CN116981056A

CN116981056A - Apparatus for artificial intelligence or machine learning assisted beam management

Info

Publication number: CN116981056A
Application number: CN202310423932.6A
Authority: CN
Inventors: 阿维克·森古普塔; 乌塔拉·香卡尔; 比什瓦鲁普·蒙达尔
Original assignee: Intel Corp
Current assignee: Intel Corp
Priority date: 2022-04-29
Filing date: 2023-04-19
Publication date: 2023-10-31

Abstract

The present application relates to an apparatus for Artificial Intelligence (AI) or Machine Learning (ML) assisted beam management, wherein the apparatus is for use in a User Equipment (UE) and comprises a processor circuit configured to: receiving a first reference signal repeatedly transmitted by a designated transmission beam of a Base Station (BS); determining signal strength parameters of the first reference signal associated with respective receive beams of the subset of receive beams of the UE; and predicting, based on the signal strength parameters of the first reference signal associated with each of the subset of receive beams of the UE, a best receive beam of the UE corresponding to the specified transmit beam of the BS using an AI or ML model for beam management, wherein the best receive beam of the UE corresponding to the specified transmit beam of the BS is either a receive beam of the subset of receive beams of the UE or a receive beam different from any of the subset of receive beams of the UE.

Description

Apparatus for artificial intelligence or machine learning assisted beam management

Cross Reference to Related Applications

The present application is based on and claims priority from U.S. patent application Ser. No.63/336,965, filed on 29 at 4/2022, the entire contents of which are incorporated herein by reference.

Technical Field

Embodiments of the present disclosure relate generally to the field of wireless communications, and more particularly, to an apparatus for Artificial Intelligence (AI) or Machine Learning (ML) -assisted beam management.

Background

Mobile communications have evolved from early voice systems to today's highly complex integrated communication platforms. A 5G or New Radio (NR) wireless communication system will provide various users and applications with access to information and sharing of data anytime and anywhere.

Drawings

Embodiments of the present disclosure will now be illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings in which like reference numerals refer to similar elements.

Fig. 1a shows a schematic diagram of a conventional beam acquisition process.

Fig. 1b shows a schematic diagram of an AI/ML assisted beam acquisition process.

FIG. 2 illustrates a block diagram of an example AI/ML model training and deployment framework in accordance with some embodiments of the present disclosure.

Fig. 3 illustrates a schematic diagram of AI/ML assisted beam prediction at a UE according to some embodiments of the present disclosure.

Fig. 4 illustrates a schematic diagram of AI/ML assisted beam prediction at a BS using downlink measurements, according to some embodiments of the present disclosure.

Fig. 5 illustrates a schematic diagram of AI/ML assisted beam prediction at a BS using uplink measurements, according to some embodiments of the present disclosure.

Fig. 6 illustrates a schematic diagram of AI/ML assisted joint beam-to-link prediction at a BS according to some embodiments of the present disclosure.

Fig. 7 illustrates an example format of an L1 reporting matrix according to some embodiments of the present disclosure.

Fig. 8 illustrates a schematic diagram of a network in accordance with various embodiments of the present disclosure.

Fig. 9 illustrates a schematic diagram of a wireless network in accordance with various embodiments of the present disclosure.

Fig. 10 illustrates a block diagram of components capable of reading instructions from a machine-readable or computer-readable medium (e.g., a non-transitory machine-readable storage medium) and performing any one or more of the methods discussed herein, in accordance with various embodiments of the disclosure.

Detailed Description

Various aspects of the illustrative embodiments will be described using terms commonly employed by those skilled in the art to convey the substance of the disclosure to others skilled in the art. However, it will be apparent to those skilled in the art that many alternative embodiments may be implemented using portions of the described aspects. For purposes of explanation, specific numbers, materials, and configurations are set forth in order to provide a thorough understanding of the illustrative embodiments. It will be apparent, however, to one skilled in the art that alternative embodiments may be practiced without these specific details. In other instances, well-known features may be omitted or simplified in order not to obscure the illustrative embodiments.

Furthermore, various operations will be described as multiple discrete operations in turn, in a manner that is most helpful in understanding the illustrative embodiments; however, the order of description should not be construed as to imply that these operations are necessarily order dependent. In particular, these operations need not be performed in the order of presentation.

The phrases "in an embodiment," "in one embodiment," and "in some embodiments" are repeated herein. These phrases generally do not refer to the same embodiment; however, they may also refer to the same embodiments. The terms "comprising," "having," and "including" are synonymous, unless the context dictates otherwise. The phrases "A or B" and "A/B" mean "(A), (B), or (A and B)".

Artificial intelligence or machine learning (AI/ML) is currently being investigated for NR air interfaces and analog beam management is determined as a candidate for AI/ML applications. The beam management process includes a beam training process for a User Equipment (UE) and a Base Station (BS), where each of the UE and BS has an antenna array including a plurality of antennas capable of forming a plurality of analog, digital, or mixed beams. The beam training process involves searching for the best beam from the perspective of the UE, BS, or joint UE and BS for a scenario where multiple beams of the UE and BS are operable.

Fig. 1a shows a schematic diagram of a conventional beam acquisition process. As shown in fig. 1a, the conventional beam acquisition process is a combined search process, typically implemented by performing a hierarchical or exhaustive beam search. The conventional beam acquisition process is performed on a Synchronization Signal (SS) and a Physical Broadcast Channel (PBCH) block (SSB) associated with a wider beam transmitted from the BS during initial access. Since SSBs are periodically transmitted by the BS and the UE can only scan a small portion of its receive beam on each SSB, the UE needs multiple SSB periods to scan all beams on each SSB. Thus, SSB periodicity and the number of beams of BS/UE form a major performance bottleneck for beam acquisition due to the large measurement delay.

The AI/ML tool may help reduce the complexity of beam acquisition, where the number of measurements may be significantly reduced by making measurements using a subset of beams and predicting the best beam using an AI/ML model based on the measurements of the subset of beams. Fig. 1b shows a schematic diagram of an AI/ML assisted beam acquisition process. As shown in fig. 1b, a trained AI/ML model may be provided with the measurement of the subset of beams as input, and the trained AI/ML model may provide an output that may be used to identify the best beam.

The AI/ML use case for beam management can be roughly divided into two sub-use cases, namely, spatial domain beam management and time domain beam management. Regardless of the specific application, a generic AI/ML model training and deployment framework can be considered.

FIG. 2 illustrates a block diagram of an example AI/ML model training and deployment framework in accordance with some embodiments of the present disclosure. As shown in fig. 2, in a first step, a data set should be generated based on the specific use case under consideration. The dataset should contain beam specific information including inputs for the AI/ML model and output tags for training, validation, and testing. The data set is typically divided into non-overlapping portions for training and testing. The next step is data preprocessing and normalization to ensure that the data is within the proper range of values for the AI/ML model. Note that normalization of the output labels may also be required depending on the problem formula and type of output layer activation function used. The AI/ML model is trained and validated based on normalized input and output data. In this example, it is assumed that the dataset generation and model training are non-real-time processes that are offline. Once the AI/ML model is trained, the retained test data is used to determine model accuracy. Once the model accuracy is acceptable, the AI/ML model can be deployed in a real-time environment to facilitate performance of specific beam management tasks.

In some embodiments, the AI/ML model for beam management may be used to predict the best transmit or receive beam at the UE or BS without an exhaustive search in order to reduce measurement and reporting delays.

I. Embodiments in deploying AI/ML model for beam management at a UE

In some embodiments, when an AI/ML model for beam management is deployed at a UE, the UE may receive a first reference signal repeatedly transmitted by a designated transmit beam of a BS, determine signal strength parameters of the first reference signal associated with each of a subset of receive beams of the UE, and predict an optimal receive beam of the UE corresponding to the designated transmit beam of the BS using the AI or ML model for beam management based on the signal strength parameters of the first reference signal associated with each of the subset of receive beams of the UE, wherein the optimal receive beam of the UE corresponding to the designated transmit beam of the BS is the receive beam of the UE or is a receive beam of any of the subset of receive beams different from the UE.

In some embodiments, the UE may determine a beam quality parameter associated with a designated receive beam of the UE, wherein the beam quality parameter indicates the UE's capability of the designated receive beam to receive reference signals transmitted by a designated transmit beam of the BS; and triggering the BS to repeatedly transmit the first reference signal through its designated transmit beam when the beam quality parameter falls below a first predetermined quality threshold.

Fig. 3 illustrates a schematic diagram of AI/ML assisted beam prediction at a UE according to some embodiments of the present disclosure. As shown in fig. 3, AI/ML assisted beam prediction involves the following processes: the UE measures beam quality parameters associated with a designated receive beam of the UE; when a beam quality parameter associated with a designated receive beam of the UE falls below a first predetermined quality threshold, the UE triggers the BS to repeatedly transmit a first reference signal over its designated transmit beam; and the UE measuring signal strength parameters of the first reference signal associated with each of the subset of receive beams of the UE to find an optimal receive beam of the UE corresponding to the specified transmit beam of the BS.

In some embodiments, the UE may also receive a plurality of first reference signals transmitted by respective transmit beams in a subset of transmit beams of the BS, determine signal strength parameters of the plurality of first reference signals associated with a designated receive beam of the UE, and predict an optimal transmit beam of the BS corresponding to the designated receive beam of the UE using an AI or ML model for beam management based on the signal strength parameters of the plurality of first reference signals associated with the designated receive beam of the UE, wherein the optimal transmit beam of the BS corresponding to the designated receive beam of the UE is the transmit beam in the subset of transmit beams of the BS or is a transmit beam different from any of the subset of transmit beams of the BS.

