 10% block error rate assuming PDCCH transmission. For example, Qout can be 10%, and the threshold used to initiate prediction (e.g., the second trigger event 702) can be 8%.

[0086] A third trigger event (also known as E3) may occur when the BLER of M BFD-RS (e.g., values ​​greater than 1) exceeds a threshold. In some implementations, M is an integer. In some implementations, the first trigger event 702 E1 may also be configured together with the second trigger event 708 E2 and / or the third trigger event E3. For example, a report may be triggered when both the first trigger event 702 E1 and the second trigger event 708 E2 are met.

[0087] In some implementations, a second trigger event 708 E2 and a third trigger event E3 can be configured regardless of whether the RS is in a configured BFD-RS set or in another configured RS set. In some implementations, a BLER prediction dwell time and confidence level can also be generated. The confidence level can be the mean squared error (MSE) between the actual BLER and the predicted BLER.

[0088] BFD triggering conditions New BFD triggering conditions can be established based on predictions. In some implementations, for a BFD-RS, if its predicted BLER at time T is greater than Qout and its confidence level is greater than a configured threshold, then the BLER of that BFD-RS can be considered greater than Qout at time T. In some implementations, if the BLER of all configured RSs is greater than Qout at time T, the PHY layer can generate a BFI at time T and transmit the BFI along with the predicted time T information to the MAC (if the BFI is generated based on the predicted BLERs of some RSs).

[0089] Figure 8A Example timeline 802 illustrates the use of predicted BLER to trigger BFD according to some implementation schemes. In some implementations, all RS use, as... Figure 8A The illustrated predicted BLER. For example, some implementations can use time BLER predictions at time T from historical measurements at time Tn.

[0090] Figure 8B Example timeline 804 illustrates the use of a real BLER and a predicted BLER to trigger BFD according to some implementation schemes. In some implementations, some RSs use the real BLER while others use the predicted BLER, such as... Figure 8B As illustrated. For example, some implementations can use cross-RS BLER prediction at time T to reduce the UE measurement burden.

[0091] In some implementations, some RSs are not part of the BFD-RS set if the network wants the UE to use prediction for some RSs that are not in the BFD-RS set. In some implementations, the MAC layer declares a BFD when the BFI counter (e.g., BFI_COUNTER) is greater than or equal to a threshold (e.g., beamFailureInstanceMaxCount). Because BFIs can be predicted before they occur, the timing of BFD declaration is earlier than it would occur in legacy systems.

[0092] BFR In some implementations, the BFR MAC-CE may be transmitted based on BLER prediction. In some implementations, for a BFD detected in a Pcell or SCell (SpCell), if some BFIs are generated based on BLER prediction and no actual BFI is detected (e.g., the channel on the SpCell is still available when the BFD is detected), the UE may report a BFR MAC-CE to the SpCell in some cases. In some implementations, the BFR MAC-CE may include at most one suitable candidate RS for a serving cell. In some implementations, the UE may report the available L1 RSRP actual measurement and / or predicted measurement of the candidate RS to the SpCell in a new RRC message. In both the BFR MAC-CE and RRC message cases, the UE may predict the BLER before the actual BFD. Therefore, the channel may still be available, allowing the UE to transmit the BFR MAC-CE or RRC message through a channel that the UE predicts will deteriorate.

[0093] When BLER prediction is based on at least one actual BFI detected, predicted beam faults can be reported using other methods. In some implementations, for a BFD detected in a SpCell, if some BFIs are generated based on BLER prediction and at least one actual BFI is detected, the UE can report a BFR MAC-CE via an available SCell. In some implementations, the UE can report actual and / or predicted measurements of an available L1 RSRP in a new RRC message. For example, the UE can apply Logical Channel Priority (LCP) restrictions to transmit Signal Radio Bearer 1 (SRB1) associated with Radio Link Control (RLC) bearers in an available SCell. In some implementations, the UE can perform an uplink handover to the SCell based on a handover mode pre-configured by the network; in some examples, an uplink handover to the SCell is performed on a different frequency band. In some implementations, the UE can report a Multiple Transmit and Receive Point (mTRP) BFR MAC-CE via an available TRP that may not declare a BFD.

[0094] In some implementations, for BFDs detected in the SpCell, if all BFIs are generated based on actual BLER measurements, the UE may follow the legacy BFR procedure. For example, the UE may trigger a RACH transmission in the SpCell. In some implementations, for BFDs detected in the SCell, the UE may report a BFRMAC-CE as done in legacy implementations.

