Sensing assisted time prediction for radio resource measurement enhancements

Abstract

A base station serving a user equipment (UE) senses environmental parameters surrounding the UE. The base station then uses an artificial intelligence (AI) model trained on these environmental parameters to predict a future LOS path-to-non-line-of-sight (NLOS) path transition based on predicted future line-of-sight (LOS) path obstructions. The base station can then switch from a first transmit (Tx) beam in the LOS path to the UE to a second Tx beam in the NLOS path, and send an indication to the UE of the LOS-to-NLOS path transition. Accordingly, the UE can receive the indication and adjust its receive (Rx) beam for communication with the base station on the NLOS path. Other implementations for sensing and AI models trained on environmental parameters, alternatively located at the UE, are also discussed.

Description

Technical Field

[0001] This application relates in general to wireless communication systems, including wireless communication systems that implement artificial intelligence (AI) / machine learning (ML) models. 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 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 510 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 The flowchart illustrating the use of an AI / ML model at the UE to identify the optimal Tx-Rx beam pair between the base station and the UE according to the implementation scheme provided herein, along with various corresponding graphical examples, is presented.

[0010] Figure 2 An example of an AI / ML model for beam management and tracking is shown.

[0011] Figure 3 An example of an AI / ML model for assisting beam management and tracking according to an embodiment of this paper is illustrated, which is trained on both the reference signal received power (RSRP) value of the probe beam and environmental parameters obtained from the sensing environment.

[0012] Figure 4 An example of future line-of-sight (LOS) path congestion prediction by an AI / ML model according to the implementation of this paper is illustrated. This AI / ML model is trained on environmental parameters obtained from sensing performed at a base station.

[0013] Figure 5 An example is illustrated by an AI / ML model based on the RSRP of the probe beam and environmental parameters obtained from sensing performed at the UE, according to the implementation of this paper.

[0014] Figure 6 An example is illustrated of the transformation from a predicted LOS path to a non-line-of-sight (NLOS) path by an AI / ML model due to LOS path obstruction, according to the implementation of this paper. The AI / ML model is trained on the RSRP value of the probe beam and environmental parameters obtained by sensing performed at the UE.

[0015] Figure 7 A flowchart and various corresponding diagrams are illustrated for signaling between the UE and the base station to the transition from a LOS path to an NLOS path predicted by an AI / ML model, according to the implementation scheme discussed herein. The AI / ML model is trained on the RSRP value of the probe beam and environmental parameters obtained by sensing performed at the UE.

[0016] Figure 8 A method for a base station to serve a UE according to an embodiment of this document is illustrated.

[0017] Figure 9 An example is provided of a method for a base station to serve a UE according to an embodiment of this document.

[0018] Figure 10 An example is provided of a method for a base station to serve a UE according to an embodiment of this document.

[0019] Figure 11 A method for a base station to serve a UE according to an embodiment of this document is illustrated.

[0020] Figure 12 An example architecture of a wireless communication system according to the implementation scheme disclosed herein is illustrated.

[0021] 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

[0022] 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 component capable of establishing a connection to a network and configured with hardware, software, and / or firmware for exchanging information and data with the network. Therefore, the UE as described herein is used to represent any suitable electronic component.

[0023] In various wireless communication systems, the overhead associated with the transmission of reference signals used for Radio Resource Management (RRM), such as Synchronization Signal Blocks (SSBs) and / or Channel State Information Reference Signals (CSI-RS), is not insignificant. For example, in an NR wireless communication system using a 20-millisecond (ms) SSB-based RRM Measurement Timing Configuration (SMTC) period and a 5-ms SSB burst in FR2, the corresponding SMTC-related overhead is understood to be 25%.

[0024] Accordingly, in some cases, it may be beneficial to reduce the number of beams used on the transmit (Tx) side and / or receive (Rx) side in layer 3 (L3) related measurements (e.g., beam measurements for RRM purposes).

[0025] The embodiments disclosed herein relate to enhancing RRM functionality using AI / ML models. In various embodiments, L3 measurement delay and / or overhead reduction can be achieved by minimizing the Tx / Rx beam scan set through spatial beam prediction performed by AI / ML models. For example, SMTC window duration can be reduced by decreasing the beam scan factor used by / in the SMTC window (e.g., by reducing the number of Tx and / or Rx beams used by the beam scan mechanism of the SMTC window).

[0026] In various implementations, L3 measurement reduction can be achieved by periodically skipping Tx / Rx beam scan instances and replacing actual measurements with spatial beam predictions from an AI / ML model. For example, SMTC periodicity might be increased, meaning that various instances of SMTC-based measurements that would otherwise occur with lower periodicity are conceptually skipped. The skipped measurements can be replaced by predictions for these measurements generated at the AI / ML model.

[0027] Due to this reduction in L3 measurements, throughput may increase. For example, scheduling constraints at orthogonal frequency division multiplexing (OFDM) symbols that would otherwise be used for measurements (e.g., symbols that would otherwise be used for the SSB to be measured) can be removed. Accordingly, RRM performance (and thus overall system performance) can be enhanced as a result of implementing RRM functionality using AI / ML models and / or algorithms.

[0028] Beamforming and LOS path blockage prediction from environmental perception In some wireless communication systems (e.g., mmWave systems), beam training can be costly. In some of these systems, LOS path, or in other words, LOS link congestion, poses a challenge to network reliability and latency because beam alignment and / or selection can depend on factors such as Tx / Rx location, the geometry of the surrounding environment, and environmental dynamics (e.g., moving objects in the environment). Therefore, gaining some awareness of the surrounding environment and its dynamics can aid in beam selection, as awareness of the surrounding area can help predict future LOS path congestion. For example, some LOS mmWave links may be blocked by moving objects. This can lead to sudden performance degradation or cell reselection. Predicting future congestion allows the serving cell to make proactive decisions, such as proactively transferring users to another cell or proactively switching users to another beam (i.e., time prediction).

[0029] RSRP and Sensing-Assisted Beam Prediction For certain wireless communication systems (e.g., sixth-generation (6G) systems), integrated communication and sensing (ICAS) has been considered. One application of ICAS is, for example, in the context of sensing-assisted communication, where sensor data (e.g., radar sensing) can be utilized to enhance wireless communication performance (e.g., beam management and / or L3 measurement). Furthermore, in some wireless communication systems, AI / ML-based beam management has been considered, where AI / ML models are trained to predict optimal beams in the spatial and / or temporal domains based on a reduced set of RSRP measurements (i.e., inputs to the AI / ML model).