In some embodiments, the UE may also receive a plurality of first reference signals transmitted by respective ones of the transmit beam subsets of the BS, determine signal strength parameters of the plurality of first reference signals associated with respective ones of the receive beam subsets of the UE, and predict an optimal beam-pair link between the UE and the BS using an AI or ML model for beam management based on the signal strength parameters of the plurality of first reference signals associated with respective ones of the receive beam subsets of the UE.

In some embodiments, the UE may also repeatedly transmit a second reference signal to the BS through its designated transmit beam, receive signal strength parameters of the second reference information from the BS associated with each of the subset of receive beams of the BS, and predict an optimal receive beam of the BS corresponding to the designated transmit beam of the UE using an AI or ML model for beam management based on the signal strength parameters of the second reference signal associated with each of the subset of receive beams of the BS, wherein the optimal receive beam of the BS corresponding to the designated transmit beam of the UE is the receive beam of the subset of receive beams of the BS or is a receive beam other than any of the subset of receive beams of the BS.

In some embodiments, the UE may also send a plurality of second reference signals to the BS over respective transmit beams of its transmit beam subset, receive signal strength parameters of the plurality of second reference signals associated with respective receive beams of the receive beam subset of the BS from the BS, and predict an optimal beam-pair link between the UE and the BS using an AI or ML model for beam management based on the signal strength parameters of the plurality of second reference signals associated with respective receive beams of the receive beam subset of the BS. The signal strength parameters of the plurality of second reference signals associated with each of the subset of receive beams of the BS are reported to the UE with an L1 reporting matrix, wherein columns and rows of the L1 reporting matrix correspond to the receive beams of the BS and the transmit beams of the UE, respectively.

In some embodiments, the UE may also predict the UE's best receive and transmit beam for the next time instant based on the UE's best receive or transmit beam within the previous time instant window using AI or ML models for beam management. The AI or ML model for beam management may be an AI or ML model based on Long Short Term Memory (LSTM). Alternatively, the AI or ML model for beam management may be a Deep Neural Network (DNN) with multiple fully connected hidden layers or a Convolutional Neural Network (CNN) with one-dimensional convolutional layers. For example, a DNN with more than 4 hidden layers may be used to predict signal strength parameters associated with all receive or transmit beams of a UE from which the best receive or transmit beam of the UE may be identified.

Embodiment when deploying AI/ML model for beam management at BS

In some embodiments, when the AI/ML model for beam management is deployed at the BS, the BS may repeatedly transmit the first reference signal to the UE through its designated transmit beam, receive a signal strength parameter of the first reference signal from the UE associated with each of the subset of receive beams of the UE, and predict an optimal receive beam of the UE corresponding to the designated transmit beam of the BS using the AI/ML model for beam management based on the signal strength parameter of the first reference signal associated with each of the subset of receive beams of the UE, wherein the optimal receive beam of the UE corresponding to the designated transmit beam of the BS is the receive beam of the UE or is a receive beam other than any of the subset of receive beams of the UE.

In some embodiments, when triggered by the UE to repeatedly transmit the first reference signal over its designated transmit beam, the BS may repeatedly transmit the first reference signal over its designated transmit beam.

In some embodiments, the BS may also transmit a plurality of first reference signals to the UE through respective transmit beams of its transmit beam subset, receive signal strength parameters of the plurality of first reference signals associated with one or more receive beams of the UE from the UE, and predict an optimal transmit beam of the BS corresponding to the one or more receive beams of the UE using an AI or ML model for beam management based on the signal strength parameters of the plurality of first reference signals associated with the one or more receive beams of the UE, wherein the optimal transmit beam of the BS corresponding to the one or more receive beams of the UE is the transmit beam of the transmit beam subset of the BS or is a transmit beam other than any of the transmit beam subsets of the BS.

In some embodiments, the BS may also receive, from the UE, a beam quality parameter associated with a specified subset of transmit beams of the BS, wherein the beam quality parameter indicates the ability of the specified subset of transmit beams of the BS to transmit reference signals to one or more receive beams of the UE, and transmit a plurality of first reference signals to the UE over each of the above-described subset of transmit beams of the BS when the beam quality parameter associated with the specified subset of transmit beams of the BS falls below a second predetermined quality threshold.

Fig. 4 illustrates a schematic diagram of AI/ML assisted beam prediction at a BS using downlink measurements, according to some embodiments of the present disclosure. As shown in fig. 4, AI/ML assisted beam prediction at the BS using downlink measurements involves the following processes: the BS receives from the UE beam quality parameters associated with a specified subset of transmit beams of the BS; when a beam quality parameter associated with a specified subset of transmit beams of the BS falls below a second predetermined quality threshold, the BS transmits a plurality of first reference signals to the UE over each of the transmit beams in the subset of transmit beams; and the BS receives from the UE a plurality of signal strength parameters of the first reference signals associated with one or more receive beams of the UE, and uses the signal strength parameters to predict an optimal transmit beam of the BS corresponding to the one or more receive beams of the UE.

In some embodiments, the BS may also receive one or more second reference signals repeatedly transmitted by one or more transmit beams of the UE, determine signal strength parameters of the one or more second reference signals associated with respective receive beams of a subset of receive beams of the BS, and predict an optimal receive beam of the BS corresponding to the one or more transmit beams of the UE using an AI or ML model for beam management based on the signal strength parameters of the one or more second reference signals associated with respective receive beams of the subset of receive beams of the BS, the optimal receive beam of the BS corresponding to the one or more transmit beams of the UE being the receive beam of the BS or the receive beam of any of the subset of receive beams other than the BS.

Fig. 5 illustrates a schematic diagram of AI/ML assisted beam prediction at a BS using uplink measurements, according to some embodiments of the present disclosure. As shown in fig. 5, AI/ML assisted beam prediction at the BS using uplink measurements includes the following processes: the BS receives from the UE a plurality of second reference signals repeatedly transmitted by one or more transmit beams of the UE; the BS measures signal strength parameters of one or more second reference signals associated with each of a subset of receive beams of the BS and uses these signal strength parameters to predict an optimal receive beam of the BS corresponding to one or more transmit beams of the UE.

In some embodiments, the BS may also send a plurality of first reference signals to the UE over its transmit beam subset, receive signal strength parameters of the plurality of first reference signals associated with the receive beam subset of the UE from the UE, and predict an optimal beam-pair link between the UE and the BS based on the signal strength parameters of the plurality of first reference signals associated with the receive beam subset of the UE.

In some embodiments, the BS may also receive a plurality of second reference signals transmitted by the transmit beam subset of the UE using its receive beam subset, determine signal strength parameters of the plurality of second reference signals associated with each of the receive beams in the receive beam subset of the BS, and predict an optimal beam-to-link between the UE and the BS using an AI or ML model for beam management based on the signal strength parameters of the plurality of second reference signals associated with each of the receive beams in the receive beam subset of the BS.

Fig. 6 illustrates a schematic diagram of AI/ML assisted joint beam-to-link prediction at a BS according to some embodiments of the present disclosure. As shown in fig. 6, AI/ML assisted joint beam-to-link prediction at the BS includes the following processes:

set 1-downlink measurement and reporting: the BS transmitting a plurality of first reference signals to the UE over a subset of its transmit beams; the BS receives from the UE a plurality of signal strength parameters of the first reference signals associated with a subset of the receive beams of the UE and uses these signal strength parameters to predict an optimal beam-pair link between the UE and the BS.

Set 2-uplink measurements and reporting: the BS receives, from the UE, a plurality of second reference signals transmitted by a transmit beam subset of the UE using a receive beam subset thereof; the BS measures signal strength parameters of a plurality of second reference signals associated with each of a subset of the BS's receive beams and uses these signal strength parameters to predict an optimal beam-to-link between the UE and the BS.

In some embodiments, signal strength parameters associated with a subset of receive beams of the UE for the plurality of first reference signals may be reported to the BS with an L1 reporting matrix, wherein columns and rows of the L1 reporting matrix correspond to transmit beams of the BS and receive beams of the UE, respectively. Fig. 7 illustrates an example format of an L1 reporting matrix according to some embodiments of the present disclosure. As shown in fig. 7, the columns of the L1 reporting matrix correspond to the transmit beams of the BS, the rows of the L1 reporting matrix correspond to the receive beams of the UE, and the shaded boxes of the L1 reporting matrix carry signal strength parameters associated with the receive beam subset of the UE for a plurality of first reference signals transmitted by the transmit beam subset of the BS.

In some embodiments, the BS may also predict the BS's best receive or transmit beam for the next time instant based on the BS's best receive or transmit beam within the previous time instant window using AI or ML models for beam management. The AI or ML model for beam management may be an LSTM-based AI or ML model. Alternatively, the AI or ML model for beam management may be a DNN with multiple fully connected hidden layers or a CNN with one-dimensional convolution layers. For example, a DNN having more than 4 hidden layers may be used to predict signal strength parameters associated with all received or transmitted beams of a BS from which the best received or transmitted beam of the BS may be identified.