[0095] BFR MAC-CE Figure 9A Example BFRs with an octet Ci field and truncated BFRs MAC CE 902 are illustrated according to some implementation schemes. Figure 9B Example BFRs and truncated BFR MAC CEs 904 with an octet Ci field are illustrated according to some implementations. MAC CEs used for BFRs (e.g., BFR MAC CE 902 and BFR MAC CE 902) may include BFR MAC CEs or truncated BFR MAC CEs. BFR MAC CEs and truncated BFR MAC CEs may be identified by a MAC subheader with a logical channel ID (LCID) / eLCID.

[0096] The C field (e.g., C field 906 and C field 908) may indicate beam fault detection. The AC field (e.g., AC field 910 and AC field 912) may indicate the presence of a candidate RS ID field in an octet. The candidate RS ID field (e.g., fields 914 and 916) may be set to the index of an SSB in the candidateBeamRSSCellList that has an SS-RSRP higher than rsrp-ThresholdBFR, or set to the index of a CSI-RS in the candidateBeamRSSCellList that has a CSI-RSRP higher than rsrp-ThresholdBFR. The BFR MAC CE may include a reserved bit (e.g., reserved bit 918).

[0097] In some implementations, when a BFR MAC-CE report is triggered, the UE can be configured to report the new BFR MAC-CE based on the predicted L1 RSRP of the candidate RS. Reporting the predicted L1 RSRP can provide the benefit of reducing channel mismatch caused by reporting delays.

[0098] In some implementations, the network configures the UE via RRC whether to report BFR MAC-CE based on the actual L1 RSRP and / or the predicted L1 RSRP. For example, in some implementations, the current MAC-CE format can be reused along with a new LCID for the predicted L1 RSRP. If the network configures the UE to report both the actual and predicted BFR MAC-CE, the UE will report both. In some implementations, the "R" field (e.g., reserved bit 918) can be used to indicate whether the L1 RSRP is the actual or predicted L1 RSRP. The network can configure the UE to prioritize the actual or predicted L1 RSRP. In some implementations, the predicted result can be reported when there are sufficient spare resources in the MAC PDU. For example, the predicted result can be included in padding bits.

[0099] Model monitoring and LCM Imagine that for the UE-side process used for BLER prediction, model monitoring (e.g., monitoring the performance of the ML model) can be performed at the UE and / or at the base station.

[0100] When model monitoring is performed at the base station, the performance monitoring metrics may vary depending on the specific implementation of the base station. In some implementations, the UE may be configured to provide information to the base station to assist in monitoring. This information may include additional temporal information, such as timestamps for prediction and timestamps corresponding to actual measurements. This information may also, or alternatively, include additional spatial information, such as the UE's actual location, the UE's actual movement orientation, changes in the UE's movement orientation, and / or incremental directions (differences) that can be compared with the prediction.

[0101] When model monitoring is performed at the UE, the model monitoring metric can, in some cases, be the confidence level of the prediction or information on the prediction accuracy. For example, this can take the form of the error between the prediction and the actual BLER measurement. For instance, the mean squared error (MSE) between some predicted BLER measurements and their corresponding actual BLER measurements can be used (note that using the MSE metric in this way can be an example of a "confidence level" as discussed herein). For monitoring purposes, the UE can perform both BLER and its prediction for a small set of RSs. Furthermore, in some implementations, the model monitoring metric can take the form of system performance. For example, the number of throughput changes or radio link failures (RLFs) over a configured duration.

[0102] In some implementations, the UE can be configured to perform UE-initiated model switching or network-initiated model switching.

[0103] In the case of UE-initiated model switching, the UE can utilize conditions and UE behavior configurations regarding model metrics (e.g., confidence levels). For example, the UE can utilize an MSE with a threshold of 0.01 and the corresponding behavior configuration. In other words, when the MSE is greater than 0.01, the UE can fall back to the traditional BLER measurement. Furthermore, the network can configure different models associated with different BFD-RS modes, such as different combinations of BFD-RS or different sets of BFD-RS. When the BFD-RS mode changes, for example via DCI, MAC-CE, or RRC, the UE switches to the associated model.

[0104] In the event of a network-initiated model switch, the UE can report model monitoring metrics and wait for base station LCM signaling. In this case, the UE can report model monitoring metrics via UAI or MAC-CE. For example, when the BFD-RS mode changes, for example via DCI, MAC-CE, or RRC, the UE can rely on explicit network indications regarding whether to perform a model switch.

[0105] In some cases, in either a UE-initiated model switch or a network-initiated model switch as disclosed herein, the UE may fall back to a legacy solution (e.g., actual BLER measurement).