[0030] The implementation schemes disclosed herein can enhance the capabilities of AI / ML models by (e.g., in radar-based scenarios) augmenting the training input dataset with sensing data. Therefore, AI / ML models can be used to, for example, facilitate sensing-assisted beam prediction / tracking and / or enable sensing-assisted obstruction prediction and active handover.

[0031] Example subsets of probe beams and AI / ML models at the UE Figure 1A flowchart 100, and various corresponding diagrammatic illustrations, are provided to illustrate the use of an AI / ML model 106 at UE 104 to identify the optimal Tx-Rx beam pair between base station 102 and UE 104 according to the embodiments provided herein. As illustrated, base station 102 may transmit a reference signal 110 to UE 104 on one or more probe beams 108. The one or more probe beams 108 used may be a subset (possibly less than all Tx beams of the selected Tx codebook) of all Tx beams available / usable at base station 102 for each selected Tx codebook. A particular subset of the one or more probe beams 108 used from the Tx codebook may be specific to the active serving cell. Depending on the beam scanning method, the transmission of the reference signal on one or more probe beams 108 may occur one Tx beam at a time.

[0032] It should be noted that in some implementations, base station 102 may also transmit 110 information corresponding to one or more probe beams 108. For example, base station 102 may transmit 110 the beam direction of one or more probe beams 108 (e.g., in relation to the angle domain information and / or SSB information of each of the one or more probe beams 108). Furthermore, base station 102 may also transmit 110 the Tx codebook size applicable to one or more probe beams 108 (e.g., the size from which the Tx codebook of one or more probe beams 108 is acquired / sampled). The beam direction and / or codebook information provided to the UE enables the UE to correctly measure / interpret the reference signals received on one or more probe beams 108.

[0033] UE 104 scans 112 one or more of its own Rx beams relative to one or more probe beams 108. In other words, UE 104 uses one or more of its own Rx beams to perform reference signal measurements on reference signals on one or more probe beams 108 and stores the reference signal strength (e.g., reference signal received power (RSRP)) corresponding to each such measurement.

[0034] One or more sets of Rx beams may be selected for these measurements to correspond to beam direction and / or codebook information such as one or more probe beams 108 received from base station 102. For example, one or more sets of Rx beams may be selected from an Rx codebook that is understood to correspond to a Tx codebook indicated by base station 102, and / or the selection may be based on the indicated beam direction from base station 102.

[0035] In some cases, UE 104 performs the procedure using all available Rx beams at UE 104 (e.g., all Rx beams of the selected Rx codebook). In other cases, UE 104 may be configured to use only a subset of all available Rx beams at UE 104.

[0036] As a result of these measurements, UE 104 obtains a measured reference signal strength 114 for various Tx-Rx beam pairs (where each such measurement corresponds to a unique combination of one of one or more probe beams 108 and one of the Rx beams used to measure the reference signal on these one or more probe beams 108, as described).

[0037] Then, these measured reference signal strengths 114 of these Tx-Rx beam pairs are provided to the AI / ML model 106, which is trained to use the measured reference signal strengths 114 to generate the predicted received signal strengths 116 of a larger overall set (e.g., all Tx-Rx beam pairs) of Tx-Rx beam pairs between the base station's Tx beam and the UE's Rx beam.

[0038] The predicted received signal strength 116 can be understood based on the reference signal strength diagram 118 used for the relationship between base station 102 and UE 104. Figure 1 The reference signal strength diagram 118 is illustrated in three dimensions. X-dimensional 120 and Y-dimensional 122 correspond to the horizontal and vertical indices, respectively, and together identify the applicable Tx beams of base station 102 for which the predicted reference signal strength applies. Then, Z-dimensional 124 contains multiple XY planes representing such reference signal strengths, where each individual plane represents the reference signal strength (as illustrated) of a different Rx beam of UE 104 relative to the Tx beams of base station 102. Accordingly, the reference signal strength diagram 118 is understood to contain predicted reference signal strengths (as predicted by AI / ML model 106) for a large overall set (e.g., all Tx-Rx beam pairs) between base station 102 and UE 104.

[0039] Then, UE 104 identifies the number of highest reference signal strengths in the Tx-Rx beam pairs represented in the reference signal strength diagram 118. K The optimal Tx-Rx beam pair predicted. K The value can be configured to UE 104 by base station 102 (e.g., previously), or it can be pre-configured according to the specifications of the type of wireless communication system of base station 102 and UE 104. K Example values ​​include 2, 4, 8, etc.

[0040] Compared to the publicly available content of this article, this quantity K The predicted optimal Tx-Rx beam pair can sometimes be more simply referred to as the "pre- K "One beam pair". Furthermore, as in Figure 1 In the case where UE 104 uses AI / ML model 106 to generate reference signal strength map 118, and the applicable type of reference signal strength is RSRP, compared with these previous K The associated predictive reference signal strengths of each beam pair can be expressed as: .

[0041] Figure 1 (For example) it illustrates one of them K In the case of =4, correspondingly, as illustrated, the four highest reference signal strengths are identified from the reference signal strength diagram 118, which ultimately allows UE 104 to know the preceding... K ( K =4) Tx and Rx beams of each beam pair in the set (e.g., the correspondence between these Tx-Rx beams and the X-dimension 120, Y-dimension 122 and Z-dimension 124 of the reference signal strength diagram 118, as described).

[0042] Before the sign K After the beam pair is determined, UE 104 sends a signal to base station 102 to notify 126 of the predicted optimal Tx-Rx beam pair (the Tx beam represented in the predicted optimal Tx-Rx beam pair). K The predicted optimal Tx beam. This number is relative to the publicly available information in this paper. K The predicted optimal Tx beam can sometimes be more simply referred to as the "front" beam. K "One Tx beam". Accordingly, Figure 1 An example is shown of the first K Tx beams 128 that can be understood at base station 102 based on signaling 126 from UE 104.

[0043] Base station 102 continues to transmit reference signals 130 on the first K Tx beams 128. During these transmissions, UE 104 uses 132 of the predicted optimal Tx-Rx beam pairs. K A number of predicted optimal Rx beams (represented in the predicted optimal Tx-Rx beam pair) are used to perform reference signal measurements of the reference signal. This number is relative to the disclosure herein. K The predicted optimal Rx beam can sometimes be more simply referred to as the "front" beam. K"One Rx beam". In this part of the process, UE104 uses its corresponding paired Rx beam to measure the reference signal on the Tx beam (because the pairing is understood based on the predicted set of optimal Tx-Rx beam pairs).