It should be appreciated that the subset of receive or transmit beams of the UE or BS includes part of the UE or BS instead of all of the receive or transmit beams, the first reference signal may be a channel state information reference signal (CSI-RS), the second reference signal may be a Sounding Reference Signal (SRS), the signal strength parameter of the first or second reference signal may be a Reference Signal Received Power (RSRP) parameter, and the BS may be a next generation node B (gNB).

Fig. 8-9 illustrate various systems, devices, and components that may implement aspects of the disclosed embodiments.

Fig. 8 illustrates a schematic diagram of a network 800, according to various embodiments of the disclosure. The network 800 may operate in accordance with the 3GPP technical specifications of a Long Term Evolution (LTE) or 5G/NR system. However, the example embodiments are not limited in this respect and the described embodiments may be applied to other networks that benefit from the principles described herein, such as future 3GPP systems, and the like.

The network 800 may include a UE 802, which may include any mobile or non-mobile computing device designed to communicate with a Radio Access Network (RAN) 804 via an over-the-air connection. The UE 802 may be, but is not limited to, a smart phone, tablet computer, wearable computer device, desktop computer, laptop computer, in-vehicle infotainment device, in-vehicle entertainment device, dashboard, heads-up display device, on-board diagnostic device, dashboard mobile device, mobile data terminal, electronic engine management system, electronic/engine control unit, electronic/engine control module, embedded system, sensor, microcontroller, control module, engine management system, network device, machine-to-machine (M2M) or device-to-device (D2D) device, internet of things (IoT) device, etc.

In some embodiments, the network 800 may include multiple UEs directly coupled to each other through a side link interface. The UE may be an M2M/D2D device that communicates using a physical sidelink channel (e.g., without limitation, a Physical Sidelink Broadcast Channel (PSBCH), a Physical Sidelink Discovery Channel (PSDCH), a Physical Sidelink Shared Channel (PSSCH), a Physical Sidelink Control Channel (PSCCH), a physical sidelink substrate channel (PSFCH), etc.).

In some embodiments, the UE 802 may also communicate with an Access Point (AP) 806 over an over-the-air connection. The AP 806 may manage Wireless Local Area Network (WLAN) connections, which may be used to offload some/all network traffic from the RAN 804. The connection between the UE 802 and the AP 806 may be consistent with any IEEE 802.11 protocol, where the AP 806 may be wireless fidelityAnd a router. In some embodiments, the UE 802, RAN 804, and AP 806 may utilize cellular WLAN aggregation (e.g., LTE-WLAN aggregation (LWA)/lightweight IP (LWIP)). Cellular WLAN aggregation may involve configuring the UE 802 by the RAN 804 to utilize both cellular radio resources and WLAN resources.

RAN 804 may include one or more access nodes, e.g., AN Access Node (AN) 808. The AN 808 may terminate the air interface protocol of the UE 802 by providing access layer protocols including a Radio Resource Control (RRC) protocol, a Packet Data Convergence Protocol (PDCP), a Radio Link Control (RLC) protocol, a Medium Access Control (MAC) protocol, and AN L1 protocol. In this way, the AN 808 may enable a data/voice connection between the Core Network (CN) 820 and the UE 802. In some embodiments, the AN 808 may be implemented in a discrete device or as one or more software entities running on a server computer (as part of a virtual network, which may be referred to as a distributed RAN (CRAN) or virtual baseband unit pool, for example). The AN 808 may be referred to as a Base Station (BS), a next generation base station (gNB), a RAN node, AN evolved node B (eNB), a next generation eNB (ng-eNB), a node B (NodeB), a roadside unit (RSU), a transmission reception point (TRxP), a transmission point (TRP), and the like. The AN 808 may be a macrocell base station or a low power base station for providing a microcell, picocell, or other similar cell having a smaller coverage area, smaller user capacity, or higher bandwidth than the macrocell.

In embodiments where the RAN 804 includes multiple ANs, the ANs may be coupled to each other through AN X2 interface (if the RAN 804 is AN LTE RAN) or AN Xn interface (if the RAN 804 is a 5G RAN). In some embodiments, the X2/Xn interface, which may be separated into control/user plane interfaces, may allow the AN to communicate information related to handoff, data/context transfer, mobility, load management, interference coordination, etc.

The AN of the RAN 804 may respectively manage one or more cells, groups of cells, component carriers, etc. to provide the UE 802 with AN air interface for network access. The UE 802 may be connected simultaneously with multiple cells provided by the same or different ANs of the RAN 804. For example, the UE 802 and the RAN 804 may use carrier aggregation to allow the UE 802 to connect with multiple component carriers, each component carrier corresponding to a primary cell (PCell) or a secondary cell (SCell). In a dual connectivity scenario, a first AN may be a primary node providing a primary cell group (MCG) and a second AN may be a secondary node providing a Secondary Cell Group (SCG). The first/second AN may be any combination of eNB, gNB, ng-enbs, etc.

RAN 804 may provide the air interface on licensed spectrum or unlicensed spectrum. To operate in unlicensed spectrum, a node may use License Assisted Access (LAA), enhanced LAA (eLAA), and/or further enhanced LAA (feLAA) mechanisms based on Carrier Aggregation (CA) techniques of PCell/Scell. Prior to accessing the unlicensed spectrum, the node may perform a medium/carrier sensing operation based on, for example, a Listen Before Talk (LBT) protocol.

In a vehicle-to-everything (V2X) scenario, the UE 802 or AN 808 may be or act as a roadside unit (RSU), which may refer to any transport infrastructure entity for V2X communications. The RSU may be implemented in or by a suitable AN or stationary (or relatively stationary) UE. An RSU implemented in or by a UE may be referred to as a "UE-type RSU"; an RSU implemented in or by an eNB may be referred to as an "eNB-type RSU"; RSUs implemented in or by next generation nodebs (gnbs) may be referred to as "gNB-type RSUs" or the like. In one example, the RSU is a computing device coupled with a radio frequency circuit located at the roadside that provides connectivity support to passing vehicle UEs. The RSU may also include internal data storage circuitry for storing intersection map geometry, traffic statistics, media, and applications/software for sensing and controlling ongoing vehicle and pedestrian traffic. The RSU may provide very low latency communications required for high speed events (e.g., collision avoidance, traffic alerts, etc.). Additionally or alternatively, the RSU may provide other cellular/WLAN communication services. The components of the RSU may be enclosed in a weather-proof enclosure suitable for outdoor installation, and may include a network interface controller to provide a wired connection (e.g., ethernet) to a traffic signal controller or backhaul network.

In some embodiments, RAN 804 may be an LTE RAN 810 that includes an evolved node B (eNB), e.g., eNB 812.LTE RAN 810 may provide an LTE air interface with the following characteristics: subcarrier spacing (SCS) of 15 kHz; a single carrier frequency division multiple access (SC-FDMA) waveform for the Uplink (UL) and a cyclic prefix orthogonal frequency division multiplexing (CP-OFDM) waveform for the Downlink (DL); turbo code for data, TBCC for control, etc. The LTE air interface may rely on channel state information reference signals (CSI-RS) for CSI acquisition and beam management; PDSCH/PDCCH demodulation is performed in dependence on Physical Downlink Shared Channel (PDSCH)/Physical Downlink Control Channel (PDCCH) demodulation reference signals (DMRS); and relying on Cell Reference Signals (CRS) for cell search and initial acquisition, channel quality measurements, and channel estimation, and on channel estimation for coherent demodulation/detection at the UE. The LTE air interface may operate on the 6GHz sub-band.

In some embodiments, RAN 804 may be a Next Generation (NG) -RAN 814 with a gNB (e.g., gNB 816) or gn-eNB (e.g., NG-eNB 818). The gNB 816 may connect with 5G enabled UEs using a 5G NR interface. The gNB 816 may connect with the 5G core through a NG interface, which may include an N2 interface or an N3 interface. The NG-eNB 818 may also connect with the 5G core over the NG interface, but may connect with the UE over the LTE air interface. The gNB 816 and the ng-eNB 818 may be connected to each other via an Xn interface.

In some embodiments, the NG interface may be divided into two parts, a NG user plane (NG-U) interface that carries traffic data between the UPF 848 and the node of NG-RAN 814 (e.g., an N3 interface) and a NG control plane (NG-C) interface that is a signaling interface between the access and mobility management function (AMF) 844 and the node of NG-RAN 814 (e.g., an N2 interface).

NG-RAN 814 may provide a 5G-NR air interface with the following characteristics: a variable SCS; cyclic prefix-orthogonal frequency division multiplexing (CP-OFDM) for DL, CP-OFDM for UL, and DFT-s-OFDM; polarity, repetition, simplex, and reed-muller codes for control; and a low density parity check code (LDPC) for data. The 5G-NR air interface may rely on channel state reference signals (CSI-RS), PDSCH/PDCCH demodulation reference signals (DMRS) like the LTE air interface. The 5G-NR air interface may not use Cell Reference Signals (CRSs), but may use Physical Broadcast Channel (PBCH) demodulation reference signals (DMRS) for PBCH demodulation; phase tracking of PDSCH using Phase Tracking Reference Signals (PTRS); and performing time tracking using the tracking reference signal. The 5G-NR air interface may operate on an FR1 band including a 6GHz sub-band or an FR2 band including 24.25GHz to 52.6GHz bands. The 5G-NR air interface may include a synchronization signal and a PBCH block (SSB), which is a region of a downlink resource grid including a Primary Synchronization Signal (PSS)/Secondary Synchronization Signal (SSS)/PBCH.