[0106] In some implementations, the base station may provide the UE with the following information as supplementary information for UE monitoring: the deployment geometry of nearby base stations, long-term statistics on temporal correlations and / or long-term statistics on inter-beam correlations (such as QCL type D).

[0107] Auxiliary information used for BLER prediction The auxiliary information used for BLER prediction may include auxiliary information transmitted from the UE to the base station. Additionally, the auxiliary information used for BLER prediction may / optionally include auxiliary information transmitted from the base station to the UE.

[0108] In the case of auxiliary information from the UE to the base station, the UE may report the following auxiliary information to the network: the suggested optimal evaluation interval for Qout_LR; the suggested optimal value for beamFailureInstanceMaxCount; the suggested set of BFD-RS; and / or the suggested BFD-RS for actual measurements. The threshold Qout_LR can be the level of a downlink radio-level link that cannot reliably receive downlink radio-level links with a given resource configuration. In some implementations, UAI can be used to transmit auxiliary information from the UE to the base station.

[0109] In cases where auxiliary information is transmitted from the base station to the UE, the base station may provide the UE with the following auxiliary information: the deployment geometry of nearby base stations; long-term statistics on temporal correlations; and / or long-term statistics on inter-cell or inter-beam correlations. In some implementations, a new downlink (DL) message may be used to transmit auxiliary information from the base station to the UE. In some implementations, this message may be a MAC-CE or RRC message, such as RRCReconfigurationComplete or a new RRC message.

[0110] Figure 10 Method 1000 of a UE according to some implementation schemes is illustrated. Method 1000 includes transmitting a message 1002 to a network node instructing the UE to support the prediction of BLER. Method 1000 also includes receiving an activation message 1004 from the network node, the activation message identifying a prediction model used at the UE to predict BLER. Method 1000 also includes determining 1006 one or more predicted BFIs using the prediction model. Method 1000 also includes determining 1008 a potential future BFD based on one or more predicted BFIs. Method 1000 also includes transmitting a BFR message 1010 to the network node before a potential future BFD occurs.

[0111] In some implementations, the BFR message includes a Layer 1 RSRP of a prediction of a candidate reference signal at a future time.

[0112] In some implementations, potential future BFDs are predicted before any real BFIs are detected, and BFR messages are transmitted to the PCell via MAC-CE or RRC messages.

[0113] In some implementations, potential future BFDs are predicted after one or more real BFIs are detected, and BFR messages are transmitted to the SCell via MAC-CE or RRC messages.

[0114] In some implementations, method 1000 further includes transmitting a notification message identifying one or more prediction models available at the UE.

[0115] In some implementations, identifying potential future BFDs includes predicting the BLER for a configured BFD reference signal (RS) or an active physical downlink control channel (PDCCH) transmission configuration indication (TCI) based on historical block error rate (BLER) samples.

[0116] In some implementations, determining potential future BFDs includes predicting the BLER of the first reference signal based on block error rate (BLER) samples of the second reference signal.

[0117] In some implementations, determining the BFI of one or more predictions using a prediction model includes: performing continuous predictions that begin upon receiving a configuration and continue until a timer expires.

[0118] In some implementations, determining the BFI of one or more forecasts using a forecasting model includes performing periodic forecasts.

[0119] In some implementations, using a prediction model to determine the BFI of one or more predictions includes: performing event-triggered predictions.

[0120] The method of claim 10, wherein the predicted event triggered by the triggering event includes: when the media access control (MAC) layer detects a threshold number of consecutive BFIs, when the block error rate (BLER) of the configured BFD reference signal (RS) is greater than a threshold percentage, or when the BLER of a set number of BFD-RS is greater than a threshold percentage.

[0121] In some implementations, method 1000 further includes monitoring the performance of the prediction model.

[0122] The embodiments contemplated herein include an apparatus comprising components for performing one or more elements of method 1000. This apparatus may be, for example, a UE (such as wireless device 1302 as a UE, as described herein).

[0123] The embodiments contemplated herein include one or more non-transitory computer-readable media comprising instructions that, when executed by one or more processors of an electronic device, cause the electronic device to perform one or more elements of method 1000. The non-transitory computer-readable media may be, for example, the memory of a UE (such as memory 1306 of a wireless device 1302 serving as a UE, as described herein).

[0124] The embodiments contemplated herein include an apparatus comprising logic components, modules, or circuitry for performing one or more elements of method 1000. This apparatus may be, for example, a UE (such as wireless device 1302 as a UE, as described herein).