[0044] Then, UE 104 identifies the highest received signal strength from the received signal strength measurements from these (actual) reference signals. UE 104 identifies the corresponding best Tx-Rx beampair from the predicted best Tx-Rx beampairs (the predicted best Tx-Rx beampair associated with the highest measured received signal strength) as the Tx-Rx beampair for communication between base station 102 and UE 104. Accordingly, UE 104 reports 134 the Tx beam in this Tx-Rx beampair to base station 102. Then, base station 102 indicates 136 to UE 104 that it has determined to use the Tx beam for subsequent communication with UE 104. Then, UE 104 correspondingly determines 138 to use the Rx beam in this Tx-Rx beampair for subsequent communication with base station 102.

[0045] like Figure 1 The training of AI / ML models on AI / ML and the prediction of optimal Tx-Rx beams, as discussed in the paper, can be applied to... Figure 2 , Figure 3 , Figure 4 , Figure 5 , Figure 6 and / or Figure 7 Various related implementation plans.

[0046] Spatial and temporal AI / ML beam prediction based on RSRP Figure 2 An example of an AI / ML model for beam management and tracking is shown.

[0047] In some wireless communication systems, for spatial and temporal beam prediction and beam tracking, an AI / ML model 206 can be trained on a subset of RSRP values ​​202 of one or more probe beams (e.g., Tx beams, Rx beams, and / or Tx-Rx beam pairs) sampled in both the spatial and temporal domains at time t-1, and a subset of RSRP values ​​204 of one or more probe beams (e.g., Tx beams, Rx beams, and / or Tx-Rx beam pairs) sampled in both the spatial and temporal domains at time t. The subsets of RSRP values ​​202 at time t-1 and RSRP values ​​204 at time t correspond to various Tx-Rx beam pairs, where the Tx beam is represented vertically as 218 and the Rx beam is represented horizontally as 220. In this example, the RSRP value of the Tx-Rx beam pair, exemplified by an asterisk (e.g., RSRP value 216), is provided as input to the AI / ML model 206.

[0048] like Figure 2 As shown, AI / ML model 206 can predict Tx-Rx beam pairs. For example, the AI / ML model can predict Tx-Rx beam pair 208 at time t+M, Tx-Rx beam pair 210 at time t+M+1, and Tx-Rx beam pair 212 at time t+M+2. AI / ML model 206 can also predict the best k beams 214 (e.g., the best k beams 214) from the set of predicted Tx-Rx beam pairs illustrated by circles. In some cases, based on the various AI / ML model inputs changing over time (such as subsets of RSRP values ​​202 of the probe beam at time t-1 and subsets of RSRP values ​​204 of the probe beam at time t changing due to environmental conditions (e.g., LOS path obstructions or other interference), the predicted best k beams change slowly over time as time changes from time t+M to time t+M+1. In some examples, Figure 2 The AI / ML model 206 discussed can be shared and targeted Figure 1 The training details discussed in the illustrated AI / ML models are similar to those discussed in the training details.

[0049] The implementation scheme disclosed herein uses an AI / ML model for beam prediction, management and tracking, wherein the AI / ML model uses both environmental parameter images (e.g., sensed environmental maps) and radio frequency (RF) received power (e.g., RSRP) to achieve higher prediction accuracy compared to AI / ML model predictions trained with the RSRP values ​​of the probed beam without any further training to take environmental factors into account.

[0050] Furthermore, the embodiments disclosed herein discuss AI / ML models trained with, for example, sensed environmental parameters to predict LOS path to NLOS path transitions and potential future congestion on the LOS path between the UE and the base station. For example, optimal K-beam multimodal power prediction can be performed using AI / ML models trained on various inputs, such as RSRP of the probe beam and radar images from the sensed environment.

[0051] Figure 3 An example of an AI / ML model for assisting beam management and tracking, according to an embodiment of this paper, is illustrated. This AI / ML model is trained on both the RSRP value of the probe beam and environmental parameters obtained from the sensed environment.

[0052] In some implementations, for spatial and temporal beam prediction and beam tracking, the AI / ML model 312 may be trained using, for example, a subset of RSRP values ​​302 of one or more probe beams sampled in both the spatial and temporal domains at time t-1, a subset of RSRP values ​​304 of one or more probe beams sampled in both the spatial and temporal domains at time t, and various environmental parameters determined by sensing the environment surrounding the UE. The subsets of RSRP values ​​302 at time t-1 and RSRP values ​​304 at time t correspond to various Tx and Rx beams, where Tx beams are represented vertically and Rx beams are represented horizontally. In this example, the RSRP values ​​of the Tx-Rx beam pairs, exemplified by asterisks, are provided as input to the AI / ML model 312. Environmental parameters are determined by sensing the environment in which the UE resides and may include, for example, a range-angle map 306, a range-Doppler map 308, and a micro-Doppler map 310. This is not an exhaustive list, and various other sensed environmental parameters can be used as training inputs in the AI / ML model 312. Furthermore, environmental sensing can be performed by the base station or the UE, and can take various forms of sensing (e.g., radar-based sensing, camera-based sensing, sensor-based sensing, LiDAR-based sensing, or a combination thereof). In some cases, the AI / ML model 312 may also be referred to as a multimodal power prediction model because it is trained on both the RSRP power of the probe beam and the sensed environmental parameters.

[0053] AI / ML model 312 can output beam predictions for Tx-Rx beams at various time points. For example, AI / ML model 312 can predict Tx-Rx beam pairs 314 at time t+M, Tx-Rx beam pairs 316 at time t+M+1, and Tx-Rx beam pairs 318 at time t+M+2, where t+M refers to various time points offset from each other by M. AI / ML model 312 can also predict the optimal K-beam 322 (e.g., the best K-beam 322) illustrated as a circle among the predicted Tx-Rx beam pairs.

[0054] In some implementations, the AI / ML model 312 can predict LOS path congestion between the network and the UE. Therefore, if the predicted best K beams change from time t+M+1 to time t+M+2, a beam handover 320 may occur to prevent beams that cannot reach the UE from being sent to the predicted LOS path congestion; in other words, the UE may be handed over to a different beam in a path not in a LOS path congestion. In some such cases, the LOS path congestion may not be predictable but is detected and is currently occurring, prompting a similar beam handover 320 to prevent beams from being sent to the LOS path congestion.

[0055] Predicting LOS-to-NLOS path transition based on sensing performed at the base station. Figure 4 An example of future LOS path 404 blockage prediction by an AI / ML model according to the implementation of this paper is illustrated. This AI / ML model is trained on environmental parameters obtained from sensing performed at the base station.