In some embodiments, the 5G-NR air interface may use bandwidth part (BWP) for various purposes. For example, BWP may be used for dynamic adaptation of SCS. For example, the UE 802 may be configured with multiple BWP, where each BWP configuration has a different SCS. When the BWP change is indicated to the UE 802, the SCS of the transmission is also changed. Another use case of BWP relates to power saving. In particular, the UE 802 may be configured with multiple BWPs having different numbers of frequency resources (e.g., PRBs) to support data transmission in different traffic load scenarios. BWP containing a smaller number of PRBs may be used for data transmission with smaller traffic load while allowing power saving at the UE 802 and in some cases the gNB 816. BWP comprising a large number of PRBs may be used for scenarios with higher traffic load.

The RAN 804 is communicatively coupled to a CN 820 that includes network elements to provide various functions to support data and telecommunications services to clients/subscribers (e.g., users of the UE 802). The components of CN 820 may be implemented in one physical node or in a different physical node. In some embodiments, network Function Virtualization (NFV) may be used to virtualize any or all of the functions provided by the network elements of CN 820 onto physical computing/storage resources in servers, switches, etc. The logical instance of the CN 820 may be referred to as a network slice, and the logical instance of a portion of the CN 820 may be referred to as a network sub-slice.

In some embodiments, CN 820 may be LTE CN 822, which may also be referred to as Evolved Packet Core (EPC). LTE CN 822 may include a Mobility Management Entity (MME) 824, a Serving Gateway (SGW) 826, a serving General Packet Radio Service (GPRS) support node (SGSN) 828, a Home Subscriber Server (HSS) 830, a Proxy Gateway (PGW) 832, and a policy control and charging rules function (PCRF) 834, which are coupled to each other through an interface (or "reference point") as shown. The function of the elements of LTE CN 822 may be briefly described as follows.

The MME 824 may implement mobility management functions to track the current location of the UE 802 to facilitate paging, bearer activation/deactivation, handover, gateway selection, authentication, and the like.

SGW 826 may terminate the S1 interface towards the RAN and route data packets between the RAN and LTE CN 822. SGW 826 may be a local mobility anchor for inter-RAN node handover and may also provide an anchor for inter-3 GPP mobility. Other responsibilities may include lawful interception, billing, and some policy enforcement.

SGSN 828 may track the location of UE 802 and perform security functions and access control. In addition, SGSN 828 may perform EPC inter-node signaling for mobility between different Radio Access Technology (RAT) networks; MME 824 specified PDN and S-GW selection; MME selection for handover, etc. The S3 reference point between MME 824 and SGSN 828 may enable user and bearer information exchange for inter-3 GPP network mobility in the idle/active state.

HSS 830 may include a database for network users that includes subscription-related information that supports network entity handling communication sessions. HSS 830 may provide support for routing/roaming, authentication, authorization, naming/addressing resolution, location dependencies, and so on. The S6a reference point between HSS 830 and MME 824 may enable the transmission of subscription and authentication data for authenticating/authorizing user access to LTE CN 820.

PGW 832 may terminate the SGi interface towards Data Network (DN) 836, which may include application/content server 838. PGW 832 may route data packets between LTE CN 822 and data network 836. PGW 832 may be coupled to SGW 826 via S5 reference points to facilitate user plane tunneling and tunnel management. PGW 832 may also include nodes (e.g., PCEFs) for policy enforcement and charging data collection. In addition, the SGi reference point between PGW 832 and data network 836 may be, for example, an operator external public, private PDN, or an operator internal packet data network for providing IP Multimedia Subsystem (IMS) services. PGW 832 may be coupled with PCRF 834 via a Gx reference point.

PCRF 834 is a policy and charging control element of LTE CN 822. PCRF 834 may be communicatively coupled to application/content server 838 to determine appropriate quality of service (QoS) and charging parameters for the service flows. PCRF 832 may provide the relevant rules to a PCEF (via a Gx reference point) with appropriate Traffic Flow Templates (TFTs) and QoS Class Identifiers (QCIs).

In some embodiments, CN 820 may be a 5G core network (5 GC) 840. The 5gc 840 may include an authentication server function (AUSF) 842, an access and mobility management function (AMF) 844, a Session Management Function (SMF) 846, a User Plane Function (UPF) 848, a Network Slice Selection Function (NSSF) 850, a network open function (NEF) 852, an NF storage function (NRF) 854, a Policy Control Function (PCF) 856, a Unified Data Management (UDM) 858, and an Application Function (AF) 860, coupled to each other through an interface (or "reference point") as shown. The function of the elements of the 5gc 840 may be briefly described as follows.

The AUSF 842 may store data for authentication of the UE 802 and process authentication related functions. The AUSF 842 may facilitate a common authentication framework for various access types. In addition to communicating with other elements of the 5gc 840 through reference points as shown, the AUSF 842 may also present an interface based on the Nausf service.

The AMF 844 may allow other functions of the 5gc 840 to communicate with the UE 802 and RAN 804 and subscribe to notifications about mobility events of the UE 802. The AMF 844 may be responsible for registration management (e.g., registering the UE 802), connection management, reachability management, mobility management, lawful intercept AMF related events, and access authentication and authorization. The AMF 844 may provide transport of Session Management (SM) messages between the UE 802 and the SMF 846 and act as a transparent proxy for routing SM messages. AMF 844 may also provide for transmission of SMS messages between UE 802 and SMSF. The AMF 844 may interact with the AUSF 842 and the UE 802 to perform various security anchoring and context management functions. Furthermore, the AMF 844 may be an end point of the RAN CP interface, which may include or be an N2 reference point between the RAN 804 and the AMF 844; the AMF 844 may act as an endpoint for NAS (N1) signaling and perform NAS ciphering and integrity protection. The AMF 844 may also support NAS signaling with the UE 802 over the N3 IWF interface.

The SMF 846 may be responsible for SM (e.g., tunnel management, session establishment between UPF 848 and AN 808); UE IP address allocation and management (including optional authorization); selection and control of the UP function; configuring flow control at UPF 848 to route traffic to an appropriate destination; termination of the interface to the policy control function; control policy enforcement, charging, and a portion of QoS; legal interception (for SM events and interfaces to LI systems); terminating the SM portion of the NAS message; downlink data notification; AN-specific SM information is initiated (sent over N2 to AN 808 via AMF 844); and determining the SSC mode of the session. SM may refer to the management of PDU sessions, and PDU sessions or "sessions" may refer to PDU connectivity services that provide or enable PDU exchanges between UE 802 and data network 836.

The UPF 848 may serve as an anchor point for intra-RAT and inter-RAT mobility, an external PDU session point interconnected with the data network 836, and a branching point to support multi-homing PDU sessions. The UPF 848 may also perform packet routing and forwarding, perform packet inspection, perform user plane parts of policy rules, lawful interception packets (UP collection), perform traffic usage reporting, perform QoS processing for the user plane (e.g., packet filtering, gating, UL/DL rate enforcement), perform uplink traffic verification (e.g., SDF to QoS flow mapping), transport layer packet tagging in the uplink and downlink, and perform downlink packet buffering and downlink data notification triggering. The UPF 848 may include an uplink classifier to support routing traffic flows to the data network.

NSSF 850 may select a set of network slice instances that serve UE 802. NSSF 850 may also determine the allowed Network Slice Selection Assistance Information (NSSAI) and the mapping to subscribed individual NSSAIs (S-NSSAIs), if desired. NSSF 850 may also determine the set of AMFs to use for serving UE 802, or a list of candidate AMFs, based on a suitable configuration and possibly by querying NRF 854. The selection of a set of network slice instances for UE 802 may be triggered by AMF 844 (with which UE 802 registers by interacting with NSSF 850), which may result in a change in AMF. NSSF 850 may interact with AMF 844 via the N22 reference point; and may communicate with another NSSF in the visited network via an N31 reference point (not shown). In addition, NSSF 850 may expose an interface based on the Nnssf service.

The NEF 852 may securely disclose services and capabilities provided by 3GPP network functions for third parties, internal exposure/re-exposure, AF (e.g., AF 860), edge computing or fog computing systems, etc. In these embodiments, NEF 852 can authenticate, authorize, or restrict AF. NEF 852 can also translate information exchanged with AF 860 and information exchanged with internal network functions. For example, the NEF 852 may translate between an AF service identifier and internal 5GC information. The NEF 852 can also receive information from other NF based on the other NF's public capabilities. This information may be stored as structured data at NEF 852 or at data storage NF using a standardized interface. The NEF 852 can then re-expose the stored information to other NF and AF, or for other purposes such as analysis. In addition, NEF 852 may expose an interface based on Nnef services.

NRF 854 may support a service discovery function, receive NF discovery requests from NF instances, and provide information of discovered NF instances to NF instances. NRF 854 also maintains information of available NF instances and services supported by it. As used herein, the terms "instantiate," "instance," and the like may refer to creating an instance, "instance" may refer to a specific occurrence of an object, which may occur, for example, during execution of program code. In addition, NRF 854 may expose an interface based on Nnrf services.

PCF 856 may provide policy rules to control plane functions to enforce those policy rules and may also support a unified policy framework to manage network behavior. PCF 856 may also implement a front end to access subscription information related to policy decisions in the UDR of UDM 858. In addition to communicating with functions through reference points as shown, PCF 856 also presents an interface based on an Npcf service.