[0125] The embodiments contemplated herein include an apparatus comprising: one or more processors, and one or more computer-readable media including instructions that, when executed by the one or more processors, cause the one or more processors to perform one or more elements of method 1000. The apparatus may be, for example, a UE (such as wireless device 1302 as a UE, as described herein).

[0126] The implementation scheme envisioned herein includes a signal as described or associated with one or more elements of method 1000.

[0127] The embodiments contemplated herein include a computer program or computer program product comprising instructions, wherein the processor executes the program to cause the processor to implement one or more elements of method 1000. The processor may be a processor of the UE (such as processor 1304 as a wireless device 1302 of the UE, as described herein). These instructions may, for example, be located in the processor and / or in the memory of the UE (such as memory 1306 as a wireless device 1302 of the UE, as described herein).

[0128] Figure 11 Method 1100 for a network node is illustrated according to some embodiments. Method 1100 includes receiving a message 1102 from a UE instructing the UE to support the prediction of BLER. Method 1100 also includes transmitting an activation message 1104 to the UE, the activation message identifying a prediction model for use at the UE to predict BLER. Method 1100 also includes receiving a BFR message 1106 prior to a potential future BFD occurring, wherein the BFR is based on the prediction model.

[0129] In some implementations, the BFR message includes the predicted Layer 1 (L1) reference signal received power (RSRP) of the candidate reference signal at a future time.

[0130] In some implementations, method 1100 also includes switching beams based on predicted L1 RSRP values.

[0131] In some implementations, the UE predicts potential future BFDs before any real BFIs are detected, and BFR messages are transmitted to the PCell via MAC-CE or RRC messages.

[0132] In some implementations, after one or more real BFIs are detected, the UE predicts potential future BFDs, and BFR messages are transmitted to the SCell via MAC-CE or RRC messages.

[0133] In some implementations, method 1100 further includes receiving a notification message identifying one or more prediction models available at the UE.

[0134] In some implementations, method 1100 further includes monitoring the performance of the prediction model.

[0135] In some implementations, method 1100 further includes initiating lifecycle monitoring (LCM) signaling for model switching or model deactivation.

[0136] The embodiments contemplated herein include an apparatus comprising components for performing one or more elements of method 1100. This apparatus may be, for example, a base station (such as network device 1318 as a base station, as described herein).

[0137] The embodiments contemplated herein include one or more non-transitory computer-readable media comprising instructions that, when executed by one or more processors of an electronic device, cause the electronic device to perform one or more elements of method 1100. The non-transitory computer-readable medium may be, for example, the memory of a base station (such as memory 1322 of a network device 1318 serving as a base station, as described herein).

[0138] The embodiments contemplated herein include an apparatus comprising logic components, modules, or circuitry for performing one or more elements of method 1100. This apparatus may be, for example, a base station (such as network device 1318 as a base station, as described herein).

[0139] The embodiments contemplated herein include an apparatus comprising: one or more processors, and one or more computer-readable media including instructions that, when executed by the one or more processors, cause the one or more processors to perform one or more elements of method 1100. The apparatus may be, for example, an apparatus for a base station (such as network device 1318 as a base station, as described herein).

[0140] The implementation scheme envisioned herein includes a signal as described or associated with one or more elements of method 1100.

[0141] The embodiments contemplated herein include a computer program or computer program product comprising instructions, wherein execution by a processing element causes the processing element to perform one or more elements of method 1100. The processor may be a processor of a base station (such as processor 1320 of network device 1318 as a base station, as described herein). These instructions may, for example, be located in the processor and / or in the memory of the base station (such as memory 1322 of network device 1318 as a base station, as described herein).

[0142] Figure 12 An example architecture of a wireless communication system 1200 according to the embodiments disclosed herein is illustrated. The following description is provided for an example wireless communication system 1200 operating in conjunction with LTE system standards and / or 5G or NR system standards provided by 3GPP technical specifications.

[0143] like Figure 12As shown, the wireless communication system 1200 includes UE 1202 and UE 1204 (but any number of UEs may be used). In this example, UE 1202 and UE 1204 are exemplified as smartphones (e.g., handheld touchscreen mobile computing devices capable of connecting to one or more cellular networks), but may also include any mobile or non-mobile computing device configured for wireless communication.

[0144] UE 1202 and UE 1204 can be configured to communicatively couple with RAN 1206. In an implementation, RAN 1206 can be NG-RAN, E-UTRAN, etc. UE 1202 and UE 1204 utilize connections (or channels) with RAN 1206 (shown as connection 1208 and connection 1210, respectively), where each connection includes a physical communication interface. RAN 1206 may include one or more base stations (such as base station 1212 and base station 1214) implementing connection 1208 and connection 1210.