[0056] Consider an example ( Figure 4 (As illustrated), a future or potential LOS path obstruction 412 can be predicted by an AI / ML model, which obstructs the LOS path 404 between a base station (e.g., mmWave base station 416) and the UE 402. In such examples, the AI / ML model is at the base station and is trained on environmental parameters obtained from sensing performed by the base station. In some cases, sensing may include radar sensing 418, where the environmental parameters are calculated / determined based on the corresponding radar reflection 420 leaving the potential obstruction 412.

[0057] exist Figure 4 In the illustrated example, UE 402 is served by a serving cell (e.g., mmWave base station 416), and a potential obstruction 412 (e.g., a bus or other vehicle) moving in the direction of UE 402 or LOS path 404 is considered a target for sensing (e.g., radar sensing 418). The base station can (e.g., using radar sensing 418) sense environmental parameters about the potential obstruction 412 and further about the environment itself. The sensed environmental parameters can be used as input to train an AI / ML model using other training inputs (e.g., Tx probe beams).

[0058] The AI / ML model then predicts the optimal K beams and anticipates future or potential LOS path 404 blockages that may affect communication with the UE. In some cases, the AI / ML model can be used to predict the transition from LOS path 404 to NLOS path 406 due to future LOS path 404 blockages. If a LOS path 404 blockage is predicted, a beam switching from the first beam 408 to the second Tx beam 410 can occur at the base station, with a corresponding Rx beam switching at the UE for the predicted optimal Tx-Rx beam pair. After the AI / ML model predicts the transition from LOS path 404 to NLOS path 406, the base station can switch from transmitting the first Tx beam 408 in the LOS path 404 to the UE to transmitting the second Tx beam 410 in the NLOS path 406 to the UE, because the UE will not be able to receive the first beam 408 due to the LOS path 404 blockage 412.

[0059] In some cases, during NLOS path 406 communication, after the transition from LOS path 404 to NLOS path 406, a second Tx beam 410 may be sent to an object in the environment that can help facilitate NLOS path 406 communication by providing an alternative beam path to UE 402. This object may, for example, take the form of a reflector 414 that reflects the second Tx beam 410 to UE 402. For example, the object may take the form of a repeater that relays the second Tx beam 410 to the UE. The object may, for example, take the form of a communication cluster, which may consist of one or more base stations or objects that help further facilitate NLOS path 406 communication. Additionally, the objects facilitating NLOS path 406 communication can be a combination of the foregoing examples. This is not an exhaustive list, but rather used as an example, and any object that can facilitate NLOS path 406 communication may be used. Such objects used for NLOS path 406 communication facilitation are therefore referred to as "communication clusters".

[0060] exist Figure 4 In the illustrated example, the base station may already have prior information about reflector 414 in the environment that can be used to communicate with the UE's NLOS path 406, but in some other examples, the base station may use sensed environmental parameters to determine which reflector 414 can be used to communicate with the UE's NLOS path 406.

[0061] Signal notification based on UE-sensed LOS to NLOS path transition prediction Figure 5 An example of future LOS path 512 obstruction prediction by an AI / ML model based on the RSRP of the probe beam and environmental parameters obtained from sensing performed at the UE is illustrated according to the implementation of this paper.

[0062] Consider an example ( Figure 5 As illustrated, future or potential LOS path 512 obstructions (e.g., sensing target 510) can be predicted at UE 502 by an AI / ML model based on sensing performed at UE 502, the AI / ML model being trained on sensed environmental parameters and probe beams (e.g., RSRP of the probe beams). Figure 5In this scenario, UE 502 is being served by a base station (e.g., mmWave base station 508), and a sensing target 510 (e.g., a vehicle) is moving toward UE 502. This sensing target 510 is considered a target for sensing (e.g., the sensing type may include radar sensing, camera sensing, sensor sensing, LiDAR sensing, and any other type of sensing), wherein in some cases, the UE may measure radar reflections 514 reflected back to the UE from the sensing target 510 to calculate and / or determine environmental parameters of the environment in which the UE is camped, such as the position of the sensing target 510 or the speed and / or rate 518 of the sensing target 510. In some cases, such as... Figure 5 As illustrated, the base station's Tx beam 504 can be transmitted to the UE 502 without any problems because an active LOS path 512 exists between the base station and the UE 502. Furthermore, in such cases, the AI / ML model trained on sensed environmental parameters and the probe beam (e.g., the probe beam's RSRP) will not predict near-future LOS path 512 blockages. In such cases, the base station's Tx beam 504 can be transmitted to the UE 502 via a LOS path 512 link with the UE's Rx beam 516, which is located within the LOS path 512 with the base station. Therefore, since an unblocked LOS path 512 link is used, intermediate auxiliary communication cluster 506 is not required and may not be utilized when transmission occurs. It can be noted that in the illustrated example, the sensing target 510 does not block the LOS path 512, but in possible future examples, when the sensing target 510 moves in the direction of the LOS path 512, the sensing target 510 may block the LOS path 512 between the base station's Tx beam 504 and the UE 502.

[0063] In some implementations, an AI / ML model trained on sensed environmental parameters and a probe beam (e.g., the RSRP of the probe beam) can predict near-future, future, or potential LOS path blockages, thereby predicting possible LOS path to NLOS path transitions. Figure 6 This situation was further explored in the literature.

[0064] Figure 6 An example is illustrated of the LOS path to NLOS path transition by an AI / ML model based on an implementation of this paper due to LOS path obstruction. This AI / ML model is trained on the RSRP value of the probe beam and environmental parameters obtained by sensing performed at the UE.

[0065] In some implementations, the UE may employ sensing (e.g., sensing types may include radar sensing, camera sensing, sensor sensing, LiDAR sensing, and any other type of sensing) and may calculate / determine various environmental parameters (e.g., Doppler angle image maps based on radar signal processing). After training on the sensed environmental parameters and the probe beam (e.g., the RSRP of the probe beam), the AI / ML model may predict whether and / or when a LOS-to-NLOS path transition will occur. The UE may signal the base station to notify of this transition to adjust its own Tx beam (e.g., from a first Tx beam in the LOS path to the UE to a second Tx beam in the NLOS path to the UE). In some implementations, the UE may also use the AI / ML model to predict the optimal Tx-Rx beam pair (i.e., the optimal beam for NLOS path communication) when the LOS-to-NLOS path transition occurs and signal the optimal Tx-Rx beam pair to the base station.