The UDM 858 may process subscription-related information to support network entities in handling communication sessions and may store subscription data for the UE 802. For example, subscription data may be transferred via an N8 reference point between UDM 858 and AMF 844. UDM 858 may include two parts: application front-end and User Data Record (UDR). The UDR may store policy data and subscription data for the UDM 858 and PCF 856, and/or structured data and application data for the NEF 852 for exposure (including PFD for application detection, application request information for multiple UEs 802). The UDR may expose an interface based on Nudr services to allow the UDM 858, PCF 856, and NEF 852 to access specific sets of stored data, as well as to read, update (e.g., add, modify), delete, and subscribe to notifications of related data changes in the UDR. The UDM may include a UDM-FE (UDM front end) that is responsible for handling credentials, location management, subscription management, etc. Several different front ends may serve the same user in different transactions. The UDM-FE accesses subscription information stored in the UDR and performs authentication credential processing, user identification processing, access authorization, registration/mobility management, and subscription management. In addition to communicating with other NFs through reference points as shown, the UDM 858 may also expose a Nudm service-based interface.

AF 860 may provide application impact on traffic routing, provide access to the NEF, and interact with the policy framework for policy control.

In some embodiments, the 5gc 840 may enable edge computation by selecting an operator/third party service that is geographically close to the point where the UE 802 connects to the network. This may reduce delay and load on the network. To provide edge computing implementations, the 5gc 840 may select a UPF 848 near the UE 802 and perform traffic steering from the UPF 848 to the data network 836 over the N6 interface. This may be based on UE subscription data, UE location, and information provided by AF 860. Thus, AF 860 may affect UPF (re) selection and traffic routing. Based on the operator deployment, the network operator may allow the AF 860 to interact directly with the associated NF when the AF 860 is considered a trusted entity. In addition, AF 860 may expose Naf service-based interfaces.

The data network 836 may represent various network operator services, internet access, or third party services that may be provided by one or more servers, including, for example, application/content servers 838.

Fig. 9 schematically illustrates a wireless network 900 according to various embodiments. The wireless network 900 may include a UE 902 in wireless communication with AN 904. The UE 902 and the AN 904 may be similar to and substantially interchangeable with the synonym components described elsewhere herein.

The UE 902 may be communicatively coupled with the AN 904 via a connection 906. Connection 906 is shown as an air interface to enable communicative coupling and may operate at millimeter wave or below 6GHz frequencies in accordance with a cellular communication protocol such as the LTE protocol or the 5G NR protocol.

The UE 902 may include a host platform 908 coupled to a modem platform 910. Host platform 908 may include application processing circuitry 912, which may be coupled with protocol processing circuitry 914 of modem platform 910. The application processing circuitry 912 may run various applications for the UE 902 to acquire/receive its application data. The application processing circuitry 912 may also implement one or more layers of operations to transmit and receive application data to and from a data network. These layer operations may include transport (e.g., UDP) and internet (e.g., IP) operations.

Protocol processing circuit 914 may implement one or more layers of operations to facilitate the transmission or reception of data over connection 906. Layer operations implemented by the protocol processing circuit 914 may include, for example, medium Access Control (MAC), radio Link Control (RLC), packet Data Convergence Protocol (PDCP), radio Resource Control (RRC), and non-access stratum (NAS) operations.

The modem platform 910 may further include digital baseband circuitry 916, which digital baseband circuitry 916 may implement one or more layer operations "below" the layer operations performed by the protocol processing circuitry 914 in the network protocol stack. These operations may include, for example, PHY operations including one or more of HARQ-ACK functions, scrambling/descrambling, encoding/decoding, layer mapping/demapping, modulation symbol mapping, received symbol/bit metric determination, multi-antenna port precoding/decoding, where these functions may include one or more of space-time, space-frequency, or spatial coding, reference signal generation/detection, preamble sequence generation and/or decoding, synchronization sequence generation/detection, control channel signal blind decoding, and other related functions.

The modem platform 910 may further include transmit circuitry 918, receive circuitry 920, RF circuitry 922, and RF front end (RFFE) circuitry 924, which may include or be connected to one or more antenna panels 926. Briefly, transmit circuitry 918 may include a digital-to-analog converter, a mixer, an Intermediate Frequency (IF) component, and the like; the receive circuitry 920 may include analog-to-digital converters, mixers, IF components, etc.; RF circuitry 922 may include low noise amplifiers, power tracking components, and the like; RFFE circuit 924 may include filters (e.g., surface/bulk acoustic wave filters), switches, antenna tuners, beam forming components (e.g., phased array antenna components), and so forth. The selection and arrangement of the components of transmit circuitry 918, receive circuitry 920, RF circuitry 922, RFFE circuitry 924, and antenna panel 926 (collectively referred to as "transmit/receive components") may be specific to the specifics of a particular implementation, e.g., whether the communication is Time Division Multiplexed (TDM) or Frequency Division Multiplexed (FDM), at mmWave or below 6GHz frequencies, etc. In some embodiments, the transmit/receive components may be arranged in a plurality of parallel transmit/receive chains, and may be arranged in the same or different chips/modules, etc.

In some embodiments, the protocol processing circuit 914 may include one or more instances of control circuitry (not shown) to provide control functions for the transmit/receive components.

UE reception may be established through and via antenna panel 926, RFFE circuitry 924, RF circuitry 922, receive circuitry 920, digital baseband circuitry 916, and protocol processing circuitry 914. In some embodiments, the antenna panel 926 may receive transmissions from the AN 904 by receiving beamformed signals received by multiple antennas/antenna elements of one or more antenna panels 926.

UE transmissions may be established via and through the protocol processing circuitry 914, digital baseband circuitry 916, transmit circuitry 918, RF circuitry 922, RFFE circuitry 924, and antenna panel 926. In some embodiments, the transmit component of the UE 902 may apply spatial filtering to the data to be transmitted to form transmit beams that are transmitted by the antenna elements of the antenna panel 926.

Similar to the UE 902, the AN 904 may include a host platform 928 coupled to a modem platform 930. Host platform 928 may include application processing circuitry 932 coupled to protocol processing circuitry 934 of modem platform 930. The modem platform may also include digital baseband circuitry 936, transmit circuitry 938, receive circuitry 940, RF circuitry 942, RFFE circuitry 944, and an antenna panel 946. The components of the AN 904 may be similar to the like-named components of the UE 902 and may be substantially interchangeable with the like-named components of the UE 902. In addition to performing data transmission/reception as described above, the components of the AN 904 may perform various logic functions including, for example, radio Network Controller (RNC) functions such as radio bearer management, uplink and downlink dynamic radio resource management, and data packet scheduling.

Fig. 10 is a block diagram illustrating components capable of reading instructions from a machine-readable or computer-readable medium (e.g., a non-transitory machine-readable storage medium) and performing any one or more of the methods discussed herein, according to some example embodiments. In particular, fig. 10 shows a schematic diagram of a hardware resource 1000, the hardware resource 1000 comprising one or more processors (or processor cores) 1010, one or more memory/storage devices 1020, and one or more communication resources 1030, wherein each of these processors, memory/storage devices, and communication resources may be communicatively coupled via a bus 1040 or other interface circuitry. For embodiments that utilize node virtualization, such as Network Function Virtualization (NFV), the hypervisor 1002 may be executed to provide an execution environment for one or more network slices/sub-slices to utilize the hardware resources 1000.

Processor 1010 may include, for example, a processor 1012 and a processor 1014. The processor 1010 may be, for example, a Central Processing Unit (CPU), a Reduced Instruction Set Computing (RISC) processor, a Complex Instruction Set Computing (CISC) processor, a Graphics Processing Unit (GPU), a Digital Signal Processor (DSP) such as a baseband processor, an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), a Radio Frequency Integrated Circuit (RFIC), another processor (including those discussed herein), or any suitable combination thereof.

Memory/storage 1020 may include main memory, a disk storage device, or any suitable combination thereof. Memory/storage 1020 may include, but is not limited to, any type of volatile, nonvolatile, or semi-volatile memory such as Dynamic Random Access Memory (DRAM), static Random Access Memory (SRAM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory, solid state memory, and the like.

The communication resources 1030 may include interconnection or network interface controllers, components, or other suitable devices to communicate with one or more peripheral devices 1004 or one or more databases 1006 or other network elements via the network 1008. For example, the communication resources 1030 may include wired communication components (e.g., for coupling via USB, ethernet, etc.), cellular communication components, near Field Communication (NFC) components, and the like,(or->Low energy) component, < >>Components, and other communication components.

The instructions 1050 may include software, programs, applications, applets, applications, or other executable code for causing at least any one of the processors 1010 to perform any one or more of the methods discussed herein. The instructions 1050 may reside, completely or partially, within at least one of the processor 1010 (e.g., in a cache of a processor), the memory/storage 1020, or any suitable combination thereof. Further, any portion of instructions 1050 may be transferred from any combination of peripherals 1004 or databases 1006 to hardware resource 1000. Accordingly, the memory of the processor 1010, the memory/storage 1020, the peripherals 1004, and the database 1006 are examples of computer readable and machine readable media.

The following paragraphs describe examples of various embodiments.