[0145] In this example, Connection 1208 and Connection 1210 are air interfaces that enable this type of communication coupling and can conform to the RAT used by RAN 1206, such as LTE and / or NR, for example.

[0146] In some implementations, UE 1202 and UE 1204 may also exchange communication data directly via sidelink interface 1216. UE 1204 is shown configured to access an access point (shown as AP 1218) via connection 1220. By way of example, connection 1220 may include a local wireless connection, such as a connection conforming to any IEEE 802.11 protocol, wherein AP 1218 may include Wi-Fi. ® Router. In this example, AP 1218 may connect to another network (e.g., the Internet) without using CN 1224.

[0147] In the implementation, UE 1202 and UE 1204 may be configured to communicate with each other or with base station 1212 and / or base station 1214 via a multi-carrier communication channel using orthogonal frequency division multiplexing (OFDM) communication signals according to various communication technologies, such as but not limited to orthogonal frequency division multiple access (OFDMA) communication technology (e.g., for downlink communication) or single-carrier frequency division multiple access (SC-FDMA) communication technology (e.g., for uplink and ProSe or sidelink communication), but the scope of the implementation is not limited in this respect. The OFDM signal may include multiple orthogonal subcarriers.

[0148] In some implementations, all or some of the base stations in base station 1212 or base station 1214 may be implemented as one or more software entities running on a server computer as part of a virtual network. Furthermore, or in other implementations, base station 1212 or base station 1214 may be configured to communicate with each other via interface 1222. In implementations where the wireless communication system 1200 is an LTE system (e.g., when CN 1224 is an EPC), interface 1222 may be an X2 interface. This X2 interface may be defined between two or more base stations (e.g., two or more eNBs, etc.) connected to the EPC and / or between two eNBs connected to the EPC. In implementations where the wireless communication system 1200 is an NR system (e.g., when CN 1224 is a 5GC), interface 1222 may be an Xn interface. The Xn interface is defined between two or more base stations (e.g., two or more gNBs, etc.) connected to the 5GC, between a base station 1212 (e.g., a gNB) connected to the 5GC and an eNB, and / or between two eNBs connected to the 5GC (e.g., CN 1224).

[0149] RAN 1206 is shown communicatively coupled to CN 1224. CN 1224 may include one or more network elements 1226 configured to provide various data and telecommunications services to customers / subscribers (e.g., users of UE 1202 and UE 1204) connected to CN 1224 via RAN 1206. Components of CN 1224 may be implemented in a single physical device or a separate physical device, including components for reading and executing instructions from machine-readable or computer-readable media (e.g., non-transitory machine-readable storage media).

[0150] In the implementation scheme, CN 1224 may be an EPC, and RAN 1206 may be connected to CN 1224 via S1 interface 1228. In the implementation scheme, S1 interface 1228 may be divided into two parts: an S1 user plane (S1-U) interface, which carries service data between base station 1212 or base station 1214 and the service gateway (S-GW); and an S1-MME interface, which is the signaling interface between base station 1212 or base station 1214 and the mobility management entity (MME).

[0151] In the implementation scheme, CN 1224 may be a 5GC, and RAN 1206 may be connected to CN 1224 via NG interface 1228. In the implementation scheme, NG interface 1228 may be divided into two parts: an NG user plane (NG-U) interface carrying service data between base station 1212 or base station 1214 and user plane function (UPF), and an S1 control plane (NG-C) interface serving as the signaling interface between base station 1212 or base station 1214 and access and mobility management function (AMF).

[0152] Generally, application server 1230 can be an element that provides Internet Protocol (IP) bearer resources (e.g., packet-switched data services) for use with CN 1224. Application server 1230 can also be configured to support one or more communication services (e.g., VoIP sessions, group communication sessions, etc.) for UE 1202 and UE 1204 via CN 1224. Application server 1230 can communicate with CN 1224 via IP communication interface 1232.

[0153] Figure 13 A system 1300 for performing signaling transfer 1334 between a wireless device 1302 and a network device 1318 according to an embodiment disclosed herein is illustrated. System 1300 may be part of a wireless communication system as described herein. Wireless device 1302 may be, for example, a UE of a wireless communication system. Network device 1318 may be, for example, a base station (e.g., an eNB or gNB) of a wireless communication system.

[0154] Wireless device 1302 may include one or more processors 1304. Processor 1304 is executable instructions that cause various operations of wireless device 1302 to be performed as described herein. Processor 1304 may include one or more baseband processors, which are implemented using, for example, a central processing unit (CPU), digital signal processor (DSP), application-specific integrated circuit (ASIC), controller, field-programmable gate array (FPGA) device, another hardware device, firmware device, or any combination thereof configured to perform the operations described herein.