[0066] Consider an example ( Figure 6 (As illustrated), where the LOS path 612 between the UE 610 and the base station (e.g., mmWave base station 614) is blocked by a sensed target 608. In some cases, the UE 610 can sense the environment by measuring radar reflection 602 reflected back to the UE from the sensed target 608, thereby obtaining parameters of the environment, the sensed target 608, and the area surrounding the sensed target 608. Based on the environmental parameters and various other training inputs such as the sounding beam, the AI / ML model may predict that the LOS path 612 is blocked by an obstruction (e.g., a vehicle, a person, a building) or will be blocked by such an obstruction in the future, thereby predicting a transition from LOS path to NLOS path. The UE 610 can then indicate to the base station that a transition from LOS path 612 to NLOS path 618 is occurring. Then, the base station (e.g., mmWave base station 614) may adjust its Tx beam from the first Tx beam 604 in the LOS path 612 to the UE 610 to the second Tx beam 606 in the NLOS path 618 to the UE 610, because the first Tx beam 604 used for communication on the LOS path 612 may no longer be used due to the LOS path 612 being blocked.

[0067] In some cases, the second Tx beam 606 may be transmitted by the base station to a communication cluster 616, which may then relay the second Tx beam 606 to the UE 610, or in other words, facilitate NLOS path 618 communication between the base station and the UE 610. It can be noted that in some cases, the base station may transmit the second Tx beam 606 using an object in the environment, rather than using the communication cluster 616 known to the UE, which may also facilitate NLOS path communication determined from the sensed environment. In such cases, the second Tx beam 606 may be transmitted, relayed, and / or reflected from an object within the environment based on environmental parameters obtained through sensing of the environment by the UE 610.

[0068] Additionally, in some implementations, when a LOS-to-NLOS path transition is predicted and / or occurs, the UE610 may signal to the base station the optimal beam pair 620 (i.e., the optimal beam for NLOS path communication) predicted by the AI / ML model disclosed herein. In such cases, the optimal beam pair may be the optimal Tx beam, the optimal Rx beam, and / or the optimal Tx / Rx beam pair.

[0069] Figure 7 A flowchart 700 for signaling between a UE and a base station to a LOS path to an NLOS path predicted by an AI / ML model, according to the implementation scheme discussed herein, is illustrated, along with various corresponding diagrammatic examples. This AI / ML model is trained on the RSRP value of the probe beam and environmental parameters obtained through sensing performed at the UE.

[0070] Flowchart 700 illustrates an example of signaling between UE 702 and a base station (e.g., gNB 704). First, UE 702 can use an AI / ML model to predict 706 a LOS-to-NLOS path transition and can indicate to the base station (e.g., gNB 704) that a predicted LOS-to-NLOS path transition has been detected. Then, UE 702 can send 708 the best next (i.e., future) Tx beam, Rx beam, and / or Tx / Rx beam pair to the base station (e.g., gNB 704). Based on the indication of the LOS-to-NLOS path transition, the base station (e.g., gNB 704) can switch 710 from transmitting a beam in the LOS path to UE 702 to transmitting a beam in the NLOS path to UE 702, or in other words, adjust its own Tx beam for communication with UE 702 on the NLOS path.

[0071] and Figure 6 and Figure 5 The examples considered in the previous examples are similar; consider an example ( Figure 7As illustrated, a sensing target 718 blocks the LOS path 714 between UE 702 and a base station (e.g., mmWave base station 712) transmitting a Tx beam 722. Additionally, in some cases, the blocking of the LOS path 714 can be predicted by an AI / ML model trained on environmental parameters obtained through sensing (e.g., sensing types may include radar sensing, camera sensing, sensor sensing, LiDAR sensing, and any other type of sensing) and a probe beam (e.g., the RSRP value of the probe beam). Therefore, UE 702 may fail to receive the Tx beam 722 because the LOS path 714 is blocked by the sensing target 718, and may need to communicate with UE 702's NLOS path 720 (e.g., via communication cluster 716, or objects in the environment known to the UE due to sensed environmental parameters). In such cases, the transition from LOS path 714 to NLOS path 720 can be detected and transmitted to the base station (e.g., gNB 704).

[0072] Furthermore, in the same example ( Figure 7 As illustrated, once a transition from LOS path 732 to NLOS path 734 is indicated to the base station (e.g., mmWave base station 730) (caused by sensing target 736 blocking LOS path 732 of UE 726), the base station can switch to the new Tx beam 724 in NLOS path 734 of UE 726. In some cases, NLOS path 734 communication can be accomplished with the assistance of a communication cluster 728 or a sensed object in the environment that can relay the new Tx beam 724 from the base station to UE 726.

[0073] While some implementations discussed in this paper describe the prediction of LOS-to-NLOS path transitions using AI / ML models, similar implementations are conceivable for predicting NLOS-to-LOS path transitions using AI / ML models. In such implementations, the AI / ML model predicts when the LOS path will be unblocked, thus allowing LOS path communication, rather than predicting future LOS path blockages. Similar to the implementations discussed herein, the AI / ML model can be trained on sensed environmental parameters and the Tx probe beam to predict when the LOS path will be unblocked. In some cases, the base station can switch from a beam in the NLOS path to the UE to a beam in the LOS path to the UE based on the predicted NLOS-to-LOS path transition and indicate the NLOS-to-LOS path transition to the UE. Accordingly, the UE can adjust the Rx beam for LOS path communication with the base station.

[0074] Sensing-assisted spatial and temporal beam prediction In some implementations, radar map sample sequences can be used to predict the transmit and / or receive beams for the next few time samples using an AI / ML model. Sensing (e.g., radar sensing) can provide contextual awareness of the communication environment, including the location, shape, and mobility of static and / or dynamic objects in the environment that affect wave propagation to the UE. Leveraging this contextual awareness, AI / ML can learn to predict future LOS links, or in other words, predict LOS path blockages before they occur. Sensing data maps (e.g., distance / velocity / Doppler maps) can be used as input to the AI / ML model to predict moving objects that will cause LOS path blockages, as well as the time and duration of these blockages. In some cases, this prediction allows the network to make proactive decisions regarding handover and beam switching to avoid abrupt communication interruptions, thereby increasing throughput.