Example 1 includes an apparatus for Artificial Intelligence (AI) or Machine Learning (ML) -assisted beam management, wherein the apparatus is for use in a User Equipment (UE) and comprises processor circuitry configured to cause the UE to: receiving a first reference signal repeatedly transmitted by a designated transmission beam of a Base Station (BS); determining signal strength parameters of the first reference signal associated with each of a subset of receive beams of the UE; and predicting a best receive beam of the UE corresponding to the specified transmit beam of the BS using an AI or ML model for beam management based on signal strength parameters of the first reference signal associated with each of the subset of receive beams of the UE, wherein the best receive beam of the UE corresponding to the specified transmit beam of the BS is either a receive beam of the subset of receive beams of the UE or a receive beam different from either of the subset of receive beams of the UE.

Example 2 includes the apparatus of example 1, wherein the processor circuit is further configured to cause the UE to: determining a beam quality parameter associated with a designated receive beam of the UE, wherein the beam quality parameter indicates a capability of the designated receive beam of the UE to receive a reference signal transmitted by a designated transmit beam of the BS; and triggering the BS to repeatedly transmit the first reference signal through a designated transmission beam of the BS when the beam quality parameter falls below a predetermined quality threshold.

Example 3 includes the apparatus of example 1, wherein the processor circuit is further configured to cause the UE to: receiving a plurality of first reference signals transmitted by respective transmit beams in a subset of transmit beams of the BS; determining signal strength parameters of the plurality of first reference signals associated with a designated receive beam of the UE; and predicting a best transmit beam of the BS corresponding to the designated receive beam of the UE using the AI or ML model for beam management based on signal strength parameters of the plurality of first reference signals associated with the designated receive beam of the UE, wherein the best transmit beam of the BS corresponding to the designated receive beam of the UE is a transmit beam of a subset of transmit beams of the BS or a transmit beam different from any of the subset of transmit beams of the BS.

Example 4 includes the apparatus of example 1, wherein the processor circuit is further configured to cause the UE to: repeatedly transmitting a second reference signal to the BS through a designated transmission beam of the UE; receiving from the BS signal strength parameters of the second reference signal associated with each of a subset of the BS's receive beams; and predicting a best receive beam of the BS corresponding to the designated transmit beam of the UE using the AI or ML model for beam management based on signal strength parameters of the second reference signal associated with each of the subset of receive beams of the BS, wherein the best receive beam of the BS corresponding to the designated transmit beam of the UE is either a receive beam of the subset of receive beams of the BS or a receive beam different from any of the subset of receive beams of the BS.

Example 5 includes the apparatus of example 1, wherein the processor circuit is further configured to cause the UE to: receiving a plurality of first reference signals transmitted by respective transmit beams in a subset of transmit beams of the BS; determining signal strength parameters of the plurality of first reference signals associated with respective receive beams of a subset of receive beams of the UE; and predicting an optimal beam-pair link between the UE and the BS using the AI or ML model for beam management based on signal strength parameters of the plurality of first reference signals associated with each of a subset of receive beams of the UE.

Example 6 includes the apparatus of example 1, wherein the processor circuit is further configured to cause the UE to: transmitting a plurality of second reference signals to the BS over respective transmit beams of the subset of transmit beams of the UE; receiving, from the BS, signal strength parameters of the plurality of second reference signals associated with each of a subset of receive beams of the BS; and predicting an optimal beam-pair link between the UE and the BS using the AI or ML model for beam management based on signal strength parameters of the plurality of second reference signals associated with each of a subset of receive beams of the BS.

Example 7 includes the apparatus of example 1, wherein the processor circuit is further configured to cause the UE to: based on the best receive or transmit beam of the UE within the previous time window, the AI or ML model for beam management is used to predict the best receive or transmit beam of the UE for the next time.

Example 8 includes the apparatus of example 7, wherein the AI or ML model for beam management is an AI or ML model based on long term memory (LSTM).

Example 9 includes the apparatus of example 7, wherein the AI or ML model for beam management is a Deep Neural Network (DNN) with multiple fully connected hidden layers or a Convolutional Neural Network (CNN) with one-dimensional convolutional layers.

Example 10 includes the apparatus of example 6, wherein the signal strength parameters of the plurality of second reference signals associated with each of the subset of receive beams of the BS are reported to the UE using an L1 reporting matrix, wherein columns and rows of the L1 reporting matrix correspond to the receive beam of the BS and the transmit beam of the UE, respectively.

Example 11 includes an apparatus for Artificial Intelligence (AI) or Machine Learning (ML) -assisted beam management, wherein the apparatus is for use in a Base Station (BS) and comprises processor circuitry configured to cause the BS to: repeatedly transmitting a first reference signal to a User Equipment (UE) through a designated transmission beam of the BS; receiving, from the UE, signal strength parameters of the first reference signal associated with each of a subset of receive beams of the UE; and predicting a best receive beam of the UE corresponding to the specified transmit beam of the BS using an AI or ML model for beam management based on signal strength parameters of the first reference signal associated with each of the subset of receive beams of the UE, wherein the best receive beam of the UE corresponding to the specified transmit beam of the BS is either a receive beam of the subset of receive beams of the UE or a receive beam different from either of the subset of receive beams of the UE.

Example 12 includes the apparatus of example 11, wherein the processor circuit is further configured to cause the BS to: and repeatedly transmitting the first reference signal through the appointed transmission beam of the BS when the first reference signal is triggered by the UE through the appointed transmission beam of the BS.

Example 13 includes the apparatus of example 11, wherein the processor circuit is further configured to cause the BS to: transmitting a plurality of first reference signals to the UE over respective transmit beams of a subset of transmit beams of the BS; receiving, from the UE, signal strength parameters of the plurality of first reference signals associated with one or more receive beams of the UE; and predicting, based on signal strength parameters of the plurality of first reference signals associated with one or more receive beams of the UE, a best transmit beam of the BS corresponding to the one or more receive beams of the UE using the AI or ML model for beam management, wherein the best transmit beam of the BS corresponding to the one or more receive beams of the UE is a transmit beam of the subset of transmit beams of the BS or a transmit beam different from any of the subset of transmit beams of the BS.

Example 14 includes the apparatus of example 13, wherein the processor circuit is further configured to cause the BS to: receiving, from the UE, beam quality parameters associated with a specified subset of transmit beams of the BS, wherein the beam quality parameters indicate the ability of the specified subset of transmit beams of the BS to transmit reference signals to one or more receive beams of the UE; and transmitting the plurality of first reference signals to the UE over each transmit beam of the subset of transmit beams of the BS when a beam quality parameter associated with a designated transmit beam of the BS falls below a predetermined quality threshold.

Example 15 includes the apparatus of example 11, wherein the processor circuit is further configured to cause the BS to: receiving one or more second reference signals repeatedly transmitted by one or more transmit beams of the UE; determining signal strength parameters of the one or more second reference signals associated with respective receive beams of the subset of receive beams of the BS; and predicting, based on signal strength parameters of the one or more second reference signals associated with each of a subset of receive beams of the BS, a best receive beam of the BS corresponding to the one or more transmit beams of the UE using the AI or ML model for beam management, wherein the best receive beam of the BS corresponding to the one or more transmit beams of the UE is a receive beam of the subset of receive beams of the BS or a receive beam different from any of the subset of receive beams of the BS.

Example 16 includes the apparatus of example 11, wherein the processor circuit is further configured to: transmitting a plurality of first reference signals to the UE over a subset of transmit beams of the BS; receiving, from the UE, signal strength parameters of the plurality of first reference signals associated with a subset of receive beams of the UE; and predicting an optimal beam-pair link between the UE and the BS using the AI or ML model for beam management based on signal strength parameters of the plurality of first reference signals associated with a subset of receive beams of the UE.

Example 17 includes the apparatus of example 11, wherein the processor circuit is further configured to: receiving a plurality of second reference signals transmitted by a transmit beam subset of the UE using a receive beam subset of the BS; determining signal strength parameters of the plurality of second reference signals associated with respective receive beams of the subset of receive beams of the BS; and predicting an optimal beam-pair link between the UE and the BS using the AI or ML model for beam management based on signal strength parameters of the plurality of second reference signals associated with each of a subset of receive beams of the BS.

Example 18 includes the apparatus of example 11, wherein the processor circuit is further configured to cause the BS to: based on the BS's best receive or transmit beam within the previous time window, the AI or ML model for beam management is used to predict the BS's best receive or transmit beam for the next time.

Example 19 includes the apparatus of example 18, wherein the AI or ML model for beam management is an AI or ML model based on long term memory (LSTM).

Example 20 includes the apparatus of example 18, wherein the AI or ML model for beam management is a Deep Neural Network (DNN) with multiple fully connected hidden layers or a Convolutional Neural Network (CNN) with one-dimensional convolutional layers.

Example 21 includes the apparatus of example 16, wherein signal strength parameters of the plurality of first reference signals associated with a subset of receive beams of the UE are reported to the BS using an L1 reporting matrix, wherein columns and rows of the L1 reporting matrix correspond to transmit beams of the BS and receive beams of the UE, respectively.

Example 22 includes a method for Artificial Intelligence (AI) or Machine Learning (ML) -assisted beam management, wherein the method is for use in a User Equipment (UE) and comprises: receiving a first reference signal repeatedly transmitted by a designated transmission beam of a Base Station (BS); determining signal strength parameters of the first reference signal associated with each of a subset of receive beams of the UE; and predicting a best receive beam of the UE corresponding to the specified transmit beam of the BS using an AI or ML model for beam management based on signal strength parameters of the first reference signal associated with each of the subset of receive beams of the UE, wherein the best receive beam of the UE corresponding to the specified transmit beam of the BS is either a receive beam of the subset of receive beams of the UE or a receive beam different from either of the subset of receive beams of the UE.