[0155] Wireless device 1302 may include memory 1306. Memory 1306 may be a non-transitory computer-readable storage medium that stores instructions 1308, which may include, for example, instructions executed by processor 1304. Instructions 1308 may also be referred to as program code or computer program. Memory 1306 may also store data used by processor 1304 and results calculated by the processor.

[0156] Wireless device 1302 may include one or more transceivers 1310, which may include radio frequency (RF) transmitter circuitry and / or receiver circuitry, which use antenna 1312 of wireless device 1302 to facilitate signaling to and / or from wireless device 1302 and other devices (e.g., network device 1318) according to a corresponding RAT (e.g., signaling transmission 1334).

[0157] Wireless device 1302 may include one or more antennas 1312 (e.g., one, two, four, or more antennas). In embodiments with multiple antennas 1312, wireless device 1302 may fully utilize the spatial diversity of such multiple antennas 1312 to transmit 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 multiple antennas used at each of the transmitting and receiving devices to implement this aspect). MIMO transmission by wireless device 1302 may be achieved according to pre-decoding (or digital beamforming) applied at wireless device 1302, which multiplexes data streams across antennas 1312 based on known or assumed channel characteristics, such that each data stream is received with appropriate signal strength relative to the others at a desired location in the spatial domain (e.g., the location of the receiver associated with that data stream). Some implementations may use a single-user MIMO (SU-MIMO) approach (where all data streams are directed to a single receiver) and / or a multi-user MIMO (MU-MIMO) approach (where individual data streams may be directed to individual (different) receivers at different locations in the airspace).

[0158] In some implementations with multiple antennas, the wireless device 1302 may implement analog beamforming technology, thereby relatively adjusting the phase of the signal transmitted by the antenna 1312 so as to direct the (joint) transmission of the antenna 1312 (this is sometimes referred to as beam control).

[0159] Wireless device 1302 may include one or more interfaces 1314. Interface 1314 can be used to provide input to or output to wireless device 1302. For example, wireless device 1302 as a UE may include interface 1314, such as a microphone, speaker, touchscreen, and buttons, to allow a user of the UE to input to and / or output to the UE. Other interfaces of such a UE may consist of transmitters, receivers, and other circuitry that allow the UE to communicate with other devices (e.g., in addition to the transceiver 1310 / antenna 1312 already described), and may be based on known protocols (e.g., Wi-Fi). ® and Bluetooth ® (etc.) to perform the operation.

[0160] Wireless device 1302 may include prediction module 1316. Prediction module 1316 may be implemented via hardware, software, or a combination thereof. For example, prediction module 1316 may be implemented as a processor, circuitry, and / or instructions 1308 stored in memory 1306 and executed by processor 1304. In some examples, prediction module 1316 may be integrated within processor 1304 and / or transceiver 1310. For example, prediction module 1316 may be implemented via a combination of software components (e.g., executed by a DSP or general-purpose processor) and hardware components (e.g., logic gates and circuitry) within processor 1304 or transceiver 1310.

[0161] Configuration module 1316 can be used in various aspects of this disclosure, for example, Figures 1 to 12 All aspects. The prediction module 1316 is configured to enable the wireless device 1302 to perform UE-based functionality corresponding to BLER prediction as discussed herein.

[0162] Network device 1318 may include one or more processors 1320. Processor 1320 is executable instructions that cause various operations of network device 1318 to be performed as described herein. Processor 1320 may include one or more baseband processors, which are implemented using, for example, a CPU, DSP, ASIC, controller, FPGA device, another hardware device, firmware device, or any combination thereof configured to perform the operations described herein.

[0163] Network device 1318 may include memory 1322. Memory 1322 may be a non-transitory computer-readable storage medium that stores instructions 1324, which may include, for example, instructions executed by processor 1320. Instructions 1324 may also be referred to as program code or a computer program. Memory 1322 may also store data used by processor 1320 and results calculated by the processor.

[0164] Network device 1318 may include one or more transceivers 1326, which may include RF transmitter circuitry and / or receiver circuitry that uses the antenna 1328 of network device 1318 to facilitate signaling transmission (e.g., signaling transmission 1334) to and / or from network device 1318 and other devices (e.g., wireless device 1302) in accordance with a corresponding RAT.

[0165] Network device 1318 may include one or more antennas 1328 (e.g., one, two, four or more). In embodiments having multiple antennas 1328, network device 1318 may perform MIMO, digital beamforming, analog beamforming, beam control, etc., as described.