[0075] Figure 8 A method 800 for a base station to serve a UE according to an embodiment of this document is illustrated. The illustrated method 800 includes sensing 802 environmental parameters surrounding the environment of the UE at the base station. Method 800 also includes using 804 an AI model trained on the environmental parameters to predict future LOS-to-NLOS path transitions, wherein the predicted LOS-to-NLOS path transitions include predicted future obstructions that block the LOS path from the base station to the UE. Method 800 also includes switching 806 from a first Tx beam in the LOS path to the UE to a second Tx beam in the NLOS path to the UE based on the predicted LOS-to-NLOS path transition. Method 800 further includes sending 808 an indication to the UE of the beam switch from the first Tx beam in the LOS path to the UE to the second Tx beam in the NLOS path to the UE based on the predicted LOS-to-NLOS path transition.

[0076] In some embodiments of method 800, sensing environmental parameters includes one or more of radar-based sensing, camera-based sensing, sensor-based sensing, and LIDAR-based sensing.

[0077] In some implementations, method 800 also includes sending the UE the optimal Tx-Rx beam pair predicted by an AI model trained on environmental parameters for use in NLOS path communication with the UE.

[0078] In some implementations, method 800 further includes sending a second Tx beam in the NLOS path to the UE to an object that facilitates NLOS path communication. In some such implementations, the object includes one or more of a communication trunking, a repeater, and a reflector.

[0079] In some implementations of method 800, the AI ​​model is also trained on the RSRP values ​​of the Tx-Rx beam pairs corresponding to the Tx probe beam. In some such implementations, the Tx probe beam is sampled in the time domain. In some other such implementations, the Tx probe beam is sampled in the spatial domain.

[0080] The embodiments contemplated herein include an apparatus comprising components for performing one or more elements of method 800. This apparatus may be, for example, a base station (such as network device 1318 as a base station, as described herein).

[0081] 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 800. The non-transitory computer-readable medium may be, for example, the memory of a base station (such as memory 1322 of network device 1318 as a base station, as described herein).

[0082] The embodiments contemplated herein include an apparatus comprising logic components, modules, or circuitry for performing one or more elements of method 800. This apparatus may be, for example, a base station (such as network device 1318 as a base station, as described herein).

[0083] 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 800. The apparatus may be, for example, an apparatus for a base station (such as network device 1318 as a base station, as described herein).

[0084] The implementation scheme envisioned herein includes a signal as described in or related to one or more elements of method 800.

[0085] 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 800. 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, reside 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).

[0086] Figure 9 A method 900 of a base station serving a UE according to an embodiment of this document is illustrated. The illustrated method 900 includes receiving from the base station 902 an indication of a predicted LOS-to-NLOS path transition at the base station by an AI model trained on environmental parameters sensed by the base station and a Tx probe beam, wherein the LOS-to-NLOS path transition includes predicted future obstructions that block the LOS path from the UE to the base station. Method 900 also includes adjusting 904 the Rx beam at the UE for communication with the base station on the NLOS path based on the received indication. Method 900 further includes receiving 906 the Tx beam in the NLOS path to the UE from the base station.

[0087] In some implementations, method 900 further includes receiving from the base station the optimal Tx-Rx beam pair predicted at the base station by an AI model trained on environmental parameters and the Tx probe beam.

[0088] In some implementations, method 900 further includes receiving a Tx beam in the NLOS path to a base station from an object that facilitates NLOS path communication. In some such implementations, the object includes one or more of a communication trunking, a repeater, and a reflector.

[0089] In some implementations of method 900, the AI ​​model is also trained on the RSRP values ​​of the Tx-Rx beam pairs corresponding to the Tx probe beam.

[0090] In some implementations of method 900, the Tx probe beam is sampled in the time domain.

[0091] In some implementations of method 900, the Tx probe beam is sampled in the airspace.

[0092] The embodiments contemplated herein include an apparatus comprising components for performing one or more elements of method 900. This apparatus may be, for example, a UE (such as wireless device 1302 as a UE, as described herein).

[0093] 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 900. 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).

[0094] The embodiments contemplated herein include an apparatus comprising logic components, modules, or circuitry for performing one or more elements of method 900. This apparatus may be, for example, a UE (such as wireless device 1302 as a UE, as described herein).

[0095] 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 900. The apparatus may be, for example, a UE (such as wireless device 1302 as a UE, as described herein).

[0096] The implementation scheme envisioned herein includes a signal as described in or related to one or more elements of method 900.

[0097] The embodiments contemplated herein include a computer program or computer program product comprising instructions, wherein execution by a processor causes the processor to perform one or more elements of method 900. The processor may be the memory of the UE (such as processor 1304 as a wireless device 1302 of the UE, as described herein). These instructions may, for example, reside in the processor and / or the memory of the UE (such as memory 1306 as a wireless device 1302 of the UE, as described herein).

[0098] Figure 10 A method 1000 for a base station to serve a UE according to an embodiment of this document is illustrated. The illustrated method 1000 includes sensing 1002 environmental parameters around the UE at the UE. Method 1000 also includes using 1004 an AI model trained on the environmental parameters to predict a future LOS-to-NLOS path transition, wherein the predicted LOS-to-NLOS path transition includes predicted future obstructions that block the LOS path from the UE to the base station. Method 1000 also includes adjusting 1006 an Rx beam for NLOS path communication with the base station based on the predicted LOS-to-NLOS path transition. Method 1000 further includes sending 1008 an indication of the predicted LOS-to-NLOS path transition to the base station.

[0099] In some embodiments of method 1000, sensing environmental parameters includes one or more of radar-based sensing, camera-based sensing, sensor-based sensing, and LIDAR-based sensing.

[0100] In some implementations, method 1000 further includes sending to a base station the optimal Tx-Rx beam pair predicted by an AI model trained on environmental parameters for NLOS path communication with the base station.

[0101] In some implementations, method 1000 further includes receiving a Tx beam in the NLOS path to a base station from an object that helps facilitate NLOS path communication. In some such implementations, the object includes one or more of a communication trunking, a repeater, and a reflector.

[0102] In some implementations of method 1000, the AI ​​model is also trained on the RSRP values ​​of the Tx-Rx beam pairs corresponding to the Tx probe beam. In some such implementations, the Tx probe beam is sampled in the time domain. In some other such implementations, the Tx probe beam is sampled in the spatial domain.

[0103] 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).

[0104] 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).

[0105] 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).

[0106] 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).

[0107] The implementation scheme envisioned herein includes a signal as described in or related to one or more elements of method 1000.

[0108] The embodiments contemplated herein include a computer program or computer program product comprising instructions, wherein execution of the program by a processor will cause the processor to perform 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, reside 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).

[0109] Figure 11 A method 1100 for a base station to serve a UE according to an embodiment of this document is illustrated. The illustrated method 1100 includes receiving from the UE 1102 an indication of a predicted LOS-to-NLOS path transition at the UE by an AI model trained on environmental parameters sensed by the UE and a Tx probe beam, wherein the LOS-to-NLOS path transition includes predicted future congestion that obstructs the LOS path from the base station to the UE. Method 1100 also includes switching 1104 from a first Tx beam in the LOS path to the UE to a second Tx beam in the NLOS path to the UE based on the received indication. Method 1100 further includes transmitting 1106 the second Tx beam in the NLOS path to the UE.

[0110] In some implementations, method 1100 further includes receiving from the UE the optimal Tx-Rx beam pair predicted by an AI model trained on environmental parameters.

[0111] In some implementations, method 1100 further includes sending a second Tx beam in the NLOS path to the UE to an object that facilitates NLOS path communication. In some such implementations, the object includes one or more of a communication trunking, a repeater, and a reflector.

[0112] In some implementations of method 1100, the AI ​​model is also trained on the RSRP values ​​of the Tx-Rx beam pairs corresponding to the Tx probe beam.

[0113] In some implementations of method 1100, the Tx probe beam is sampled in the time domain.

[0114] In some implementations of method 1100, the Tx probe beam is sampled in the airspace.

[0115] 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).

[0116] 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).

[0117] 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).

[0118] 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).

[0119] The implementation scheme envisioned herein includes a signal as described in or related to one or more elements of method 1100.

[0120] 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, reside 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).

[0121] Figure 12 An example architecture of a wireless communication system 1200 according to an embodiment 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.

[0122] 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.

[0123] UE 1202 and UE 1204 can be configured to be communicatively coupled to 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 of these connections 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.

[0124] In this example, Connection 1208 and Connection 1210 are air interfaces that implement this type of communication coupling and can conform to the RAT used by RAN 1206, such as LTE and / or NR, for example.

[0125] 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. For example, connection 1220 may include a local wireless connection, such as a connection conforming to any IEEE 802.11 protocol, while 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.

[0126] In some implementations, UE 1202 and UE 1204 may be configured to communicate with each other or with base station 1212 and / or base station 1214 on 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.

[0127] 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).

[0128] 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).

[0129] In this implementation, CN 1224 may be an EPC, and RAN 1206 may be connected to CN 1224 via S1 interface 1228. In this implementation, S1 interface 1228 may be divided into two parts: an S1 user plane (S1-U) interface carrying service data between base station 1212 or base station 1214 and the serving gateway (S-GW), and an S1-MME interface serving as the signaling interface between base station 1212 or base station 1214 and the mobility management entity (MME).

[0130] 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, which carries service data between base station 1212 or base station 1214 and the user plane function (UPF); and an S1 control plane (NG-C) interface, which is the signaling interface between base station 1212 or base station 1214 and the access and mobility management function (AMF).

[0131] Generally, application server 1230 may be an element that provides Internet Protocol (IP) bearer resources (e.g., packet-switched data services) for use with CN 1224. Application server 1230 may 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.

[0132] 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.

[0133] 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.

[0134] 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 a computer program. Memory 1306 may also store data used by processor 1304 and results calculated by the processor.

[0135] Wireless device 1302 may include one or more transceivers 1310, which may include radio frequency (RF) transmitter circuitry and / or receiver circuitry that use antenna 1312 of wireless device 1302 to facilitate signaling (e.g., signaling 1334) to and / or from wireless device 1302 and other devices (e.g., network device 1318) in accordance with a corresponding RAT.

[0136] Wireless device 1302 may include one or more antennas 1312 (e.g., one, two, four or more). 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-frequency resource. 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 other streams and 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).

[0137] In some implementations with multiple antennas, wireless device 1302 may implement analog beamforming technology, whereby the phase of the signal transmitted by antenna 1312 is relatively adjusted so that the (joint) transmission of antenna 1312 can be directed (this is sometimes referred to as beam control).

[0138] Wireless device 1302 may include one or more interfaces 1314. Interfaces 1314 can be used to provide input to or from wireless device 1302. For example, wireless device 1302 as a UE may include interfaces 1314, such as microphones, speakers, touchscreens, and buttons, to allow users of the UE to make inputs and / or outputs to the UE. Other interfaces of such UEs 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.

[0139] Wireless device 1302 may include a sensing-assisted timing prediction module 1316. The sensing-assisted timing prediction module 1316 may be implemented via hardware, software, or a combination thereof. For example, the sensing-assisted timing 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, the sensing-assisted timing prediction module 1316 may be integrated within processor 1304 and / or transceiver 1310. For example, the sensing-assisted timing 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.

[0140] The sensing-assisted time prediction module 1316 can be used in various aspects of this disclosure, such as Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5 , Figure 6 , Figure 7 , Figure 9 and Figure 10 The sensing-assisted timing prediction module 1316 is configured, for example, to use an AI / ML model trained on sensed environmental parameters to predict the transition from a future LOS path to an NLOS path based on predicted future obstructions blocking the LOS path of the base station. In some cases, the sensing-assisted timing prediction module 1316 may be configured, for example, to use an AI / ML model trained on sensed environmental parameters to predict the optimal Tx-Rx beam pair for NLOS path communication and to send the optimal Tx-Rx beam pair to the base station.

[0141] 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.

[0142] 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.

[0143] 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 (e.g., signaling 1334) to and / or from network device 1318 and other devices (e.g., wireless device 1302) in accordance with a corresponding RAT.

[0144] 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.

[0145] Network device 1318 may include one or more interfaces 1330. Interface 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 interface 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 and databases, etc., for the purpose of performing operations, management and maintenance of the base station or other equipment operatively connected to the base station.

[0146] Network device 1318 may include a sensing-assisted timing prediction module 1332. The sensing-assisted timing prediction module 1332 may be implemented via hardware, software, or a combination thereof. For example, the sensing-assisted timing 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, the sensing-assisted timing prediction module 1332 may be integrated within processor 1320 and / or transceiver 1326. For example, the sensing-assisted timing 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.

[0147] The sensing-assisted time prediction module 1332 can be used in various aspects of this disclosure, such as Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5 , Figure 6 , Figure 7 , Figure 8 and Figure 11The sensing-assisted timing prediction module 1332 is configured, for example, to use an AI / ML model trained on sensed environmental parameters to predict the transition from a future LOS path to an NLOS path based on predicted future obstructions blocking the base station's LOS path. In some cases, the sensing-assisted timing prediction module 1316 may be configured, for example, to use an AI / ML model trained on sensed environmental parameters to predict the optimal Tx-Rx beam pair for NLOS path communication and send the optimal Tx-Rx beam pair to the UE.

[0148] 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.

[0149] 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 forms disclosed. In light of the teachings above, modifications and variations are possible, or modifications and variations may be derived from practice with various embodiments.

[0150] 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.

[0151] 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 conceivable to use parameters, attributes, aspects, etc., of one implementation in one implementation. 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.

[0152] 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.

[0153] 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. Accordingly, 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 base station to serve a user equipment (UE), the method comprising: At the base station, environmental parameters surrounding the UE are sensed. An artificial intelligence (AI) model trained on the environmental parameters is used to predict future line-of-sight (LOS) to non-line-of-sight (NLOS) path transitions, wherein the predicted LOS to NLOS path transitions include predicted future blockages that block the LOS path from the base station to the UE. Based on the predicted LOS-to-NLOS path transition, switch from the first transmit (Tx) beam in the LOS path to the UE to the second Tx beam in the NLOS path to the UE. as well as Based on the predicted LOS-to-NLOS path transition, an indication is sent to the UE for beam switching from the first Tx beam in the LOS path to the UE to the second Tx beam in the NLOS path to the UE.

2. The method of claim 1, wherein sensing the environmental parameters includes one or more of radar-based sensing, camera-based sensing, sensor-based sensing, and light detection and ranging (LIDAR)-based sensing.

3. The method of claim 1, further comprising sending to the UE the optimal Tx-receive (Rx) beam pair predicted by the AI ​​model trained on the environmental parameters for communication with the UE's NLOS path.

4. The method of claim 1, further comprising sending the second Tx beam in the NLOS path to the UE to an object that facilitates NLOS path communication.

5. The method of claim 4, wherein the object comprises one or more of a communication cluster, a repeater, and a reflector.

6. The method of claim 1, wherein the AI ​​model is further trained on the reference signal received power (RSRP) value of the Tx-receive (Rx) beam pair corresponding to the Tx probe beam.

7. The method of claim 6, wherein the Tx probe beam is sampled in the time domain.

8. The method of claim 6, wherein the Tx probe beam is sampled in the airspace.

9. A method for serving a user equipment (UE) from a base station, the method comprising: The system receives an indication from the base station of a line-of-sight (LOS) path to non-line-of-sight (NLOS) path transition predicted at the base station by an artificial intelligence (AI) model trained on environmental parameters sensed by the base station and a transmit (Tx) probe beam, wherein the LOS path to NLOS path transition includes predicted future obstructions that block the LOS path from the UE to the base station. At the UE, the receive (Rx) beam is adjusted based on the instruction for communication with the base station via the NLOS path; as well as Receive the Tx beam in the NLOS path to the UE from the base station.

10. The method of claim 9, further comprising receiving from the base station the optimal Tx-Rx beam pair predicted at the base station by the AI ​​model trained on the environmental parameters and the Tx probe beam.

11. The method of claim 9, further comprising receiving a Tx beam in the NLOS path to the base station from an object that helps facilitate NLOS path communication.

12. The method of claim 11, wherein the object comprises one or more of a communication cluster, a repeater, and a reflector.

13. The method of claim 9, wherein the AI ​​model is further trained on the reference signal received power (RSRP) value of the Tx-Rx beam pair corresponding to the Tx probe beam.

14. The method of claim 9, wherein the Tx probe beam is sampled in the time domain.

15. The method of claim 9, wherein the Tx probe beam is sampled in the airspace.

16. A method for serving a user equipment (UE) from a base station, the method comprising: Sensing environmental parameters around the UE at the UE; An artificial intelligence (AI) model trained on the environmental parameters is used to predict future line-of-sight (LOS) to non-line-of-sight (NLOS) path transitions, wherein the predicted LOS to NLOS path transitions include predicted future blockages that block the LOS path from the UE to the base station. The receive (Rx) beam is adjusted based on the predicted LOS-to-NLOS path transition for communication with the base station via the NLOS path. as well as Send an indication to the base station of the predicted LOS path to NLOS path transition.

17. The method of claim 16, wherein sensing the environmental parameters comprises one or more of radar-based sensing, camera-based sensing, sensor-based sensing, and light detection and ranging (LIDAR)-based sensing.

18. The method of claim 16, further comprising sending to the base station an optimal transmit (Tx)-Rx beam pair predicted by the AI ​​model trained on the environmental parameters for communication with the NLOS path of the base station.

19. The method of claim 16, further comprising receiving a transmit (Tx) beam in the NLOS path to the base station from an object that helps facilitate communication along the NLOS path.

20. The method of claim 19, wherein the object comprises one or more of a communication cluster, a repeater, and a reflector.

21. The method of claim 16, wherein the AI ​​model is further trained on the reference signal received power (RSRP) value of the transmit (Tx)-Rx beam pair corresponding to the Tx probe beam.

22. The method of claim 21, wherein the Tx probe beam is sampled in the time domain.

23. The method of claim 21, wherein the Tx probe beam is sampled in the airspace.

24. A method for a base station to serve a user equipment (UE), the method comprising: The UE receives an indication of a line-of-sight (LOS) to non-line-of-sight (NLOS) path transition predicted at the UE by an artificial intelligence (AI) model trained on environmental parameters sensed by the UE and a transmit (Tx) probe beam, wherein the LOS to NLOS path transition includes predicted future obstructions that block the LOS path from the base station to the UE. Based on the indication, switch from the first Tx beam in the LOS path to the UE to the second Tx beam in the NLOS path to the UE; as well as The second Tx beam is transmitted in the NLOS path to the UE.

25. The method of claim 24, further comprising receiving from the UE the optimal Tx-receive (Rx) beam pair predicted by the AI ​​model trained on the environmental parameters.

26. The method of claim 24, further comprising sending the second Tx beam in the NLOS path to the UE to an object that facilitates NLOS path communication.

27. The method of claim 26, wherein the object comprises one or more of a communication cluster, a repeater, and a reflector.

28. The method of claim 24, wherein the AI ​​model is further trained on the reference signal received power (RSRP) value of the Tx-receive (Rx) beam pair corresponding to the Tx probe beam.

29. The method of claim 24, wherein the Tx probe beam is sampled in the time domain.

30. The method of claim 24, wherein the Tx probe beam is sampled in the airspace.

31. An apparatus comprising components for performing the method according to any one of claims 1 to 30.

32. 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 30.

33. An apparatus comprising a logic component, module, or circuit for performing the method according to any one of claims 1 to 30.

34. A baseband processor for a user equipment (UE), the baseband processor being configured to perform the method according to any one of claims 9 to 23.

Images