Example 23 includes the method of example 22, wherein the method further comprises: determining a beam quality parameter associated with a designated receive beam of the UE, wherein the beam quality parameter indicates a capability of the designated receive beam of the UE to receive a reference signal transmitted by a designated transmit beam of the BS; and triggering the BS to repeatedly transmit the first reference signal through a designated transmission beam of the BS when the beam quality parameter falls below a predetermined quality threshold.

Example 24 includes the method of example 22, wherein the method further comprises: receiving a plurality of first reference signals transmitted by respective transmit beams in a subset of transmit beams of the BS; determining signal strength parameters of the plurality of first reference signals associated with a designated receive beam of the UE; and predicting a best transmit beam of the BS corresponding to the designated receive beam of the UE using the AI or ML model for beam management based on signal strength parameters of the plurality of first reference signals associated with the designated receive beam of the UE, wherein the best transmit beam of the BS corresponding to the designated receive beam of the UE is a transmit beam of a subset of transmit beams of the BS or a transmit beam different from any of the subset of transmit beams of the BS.

Example 25 includes the method of example 22, wherein the method further comprises: repeatedly transmitting a second reference signal to the BS through a designated transmission beam of the UE; receiving from the BS signal strength parameters of the second reference signal associated with each of a subset of the BS's receive beams; and predicting a best receive beam of the BS corresponding to the designated transmit beam of the UE using the AI or ML model for beam management based on signal strength parameters of the second reference signal associated with each of the subset of receive beams of the BS, wherein the best receive beam of the BS corresponding to the designated transmit beam of the UE is either a receive beam of the subset of receive beams of the BS or a receive beam different from any of the subset of receive beams of the BS.

Example 26 includes the method of example 22, wherein the method further comprises: receiving a plurality of first reference signals transmitted by respective transmit beams in a subset of transmit beams of the BS; determining signal strength parameters of the plurality of first reference signals associated with respective receive beams of a subset of receive beams of the UE; and predicting an optimal beam-pair link between the UE and the BS using the AI or ML model for beam management based on signal strength parameters of the plurality of first reference signals associated with each of a subset of receive beams of the UE.

Example 27 includes the method of example 22, wherein the method further comprises: transmitting a plurality of second reference signals to the BS over respective transmit beams of the subset of transmit beams of the UE; receiving, from the BS, signal strength parameters of the plurality of second reference signals associated with each of a subset of receive beams of the BS; and predicting an optimal beam-pair link between the UE and the BS using the AI or ML model for beam management based on signal strength parameters of the plurality of second reference signals associated with each of a subset of receive beams of the BS.

Example 28 includes the method of example 22, wherein the method further comprises: based on the best receive or transmit beam of the UE within the previous time window, the AI or ML model for beam management is used to predict the best receive or transmit beam of the UE for the next time.

Example 29 includes the method of example 28, wherein the AI or ML model for beam management is an AI or ML model based on long term memory (LSTM).

Example 30 includes the method of example 28, wherein the AI or ML model for beam management is a Deep Neural Network (DNN) with multiple fully connected hidden layers or a Convolutional Neural Network (CNN) with one-dimensional convolutional layers.

Example 31 includes the method of example 27, wherein signal strength parameters of the plurality of second reference signals associated with each of the subset of receive beams of the BS are reported to the UE using an L1 reporting matrix, wherein columns and rows of the L1 reporting matrix correspond to the receive beam of the BS and the transmit beam of the UE, respectively.

Example 32 includes a method for Artificial Intelligence (AI) or Machine Learning (ML) -assisted beam management, wherein the method is used in a Base Station (BS) and comprises: repeatedly transmitting a first reference signal to a User Equipment (UE) through a designated transmission beam of the BS; receiving, from the UE, signal strength parameters of the first reference signal associated with each of a subset of receive beams of the UE; and predicting a best receive beam of the UE corresponding to the specified transmit beam of the BS using an AI or ML model for beam management based on signal strength parameters of the first reference signal associated with each of the subset of receive beams of the UE, wherein the best receive beam of the UE corresponding to the specified transmit beam of the BS is either a receive beam of the subset of receive beams of the UE or a receive beam different from either of the subset of receive beams of the UE.

Example 33 includes the method of example 32, wherein the method further comprises: and repeatedly transmitting the first reference signal through the appointed transmission beam of the BS when the first reference signal is triggered by the UE through the appointed transmission beam of the BS.

Example 34 includes the method of example 32, wherein the method further comprises: transmitting a plurality of first reference signals to the UE over respective transmit beams of a subset of transmit beams of the BS; receiving, from the UE, signal strength parameters of the plurality of first reference signals associated with one or more receive beams of the UE; and predicting, based on signal strength parameters of the plurality of first reference signals associated with one or more receive beams of the UE, a best transmit beam of the BS corresponding to the one or more receive beams of the UE using the AI or ML model for beam management, wherein the best transmit beam of the BS corresponding to the one or more receive beams of the UE is a transmit beam of the subset of transmit beams of the BS or a transmit beam different from any of the subset of transmit beams of the BS.

Example 35 includes the method of example 34, wherein the method further comprises: receiving, from the UE, beam quality parameters associated with a specified subset of transmit beams of the BS, wherein the beam quality parameters indicate the ability of the specified subset of transmit beams of the BS to transmit reference signals to one or more receive beams of the UE; and transmitting the plurality of first reference signals to the UE over each transmit beam of the subset of transmit beams of the BS when a beam quality parameter associated with a designated transmit beam of the BS falls below a predetermined quality threshold.

Example 36 includes the method of example 32, wherein the method further comprises: receiving one or more second reference signals repeatedly transmitted by one or more transmit beams of the UE; determining signal strength parameters of the one or more second reference signals associated with respective receive beams of the subset of receive beams of the BS; and predicting, based on signal strength parameters of the one or more second reference signals associated with each of a subset of receive beams of the BS, a best receive beam of the BS corresponding to the one or more transmit beams of the UE using the AI or ML model for beam management, wherein the best receive beam of the BS corresponding to the one or more transmit beams of the UE is a receive beam of the subset of receive beams of the BS or a receive beam different from any of the subset of receive beams of the BS.

Example 37 includes the method of example 32, wherein the method further comprises: transmitting a plurality of first reference signals to the UE over a subset of transmit beams of the BS; receiving, from the UE, signal strength parameters of the plurality of first reference signals associated with a subset of receive beams of the UE; and predicting an optimal beam-pair link between the UE and the BS using the AI or ML model for beam management based on signal strength parameters of the plurality of first reference signals associated with a subset of receive beams of the UE.

Example 38 includes the method of example 32, wherein the method further comprises: receiving a plurality of second reference signals transmitted by a transmit beam subset of the UE using a receive beam subset of the BS; determining signal strength parameters of the plurality of second reference signals associated with respective receive beams of the subset of receive beams of the BS; and predicting an optimal beam-pair link between the UE and the BS using the AI or ML model for beam management based on signal strength parameters of the plurality of second reference signals associated with each of a subset of receive beams of the BS.

Example 39 includes the method of example 32, wherein the method further comprises: based on the BS's best receive or transmit beam within the previous time window, the AI or ML model for beam management is used to predict the BS's best receive or transmit beam for the next time.

Example 40 includes the method of example 39, wherein the AI or ML model for beam management is an AI or ML model based on long term memory (LSTM).

Example 41 includes the method of example 39, wherein the AI or ML model for beam management is a Deep Neural Network (DNN) with multiple fully connected hidden layers or a Convolutional Neural Network (CNN) with one-dimensional convolutional layers.

Example 42 includes the method of example 37, wherein signal strength parameters of the plurality of first reference signals associated with a subset of receive beams of the UE are reported to the BS using an L1 reporting matrix, wherein columns and rows of the L1 reporting matrix correspond to transmit beams of the BS and receive beams of the UE, respectively.

Example 43 includes a computer-readable storage medium having stored thereon computer-executable instructions, wherein the computer-executable instructions, when executed by processor circuitry for use in a User Equipment (UE), cause the UE to implement the method of any of examples 22 to 31.

Example 44 includes a computer-readable storage medium having stored thereon computer-executable instructions, wherein the computer-executable instructions, when executed by processor circuitry used in a Base Station (BS), cause the BS to implement the method of any of examples 32 to 42.

Example 45 includes an apparatus for Artificial Intelligence (AI) or Machine Learning (ML) assisted beam management, wherein the apparatus is for use in a User Equipment (UE) and comprises means for implementing the method of any of examples 22-31.

Example 46 includes a User Equipment (UE) comprising processor circuitry configured to implement the method of any of examples 22 to 31.

Example 47 includes a User Equipment (UE) comprising means for implementing the method of any of examples 22 to 31.

Example 48 includes an apparatus for Artificial Intelligence (AI) or Machine Learning (ML) assisted beam management, wherein the apparatus is for use in a Base Station (BS) and comprises means for implementing the method of any of examples 32-42.

Example 49 includes a Base Station (BS) comprising processor circuitry configured to implement the method of any of examples 32 to 42.

Example 50 includes a Base Station (BS) comprising means for implementing the method of any of examples 32-42.