[0166] Network device 1318 may include one or more interfaces 1330. Interfaces 1330 may be used to provide input to or output to network device 1318. For example, network device 1318 as a base station may include interfaces 1330 consisting of transmitters, receivers, and other circuitry (e.g., in addition to the transceiver 1326 / antenna 1328 already described), which enable the base station to communicate with other equipment in the core network and / or enable the base station to communicate with external networks, computers, databases, etc., for the purpose of performing operations, management, and maintenance of the base station or other equipment operatively connected to the base station.

[0167] Network device 1318 may include prediction module 1332. Prediction module 1332 may be implemented via hardware, software, or a combination thereof. For example, prediction module 1332 may be implemented as a processor, circuitry, and / or instructions 1324 stored in memory 1322 and executed by processor 1320. In some examples, prediction module 1332 may be integrated within processor 1320 and / or transceiver 1326. For example, prediction module 1332 may be implemented via a combination of software components (e.g., executed by a DSP or general-purpose processor) and hardware components (e.g., logic gates and circuitry) within processor 1320 or transceiver 1326.

[0168] The HP EDCA module 1332 can be used in various aspects of this disclosure, for example, Figures 1 to 12 All aspects. The prediction module 1332 is configured to enable the network device 1318 to perform base station-based functionality corresponding to BLER prediction as discussed herein.

[0169] For one or more embodiments, at least one of the components illustrated in one or more of the foregoing figures may be configured to perform one or more operations, techniques, processes, and / or methods as described herein. For example, a baseband processor as described herein in conjunction with one or more of the foregoing figures may be configured to operate according to one or more of the examples illustrated herein. Similarly, circuitry associated with a UE, base station, network element, etc., as described above in conjunction with one or more of the foregoing figures may be configured to operate according to one or more of the examples illustrated herein.

[0170] Unless otherwise expressly stated, any of the embodiments described above may be combined with any other embodiment (or combination of embodiments). The foregoing description of one or more specific embodiments provides illustrative and descriptive information, but is not intended to be exhaustive or to limit the scope of the embodiments to the precise form disclosed. In light of the teachings above, modifications and variations are possible, or modifications and variations may be derived from practice with various embodiments.

[0171] Implementations and specific embodiments of the systems and methods described herein may include various operations embodied in machine-executable instructions to be executed by a computer system. The computer system may include one or more general-purpose or special-purpose computers (or other electronic devices). The computer system may include hardware components, including specific logical parts for performing the operations; or may include a combination of hardware, software, and / or firmware.

[0172] It should be recognized that the systems described herein include descriptions of specific implementations. These implementations may be combined into a single system, partially integrated into other systems, divided into multiple systems, or otherwise partitioned or combined. Furthermore, it is contemplated that parameters, attributes, aspects, etc., of one implementation may be used in another. For clarity, these parameters, attributes, aspects, etc., are described only in one or more implementations, and it should be recognized that, unless expressly stated herein, these parameters, attributes, aspects, etc., may be combined with or substituted for parameters, attributes, aspects, etc., of another implementation.

[0173] As is widely recognized, the use of personally identifiable information should comply with privacy policies and practices that are generally accepted to meet or exceed industry or governmental requirements for protecting user privacy. Specifically, personally identifiable information data should be managed and processed to minimize the risk of unintentional or unauthorized access or use, and the nature of authorized use should be clearly explained to users.

[0174] Although the foregoing has been described in considerable detail for clarity, it will be apparent that certain changes and modifications can be made without departing from the principles of the invention. It should be noted that many alternative ways exist to implement both the processes and apparatus described herein. Therefore, embodiments of the invention should be considered illustrative rather than restrictive, and this specification is not limited to the details given herein, but can be modified within the scope and equivalents of the appended claims.

Claims

1. A method for a user equipment (UE), the method comprising: Transmit a message to the network node indicating that the UE supports prediction of block error rate (BLER); Receive an activation message from the network node, the activation message identifying a predictive model used at the UE to predict the BLER; The prediction model is used to determine one or more predicted beam fault indications (BFIs). Potential future beam failure detection (BFD) is determined based on one or more of the predicted BFIs. as well as Before the potential future BFD occurs, a beam fault recovery (BFR) message is transmitted to the network node.

2. The method of claim 1, wherein the BFR message includes the predicted Layer 1 Reference Signal Received Power (RSRP) of the candidate reference signal at a future time.

3. The method of claim 1, wherein the potential future BFD is predicted before the actual BFI is detected, and wherein the BFR message is transmitted to the primary cell (PCell) via a Medium Access Control Element (MAC-CE) or Radio Resource Control (RRC) message.

4. The method of claim 1, wherein the potential future BFD is predicted after one or more real BFIs are detected, and wherein the BFR message is transmitted to the secondary cell (SCell) via a Medium Access Control Element (MAC-CE) or Radio Resource Control (RRC) message.

5. The method according to claim 1, further comprising: Transmit a notification message identifying one or more prediction models available at the UE.

6. The method of claim 1, wherein determining the potential future BFD comprises: The BLER is predicted based on historical BLER samples for the transmission configuration indication (TCI) against the configured BFD reference signal (RS) or the active physical downlink control channel (PDCCH).

7. The method of claim 1, wherein determining the potential future BFD comprises: The BLER of the first reference signal is predicted based on the BLER samples of the second reference signal.

8. The method of claim 1, wherein determining the one or more predicted BFIs using the prediction model comprises: Continuous prediction is performed, which begins upon receiving the configuration and continues until the timer expires.

9. The method of claim 1, wherein determining the one or more predicted BFIs using the prediction model comprises: Perform periodic forecasting.

10. The method of claim 1, wherein determining the one or more predicted BFIs using the prediction model comprises: Predictions triggered by execution events.

11. The method of claim 10, wherein the predicted event that triggers the event includes: When the Media Access Control (MAC) layer detects a threshold number of consecutive BFIs, when the BLER of the configured BFD reference signal (RS) is greater than the threshold percentage, or when the BLER of a set number of BFD-RS is greater than the threshold percentage.

12. The method according to claim 10, further comprising: Monitor the performance of the prediction model.

13. The method according to claim 1, further comprising: Transmitting auxiliary information to the network node, wherein the auxiliary information includes at least one of the following: The optimal evaluation interval suggested by Qout_LR; The recommended optimal value for beamFailureInstanceMaxCount; Recommended set of BFD reference signals (RS); or Recommended BFD-RS for actual measurements.

14. The method according to claim 1, further comprising: Receive auxiliary information from the network node, wherein the auxiliary information includes at least one of the following: The geometry of nearby network node deployments; Long-term statistics on time correlation; or Long-term statistics on inter-cell correlation or inter-beam correlation.

15. A method for a network node, the method comprising: Receive a message from the user equipment (UE) instructing the UE to support prediction of the block error rate (BLER); An activation message is transmitted to the UE, the activation message identifying a prediction model used at the UE to predict the BLER; and Receive beam fault recovery (BFR) messages before a potential future beam fault recovery (BFD) occurs, wherein the BFR messages are based on the prediction model.

16. The method of claim 15, wherein the BFR message includes a predicted Layer 1 (L1) Reference Signal Received Power (RSRP) value for a candidate reference signal at a future time.

17. The method of claim 16, further comprising: Beam switching is based on the predicted L1 RSRP value.

18. The method of claim 15, wherein the potential future BFD is predicted by the UE before the actual BFI is detected, and wherein the BFR message is transmitted to the primary cell (PCell) via a Media Access Control Element (MAC-CE) or Radio Resource Control (RRC) message.

19. The method of claim 15, wherein the potential future BFD is predicted by the UE after one or more real BFIs are detected, and wherein the BFR message is transmitted to the secondary cell (SCell) via a Media Access Control Element (MAC-CE) or Radio Resource Control (RRC) message.

20. The method of claim 15, further comprising: Receive notification messages identifying one or more prediction models available at the UE.

21. The method according to claim 15, further comprising: Monitor the performance of the prediction model.

22. The method according to claim 15, further comprising: Initiate lifecycle monitoring (LCM) signaling for model switching or model deactivation.

23. The method according to claim 15, further comprising: The UE receives assistance information, wherein the assistance information includes at least one of the following: The optimal evaluation interval suggested by Qout_LR; The recommended optimal value for beamFailureInstanceMaxCount; Recommended set of BFD reference signals (RS); or Recommended BFD-RS for actual measurements.

24. The method according to claim 15, further comprising: The auxiliary information is transmitted to the UE, wherein the auxiliary information includes at least one of the following: The geometry of nearby network node deployments; Long-term statistics on time correlation; or Long-term statistics on inter-cell correlation or inter-beam correlation.

25. An apparatus comprising components for performing the method according to any one of claims 1 to 24.

26. A computer-readable medium comprising instructions that, when executed by one or more processors of an electronic device, cause the electronic device to perform the method according to any one of claims 1 to 24.

27. An apparatus comprising a logic component, module, or circuit for performing the method according to any one of claims 1 to 24.

Images