Although certain embodiments have been illustrated and described herein for purposes of description, a wide variety of alternate and/or equivalent embodiments or implementations calculated to achieve the same purposes may be substituted for the embodiments shown and described without departing from the scope of the present disclosure. This disclosure is intended to cover any adaptations or variations of the embodiments discussed herein. Accordingly, the embodiments described herein are obviously limited only by the following claims and equivalents thereof.

Claims

1. An apparatus for Artificial Intelligence (AI) or Machine Learning (ML) assisted beam management, wherein the apparatus is for use in a User Equipment (UE) and comprises processor circuitry configured to cause the UE to:

receiving a first reference signal repeatedly transmitted by a designated transmission beam of a Base Station (BS);

determining signal strength parameters of the first reference signal associated with each of a subset of receive beams of the UE; and

predicting an optimal receive beam of the UE corresponding to a designated transmit beam of the BS using an AI or ML model for beam management based on signal strength parameters of the first reference signal associated with each receive beam of a subset of receive beams of the UE, wherein

The best receive beam of the UE corresponding to the designated transmit beam of the BS is the receive beam of the subset of receive beams of the UE or is a receive beam different from any of the subset of receive beams of the UE.

2. The apparatus of claim 1, wherein the processor circuit is further configured to cause the UE to:

determining a beam quality parameter associated with a designated receive beam of the UE, wherein the beam quality parameter indicates a capability of the designated receive beam of the UE to receive a reference signal transmitted by a designated transmit beam of the BS; and

triggering the BS to repeatedly send the first reference signal through a designated transmission beam of the BS when the beam quality parameter falls below a preset quality threshold.

3. The apparatus of claim 1, wherein the processor circuit is further configured to cause the UE to:

receiving a plurality of first reference signals transmitted by respective transmit beams in a subset of transmit beams of the BS;

determining signal strength parameters of the plurality of first reference signals associated with a designated receive beam of the UE; and

predicting an optimal transmit beam of the BS corresponding to the designated receive beam of the UE using the AI or ML model for beam management based on signal strength parameters of the plurality of first reference signals associated with the designated receive beam of the UE, wherein

The best transmit beam of the BS corresponding to the designated receive beam of the UE is the transmit beam of the subset of transmit beams of the BS or the transmit beam different from any of the subset of transmit beams of the BS.

4. The apparatus of claim 1, wherein the processor circuit is further configured to cause the UE to:

repeatedly transmitting a second reference signal to the BS through a designated transmission beam of the UE;

receiving from the BS signal strength parameters of the second reference signal associated with each of a subset of the BS's receive beams; and

predicting an optimal receive beam of the BS corresponding to the designated transmit beam of the UE using the AI or ML model for beam management based on signal strength parameters of the second reference signal associated with each receive beam of the subset of receive beams of the BS, wherein

The best receive beam of the BS corresponding to the designated transmit beam of the UE is the receive beam of the subset of receive beams of the BS or is a receive beam different from any of the subset of receive beams of the BS.

5. The apparatus of claim 1, wherein the processor circuit is further configured to cause the UE to:

determining signal strength parameters of the plurality of first reference signals associated with respective receive beams of a subset of receive beams of the UE; and

the AI or ML model for beam management is used to predict an optimal beam-pair link between the UE and the BS based on signal strength parameters of the plurality of first reference signals associated with each of a subset of receive beams of the UE.

6. The apparatus of claim 1, wherein the processor circuit is further configured to cause the UE to:

transmitting a plurality of second reference signals to the BS over respective transmit beams of the subset of transmit beams of the UE;

receiving, from the BS, signal strength parameters of the plurality of second reference signals associated with each of a subset of receive beams of the BS; and

the AI or ML model for beam management is used to predict an optimal beam-pair link between the UE and the BS based on signal strength parameters of the plurality of second reference signals associated with each of a subset of receive beams of the BS.

7. The apparatus of claim 1, wherein the processor circuit is further configured to cause the UE to:

based on the best receive or transmit beam of the UE within the previous time window, the best receive or transmit beam of the UE is predicted for the next time using the AI or ML model for beam management.

8. The apparatus of claim 7, wherein the AI or ML model for beam management is an AI or ML model based on long term memory (LSTM).

9. The apparatus of claim 7, wherein the AI or ML model for beam management is a Deep Neural Network (DNN) with multiple fully connected hidden layers or a Convolutional Neural Network (CNN) with one-dimensional convolutional layers.

10. The apparatus of claim 6, wherein signal strength parameters of the plurality of second reference signals associated with respective receive beams of the subset of receive beams of the BS are reported to the UE using an L1 reporting matrix, wherein columns and rows of the L1 reporting matrix correspond to the receive beams of the BS and the transmit beams of the UE, respectively.

11. An apparatus for Artificial Intelligence (AI) or Machine Learning (ML) assisted beam management, wherein the apparatus is for use in a Base Station (BS) and comprises processor circuitry configured to cause the BS to:

Repeatedly transmitting a first reference signal to a User Equipment (UE) through a designated transmission beam of the BS;

receiving, from the UE, signal strength parameters of the first reference signal associated with each of a subset of receive beams of the UE; and

12. The apparatus of claim 11, wherein the processor circuit is further configured to cause the BS to:

and repeatedly transmitting the first reference signal through the appointed transmission beam of the BS when the first reference signal is triggered by the UE through the appointed transmission beam of the BS.

13. The apparatus of claim 11, wherein the processor circuit is further configured to cause the BS to:

Transmitting a plurality of first reference signals to the UE over respective transmit beams of a subset of transmit beams of the BS;

receiving, from the UE, signal strength parameters of the plurality of first reference signals associated with one or more receive beams of the UE; and

predicting an optimal transmit beam of the BS corresponding to one or more receive beams of the UE using the AI or ML model for beam management based on signal strength parameters of the plurality of first reference signals associated with the one or more receive beams of the UE, wherein

The best transmit beam of the BS corresponding to the one or more receive beams of the UE is the transmit beam of the transmit beam subset of the BS or is a transmit beam different from any of the transmit beam subsets of the BS.

14. The apparatus of claim 13, wherein the processor circuit is further configured to cause the BS to:

receiving, from the UE, beam quality parameters associated with a specified subset of transmit beams of the BS, wherein the beam quality parameters indicate the ability of the specified subset of transmit beams of the BS to transmit reference signals to one or more receive beams of the UE; and

The plurality of first reference signals are transmitted to the UE over respective transmit beams in a subset of transmit beams of the BS when beam quality parameters associated with the designated transmit beam of the BS fall below a predetermined quality threshold.

15. The apparatus of claim 11, wherein the processor circuit is further configured to cause the BS to:

receiving one or more second reference signals repeatedly transmitted by one or more transmit beams of the UE;

determining signal strength parameters of the one or more second reference signals associated with respective receive beams of the subset of receive beams of the BS; and

predicting an optimal receive beam of the BS corresponding to one or more transmit beams of the UE using the AI or ML model for beam management based on signal strength parameters of the one or more second reference signals associated with each receive beam of the subset of receive beams of the BS, wherein

The best receive beam of the BS corresponding to the one or more transmit beams of the UE is the receive beam of the subset of receive beams of the BS or is a receive beam different from any of the subset of receive beams of the BS.

16. The apparatus of claim 11, wherein the processor circuit is further configured to:

transmitting a plurality of first reference signals to the UE over a subset of transmit beams of the BS;

receiving, from the UE, signal strength parameters of the plurality of first reference signals associated with a subset of receive beams of the UE; and

the AI or ML model for beam management is used to predict an optimal beam-pair link between the UE and the BS based on signal strength parameters of the plurality of first reference signals associated with a subset of receive beams of the UE.

17. The apparatus of claim 11, wherein the processor circuit is further configured to:

receiving a plurality of second reference signals transmitted by a transmit beam subset of the UE using a receive beam subset of the BS;

determining signal strength parameters of the plurality of second reference signals associated with respective receive beams of the subset of receive beams of the BS; and

18. The apparatus of claim 11, wherein the processor circuit is further configured to cause the BS to:

based on the best receive or transmit beam of the BS within the previous time window, the best receive or transmit beam of the BS is predicted for the next time using the AI or ML model for beam management.

19. The apparatus of claim 18, wherein the AI or ML model for beam management is an AI or ML model based on long term memory (LSTM).

20. The apparatus of claim 18, wherein the AI or ML model for beam management is a Deep Neural Network (DNN) with multiple fully connected hidden layers or a Convolutional Neural Network (CNN) with one-dimensional convolutional layers.

21. The apparatus of claim 16, wherein signal strength parameters of the plurality of first reference signals associated with a subset of receive beams of the UE are reported to the BS using an L1 reporting matrix, wherein columns and rows of the L1 reporting matrix correspond to transmit beams of the BS and receive beams of the UE, respectively.

22. A computer-readable storage medium having stored thereon computer-executable instructions, wherein the computer-executable instructions, when executed by processor circuitry used in a User Equipment (UE), cause the UE to:

23. The computer-readable storage medium of claim 22, wherein the computer-executable instructions, when executed by the processor circuit used in the UE, further cause the UE to:

24. A computer-readable storage medium having stored thereon computer-executable instructions, wherein the computer-executable instructions, when executed by processor circuitry used in a Base Station (BS), cause the BS to:

25. The computer-readable storage medium of claim 24, wherein the computer-executable instructions, when executed by the processor circuit used in the BS, further cause the BS to: