Method and apparatus for ai / ML-based RRM including wide beam search and fine beam search

Abstract

Embodiments relate to a method and apparatus for artificial intelligence / machine learning (AI / ML) based radio resource management (RRM) including wide beam search and fine beam search. In particular, embodiments relate to deep learning that employs an AI / ML algorithm to learn mappings between low-resolution to high-resolution mappings by a UE. In one embodiment, a process implemented by a UE includes selecting subsamples of a beam received by the UE from a base station. Based on the selection of the subsamples of the beam, the process further includes the UE implementing an AI / ML model function to: generate a coarse training image map; generating a predicted image map from the coarse training image map; and selecting an optimal beam pair from the predicted image map for communication with the base station.

Description

[0001] Cross-references to related applications

[0002] This application claims the benefit and priority of U.S. Provisional Patent Application No. 63 / 457,697, filed April 6, 2023, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This invention relates generally to the field of wireless communication, and more specifically, to a method and apparatus for radio resource management (RRM) based on artificial intelligence / machine learning (AI / ML), including wide beam search and narrow beam search. Background Technology

[0004] In wireless communication networks, user equipment (UE) can communicate with the network's base station by establishing a radio link between the UE and the base station. In 5G (New Radio or NR) or 4G (LTE) wireless networks, the UE can receive signaling and data from the serving base station in the downlink (DL) transmission direction or send signaling and data to the serving base station in the uplink (UL) transmission direction.

[0005] Research project (SI) RP-213599 explores the benefits of leveraging features to augment the air interface, improving support for AI / ML-based algorithms to enhance performance and / or reduce complexity / overhead. However, from the UE's perspective, Radio Resource Management (RRM) and L1 measurement enhancements have not yet become a focus of existing Radio Access Network 1 (RAN1)-dominated SIs. It is worth noting that in current New Radio (NR) designs, the overhead of reference signals (RS) used for RRM (i.e., Synchronization Signal Block (SSB) and Channel State Reference Information Reference Signal (CSI-RS)) is quite high. For example, when the SSB-based Measurement Timing Configuration (SMTC) periodicity is 20ms, the associated SMTC overhead in the frequency range (FR2) is approximately 25%, which is very high. It would be quite beneficial to reduce the number of beams at both Tx and / or Rx in measurements while maintaining existing delay and accuracy requirements. Summary of the Invention

[0006] The implementation relates to a method and apparatus for radio resource management (RRM) based on artificial intelligence / machine learning (AI / ML), including wide beam search and narrow beam search. According to the implementation described below, potential enhancements to RRM functionality can be achieved using AI / ML model functions implemented by the UE. In one implementation, to reduce overhead and increase throughput, it is preferred to reduce the training overhead from a full search performed by the UE to a partial search. As an example, as described below, the Reference Signal Received Power (RSRP) value across a complete Rx, Tx beam scan can be considered as an image where individual pixels represent the RSRP value of each Rx, Tx beam combination. The reduced measurement would result in subsampling of the complete image, and would represent a low-resolution image. Therefore, the proposed implementation may involve employing deep learning to learn a mapping between low-resolution and high-resolution mappings by the UE utilizing AI / ML algorithms. RRM performance enhancements can be achieved by utilizing the implementation of AI / ML algorithms implemented by the UE, as described below.

[0007] In one implementation, the process implemented by the UE includes: selecting a subsample of a beam received by the UE from the base station. Based on the selection of the subsample of the beam, the process further includes the UE implementing an AI / ML model function to: generate a coarse training image map; generate a predicted image map from the coarse training image map; and select an optimal beam pair from the predicted image map for communication with the base station.

[0008] In one implementation, a subsample of the beam includes a narrow beam. In another implementation, a subsample of the beam includes a wide beam. In one implementation, the AI / ML model function is based on an 8×8 uniform planar array (UPA) Tx and a 4x4 Rx antenna array. In one implementation, the optimal beam pair from the predicted image map for communication with the base station includes a Tx, Rx pair. In one implementation, the coarse-trained image map is generated based on training data {X input, Y output} pairs, where X input represents a subset of beam pair reference signal received power (RSRP) measurements, and Y output represents the true full-search RSRP measurements. In one implementation, the AI / ML model function is trained to find the inverse function: ,in X corresponds to the predicted image mapping, and X corresponds to the coarse training image mapping. In one implementation, the AI / ML model function is based on the interpolation mapping. To predict the optimal beam pair {Tx,Rx}, where Returns the image corresponding to the predicted image mapping. The optimal peak value. In one implementation, the subsamples of the beam include a wide beam, and the wide beam can be identified in an RRC configuration that includes wide beam scanning and wide beam size.

[0009] In another type of implementation, a user equipment (UE) is disclosed for implementing radio resource management (RRM) for the UE, which is coupled to a base station. The UE includes: at least one antenna; at least one radio component configured to communicate with the base station using the at least one antenna; and at least one processor coupled to the at least one radio component. The at least one processor is configured to perform operations including: selecting a subsample of a beam received from the base station via the antenna; and based on the selection of the subsample of the beam, implementing an artificial intelligence / machine learning (AI / ML) model function to: generate a coarse-trained image map; generate a predicted image map from the coarse-trained image map; and select an optimal beam pair from the predicted image map for communication with the base station.

[0010] In one implementation, a subsample of the beam includes a narrow beam. In another implementation, a subsample of the beam includes a wide beam. In one implementation, the AI / ML model function is based on an 8×8 uniform planar array (UPA) Tx and a 4x4 Rx antenna array. In one implementation, the optimal beam pair from the predicted image map for communication with the base station includes a Tx, Rx pair. In one implementation, the coarse-trained image map is generated based on training data {X input, Y output} pairs, where X input represents a subset of beam pair reference signal received power (RSRP) measurements, and Y output represents the true full-search RSRP measurements. In one implementation, the AI / ML model function is trained to find the inverse function: ,in X corresponds to the predicted image mapping, and X corresponds to the coarse training image mapping. In one implementation, the AI / ML model function is based on the interpolation mapping. To predict the optimal beam pair {Tx,Rx}, where Returns the image corresponding to the predicted image mapping. The optimal peak value. In one implementation, the subsamples of the beam include a wide beam, and the wide beam can be identified in an RRC configuration that includes wide beam scanning and wide beam size.

[0011] Other methods and apparatus are also described. Attached Figure Description

[0012] The invention is illustrated by way of example and is not limited to the figures in the accompanying drawings, in which similar reference numerals indicate similar elements.

[0013] Figure 1 An example wireless communication system according to one embodiment of the present disclosure is illustrated.

[0014] Figure 2 An example of a user equipment that communicates directly with a base station (BS) according to one embodiment of the present disclosure is illustrated.

[0015] Figure 3 An example block diagram of a UE according to one embodiment of the present disclosure is shown.

[0016] Figure 4 An example block diagram of a BS according to one embodiment of the present disclosure is shown.

[0017] Figure 5 An example block diagram of a cellular communication circuit according to one embodiment of the present disclosure is shown.

[0018] Figure 6 A flowchart illustrating a process for implementing Radio Resource Management (RRM) for a UE according to one embodiment of the present disclosure is shown.

[0019] Figure 7A A diagram illustrating a fine beam from a base station to one or more UEs according to one embodiment of the present disclosure is shown.

[0020] Figure 7B A diagram illustrating a wide beam from a base station to one or more UEs according to one embodiment of the present disclosure is shown.

[0021] Figure 8 An image map illustrating the training of an AI / ML model function for exemplifying a UE, according to one embodiment of this disclosure, is shown.

[0022] Figure 9A A graph illustrating the accuracy of a previously described method for wide-beam and narrow-band training according to one embodiment of this disclosure is shown.

[0023] Figure 9B A graph illustrating the accuracy of a previously described method for wide-beam and narrow-band training according to one embodiment of this disclosure is shown.

[0024] Figure 10 A diagram illustrating various SSB index points of a beam measured in X, Y, and Z directions, according to one embodiment of this disclosure, is shown.

[0025] Figure 11 A flowchart of a process for implementing radio resource management (RRM) for a UE according to one embodiment of the present disclosure is shown, the process including the use of X and Y spatial coordinates from SSB index point measurements. Detailed Implementation

[0026] In the following description, numerous specific details are set forth to provide a thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other instances, well-known components, structures, and techniques have not been shown in detail so as not to obscure the understanding of this description.

[0027] In this specification, references to "some embodiments" or "implementation" mean that a particular feature, structure, or characteristic described in connection with that embodiment may be included in at least one embodiment of the invention. The phrase "some embodiments" appearing in various places throughout this specification does not necessarily refer to the same embodiment.

[0028] In the following description and claims, the terms “coupled” and “connected” and their derivatives may be used. It should be understood that these terms are not intended to be synonymous with each other. “Coupled” is used to refer to two or more elements that may or may not be in direct physical or electrical contact with each other, cooperating or interacting with each other. “Connected” is used to refer to the establishment of communication between two or more coupled elements.

[0029] The processes illustrated in the following figures are executed by processing logic, which includes hardware (e.g., circuitry, special-purpose logic, etc.), software (such as software running on a general-purpose computer system or a special-purpose machine), or a combination of both. While these processes are described below in a certain order, it should be understood that some of the described operations may be performed in a different order. Furthermore, some operations may be performed in parallel rather than sequentially.

[0030] The terms “server,” “client,” and “device” are intended to refer generally to a data processing system, rather than to specific constituent elements of a server, client, and / or device.

[0031] Figure 1 A simplified example wireless communication system according to one aspect of this disclosure is illustrated. It should be noted that... Figure 1 The system described is merely one example of a possible system, and the features of this disclosure can be implemented in any of a variety of systems as needed.

[0032] As shown in the figure, the example wireless communication system includes a base station 102A, which communicates with one or more user equipments 106A, 106B to 106N, etc., via a transmission medium. Each user equipment may be referred to herein as a "user equipment" (UE). Therefore, user equipment 106 is referred to as a UE or UE device.

[0033] Base station (BS) 102A may be a transceiver base station (BTS) or a cell site (“cellular base station”), and may include hardware that enables wireless communication with UE 106A to UE 106N.

[0034] The communication area (or coverage area) of a base station may be referred to as a "cell". Base station 102A and UE 106 can be configured to communicate via a transmission medium using any of a variety of Radio Access Technologies (RATs), also known as wireless communication technologies or telecommunications standards, such as GSM, UMTS (associated with air interfaces such as WCDMA or TD-SCDMA), LTE, LTE-Advanced (LTE-A), 5G New Radio (5G NR), HSPA, 3GPP2 CDMA2000 (e.g., 1xRTT, 1xEV-DO, HRPD, eHRPD), etc. Note that if base station 102A is implemented in an LTE environment, its alternative location may be referred to as an "eNodeB" or "eNB". It should also be noted that if base station 102A is implemented in a 5G NR environment, its alternative location may be referred to as a "gNodeB" or "gNB".

[0035] As shown in the figure, base station 102A can also be configured to communicate with network 100 (e.g., in various possibilities, the core network of a cellular service provider, telecommunications networks such as the Public Switched Telephone Network (PSTN), and / or the Internet). Therefore, base station 102A facilitates communication between user equipments and / or between user equipments and network 100. Specifically, cellular base station 102A can provide UE 106 with various telecommunications capabilities, such as voice, SMS, and / or data services.

[0036] Base station 102A and other similar base stations (such as base station 102B...102N) operating under the same or different cellular communication standards can thus provide a network as a cell that can provide continuous or near-continuous overlapping services to UE 106A to 106N and similar devices over a geographical area via one or more cellular communication standards.

[0037] Therefore, although base station 102A can act as such Figure 1The example illustrates the "serving cells" of UEs 106A to 106N, but each UE 106 may also be able to receive signals (and possibly within its communication range) from one or more other cells (which may be provided by base stations 102B to 102N and / or any other base stations), which may be referred to as "neighboring cells." Such cells may also facilitate communication between user equipments and / or between user equipments and network 100. These cells may include "macro" cells, "micro" cells, "pecimen" cells, and / or any other cells of various other granularities providing service area size. For example, in... Figure 1 Base stations 102A to 102B illustrated can be macro cells, while base station 102N can be a micro cell. Other configurations are also possible.

[0038] In some implementations, base station 102A may be a next-generation base station, such as a 5G New Radio (5G NR) base station or a “gNB”. In some implementations, the gNB may be connected to a legacy evolved packet core (EPC) network and / or to an NR core (NRC) network. Furthermore, a gNB cell may include one or more transition and receive points (TRPs). Additionally, a UE capable of operating according to 5G NR may be connected to one or more TRPs within one or more gNBs.

[0039] It should be noted that UE 106 may be able to communicate using multiple wireless communication standards. For example, UE 106 may be configured to communicate using wireless networking (e.g., Wi-Fi) and / or peer-to-peer wireless communication protocols (e.g., Bluetooth, Wi-Fi peer-to-peer, etc.) other than at least one cellular communication protocol (e.g., GSM, UMTS (associated with, for example, WCDMA or TD-SCDMA air interfaces), LTE, LTE-A, 5G NR, HSPA, 3GPP2 CDMA2000 (e.g., 1xRTT, 1xEV-DO, HRPD, eHRPD, etc.)). If desired, UE 106 may also be configured, or alternatively, to communicate using one or more Global Navigation Satellite Systems (GNSS, such as GPS or GLONASS), one or more mobile television broadcasting standards (e.g., ATSC-M / H or DVB-H) and / or any other wireless communication protocol. Other combinations of wireless communication standards (including more than two wireless communication standards) are also possible.

[0040] Figure 2An example of a UE 106 is illustrated, which communicates directly with base station 102 via uplink and downlink communication according to one aspect of this disclosure. UE 106 may be a cellular communication-capable device, such as a mobile phone, handheld device, computer, or tablet computer, or virtually any type of wireless device. UE 106 may include a processor configured to execute program instructions stored in memory. UE 106 may perform any method implementation of the method implementations described herein by executing such stored instructions. Alternatively or additionally, UE 106 may include programmable hardware elements, such as a field-programmable gate array (FPGA) configured to perform any of the method implementations described herein or any portion thereof.

[0041] UE 106 may include one or more antennas for communicating using one or more wireless communication protocols or technologies. In some embodiments, UE 106 may be configured to communicate using, for example, CDMA2000 (1xRTT, 1xEV-DO, HRPD, eHRPD) or LTE using a single shared radio component and / or GSM or LTE using a single shared radio component. The shared radio component may be coupled to a single antenna or to multiple antennas (e.g., for MIMO) for performing wireless communication. Generally, the radio component may include any combination of baseband processor, analog RF signal processing circuitry (e.g., including filters, mixers, oscillators, amplifiers, etc.) or digital processing circuitry (e.g., for digital modulation and other digital processing). Similarly, the radio component may use the aforementioned hardware to implement one or more receive chains and transmit chains. For example, UE 106 may share one or more portions of the receive chain and / or transmit chain among multiple wireless communication technologies (such as those discussed above).

[0042] In some implementations, UE 106 may include independent transmit and / or receive chains (e.g., including independent antennas and other radio components) for each wireless communication protocol configured to communicate therewith. As another possibility, UE 106 may include one or more radio components shared among multiple wireless communication protocols, as well as one or more radio components uniquely used by a single wireless communication protocol. For example, UE 106 may include shared radio components for communication using either LTE or 5G NR (or LTE or 1xRTT, or LTE or GSM), and separate radio components for communication using each of Wi-Fi and Bluetooth. Other configurations are also possible.

[0043] Figure 3A simplified block diagram of a communication device 106 according to one aspect of this disclosure is illustrated. It should be noted that... Figure 3 The block diagram of the communication device is merely one example of possible communication devices. According to the implementation, among other devices, the communication device 106 may be a combination of user equipment (UE) equipment, mobile equipment or mobile station, wireless equipment or wireless station, desktop computer or computing device, mobile computing device (e.g., laptop computer, notebook computer, or portable computing device), tablet computer, and / or other devices. As shown, the communication device 106 may include a set of components 300 configured to perform core functions. For example, this set of components may be implemented as a system-on-a-chip (SOC), which may include portions for various purposes. Alternatively, the set of components 300 may be implemented as individual components or groups of components for various purposes. This set of components 300 may be (e.g., communicatively; directly or indirectly) coupled to various other circuitry of the communication device 106.

[0044] For example, communication device 106 may include various types of memory (e.g., including NAND flash memory 310), input / output interfaces such as connector I / F 320 (e.g., for connection to a computer system; docking station; charging station; input devices such as microphone, camera, keyboard; output devices such as speaker; etc.), a display 360 that can be integrated with or external to the communication device 106, and cellular communication circuitry 330 such as for 5G NR, LTE, GSM, etc., and short- to medium-range wireless communication circuitry 329 (e.g., Bluetooth). ™ (and WLAN circuitry). In some embodiments, the communication device 106 may include wired communication circuitry (not shown), such as, for example, a network interface card for Ethernet.

[0045] Cellular communication circuitry 330 may be coupled (e.g., communicatively; directly or indirectly) to one or more antennas, such as antennas 335 and 336 shown. Short-to-medium-range wireless communication circuitry 329 may also be coupled (e.g., communicatively; directly or indirectly) to one or more antennas, such as antennas 337 and 338 shown. Alternatively, short-to-medium-range wireless communication circuitry 329 may be coupled (e.g., communicatively; directly or indirectly) to antennas 335 and 336 in addition to or instead of being coupled to antennas 337 and 338. Short-to-medium-range wireless communication circuitry 329 and / or cellular communication circuitry 330 may include multiple receive chains and / or multiple transmit chains for receiving and / or transmitting multiple spatial streams, such as in a multiple-input multiple-output (MIMO) configuration.

[0046] In some embodiments, as further described below, the cellular communication circuit 330 may include dedicated receive chains (including and / or coupled to (e.g., communicatively; directly or indirectly) dedicated processors and / or radio components) for multiple radio access technologies (RATs) (e.g., a first receive chain for LTE and a second receive chain for 5G-NR). Furthermore, in some embodiments, the cellular communication circuit 330 may include a single transmit chain that can be switched between radio components dedicated to a particular RAT. For example, a first radio component may be dedicated to a first RAT, such as LTE, and may communicate with a dedicated receive chain and a transmit chain shared with additional radio components, such as a second radio component that may be dedicated to a second RAT (e.g., 5G NR) and may communicate with a dedicated receive chain and a shared transmit chain.

[0047] The communication device 106 may also include one or more user interface elements and / or be configured to be used with one or more user interface elements. The user interface elements may include any of a variety of elements such as a display 360 (which may be a touch screen display), a keyboard (which may be a separate keyboard or may be implemented as part of a touch screen display), a mouse, a microphone and / or a speaker, one or more cameras, one or more buttons, and / or any of a variety of other elements capable of providing information to the user and / or receiving or interpreting user input.

[0048] The communication device 106 may also include one or more smart cards 345 with SIM (Subscriber Identity Module) functionality, such as one or more UICC (Universal Integrated Circuit Card) 345.

[0049] As shown, the SOC 300 may include a processor 302 and a display circuit 304. The processor executes program instructions for the communication device 106, and the display circuit performs graphics processing and provides display signals to the display 360. The processor 302 may also be coupled to a memory management unit (MMU) 340 (which may be configured to receive addresses from the processor 302 and translate those addresses into locations in memory (e.g., memory 306, read-only memory (ROM) 350, NAND flash memory 310)) and / or coupled to other circuitry or devices (such as the display circuit 304, short-range wireless communication circuitry 229, cellular communication circuitry 330, connector I / F 320, and / or display 360). The MMU 340 may be configured to perform memory protection and page table translation or setup. In some embodiments, the MMU 340 may be included as part of the processor 302.

[0050] As mentioned above, communication device 106 can be configured to communicate using wireless and / or wired communication circuits. Communication device 106 can also be configured to determine physical downlink shared channel scheduling resources for user equipment and base stations. Furthermore, communication device 106 can be configured to select and group component carriers (CCs) from the wireless link, and determine virtual CCs from the selected CC groups. The wireless device can also be configured to perform physical downlink resource mapping based on an aggregation resource matching mode for CC groups.

[0051] As described herein, communication device 106 may include hardware and software components for implementing the aforementioned features for determining physical downlink shared channel scheduling resources for communication device 106 and a base station. For example, by executing program instructions stored on a memory medium (e.g., a non-transitory computer-readable memory medium), processor 302 of communication device 106 may be configured to implement some or all of the features described herein. Alternatively (or further), processor 302 may be configured as a programmable hardware element, such as an FPGA (Field-Programmable Gate Array) or ASIC (Application-Specific Integrated Circuit). Alternatively (or further), in conjunction with one or more of other components 300, 304, 306, 310, 320, 329, 330, 340, 345, 350, 360, processor 302 of communication device 106 may be configured to implement some or all of the features described herein.

[0052] Furthermore, as described herein, processor 302 may include one or more processing elements. Therefore, processor 302 may include one or more integrated circuits (ICs) configured to perform the functions of processor 302. Additionally, each integrated circuit may include circuitry (e.g., a first circuit, a second circuit, etc.) configured to perform the functions of one or more processors 302.

[0053] Furthermore, as described herein, both the cellular communication circuit 330 and the short-range wireless communication circuit 329 may include one or more processing elements. In other words, one or more processing elements may be included in the cellular communication circuit 330, and similarly, one or more processing elements may be included in the short-range wireless communication circuit 329. Therefore, the cellular communication circuit 330 may include one or more integrated circuits (ICs) configured to perform the functions of the cellular communication circuit 330. Furthermore, each integrated circuit may include circuitry (e.g., a first circuit, a second circuit, etc.) configured to perform the functions of the wireless communication circuit 330. Similarly, the short-range wireless communication circuit 329 may include one or more ICs configured to perform the functions of the short-range wireless communication circuit 329. Furthermore, each integrated circuit may include circuitry (e.g., a first circuit, a second circuit, etc.) configured to perform the functions of the short-range wireless communication circuit 329.

[0054] Figure 4 An example block diagram of a base station 102 according to one aspect of this disclosure is shown. It should be noted that... Figure 4 The base station shown is merely one example of a possible base station. As illustrated, base station 102 may include processor 404, which executes program instructions for base station 102. Processor 404 may also be coupled to memory management unit (MMU) 440, which may be configured to receive addresses from processor 404 and translate these addresses into locations in memory (e.g., memory 460 and read-only memory (ROM) 450), or to other circuitry or devices.

[0055] Base station 102 may include at least one network port 470. Network port 470 may be configured to couple to a telephone network and provide access as described above. Figure 1 and Figure 2 The telephone network described herein includes several devices such as UE 106.

[0056] Network port 470 (or an additional network port) may also be configured, or alternatively configured, to couple to a cellular network, such as the core network of a cellular service provider. The core network may provide mobility-related services and / or other services to multiple devices such as UE 106. In some cases, network port 470 may be coupled to a telephone network via the core network, and / or the core network may provide a telephone network (e.g., in other UEs served by the cellular service provider).

[0057] In some implementations, base station 102 may be a next-generation base station, such as a 5G New Radio (5G NR) base station, or “gNB”. In such implementations, base station 102 may be connected to a legacy evolved packet core (EPC) network and / or to an NR core (NRC) network. Furthermore, base station 102 may be considered a 5G NR cell and may include one or more transition and receive points (TRPs). Additionally, UEs capable of operating according to 5G NR may be connected to one or more TRPs within one or more gNBs.

[0058] Base station 102 may include at least one antenna 434, and may include multiple antennas. The at least one antenna 434 may be configured to function as a wireless transceiver and may be further configured to communicate with UE 106 via radio component 430. Antenna 434 communicates with radio component 430 via communication link 432. Communication link 432 may be a receive link, a transmit link, or both. Radio component 430 may be configured to communicate via various wireless communication standards, including but not limited to 5G NR, LTE, LTE-A, GSM, UMTS, CDMA2000, Wi-Fi, etc.

[0059] Base station 102 can be configured to perform wireless communication using multiple wireless communication standards. In some instances, base station 102 may include multiple radio components that enable base station 102 to communicate according to multiple wireless communication technologies. For example, as one possibility, base station 102 may include an LTE radio component for performing communication according to LTE and a 5G NR radio component for performing communication according to 5G NR. In this case, base station 102 may be able to operate as both an LTE base station and a 5G NR base station. As another possibility, base station 102 may include a multimode radio component capable of performing communication according to any of multiple wireless communication technologies (e.g., 5G NR and Wi-Fi, LTE and Wi-Fi, LTE and UMTS, LTE and CDMA2000, UMTS and GSM, etc.).

[0060] As further described herein, BS 102 may include hardware and software components for implementing or supporting specific implementations of the features described herein. The processor 404 of base station 102 may be configured, for example, to implement or support specific implementations of some or all of the methods described herein by executing program instructions stored on a memory medium (e.g., a non-transitory computer-readable memory medium). Alternatively, processor 404 may be configured as a programmable hardware element such as a FPGA (Field-Programmable Gate Array), or as an ASIC (Application-Specific Integrated Circuit), or a combination thereof. Alternatively (or further), in conjunction with one or more of other components 430, 432, 434, 440, 450, 460, 470, the processor 404 of BS 102 may be configured to implement or support implementations of some or all of the features described herein.

[0061] Furthermore, as described herein, processor 404 may comprise one or more processing elements. In other words, one or more processing elements may be included in processor 404. Therefore, processor 404 may include one or more integrated circuits (ICs) configured to perform the functions of processor 404. Additionally, each integrated circuit may include circuitry (e.g., a first circuit, a second circuit, etc.) configured to perform the functions of one or more processors 404.

[0062] Furthermore, as described herein, radio component 430 may comprise one or more processing elements. In other words, radio component 430 may include one or more processing elements. Therefore, radio component 430 may include one or more integrated circuits (ICs) configured to perform the functions of radio component 430. Additionally, each integrated circuit may include circuitry (e.g., a first circuit, a second circuit, etc.) configured to perform the functions of radio component 430.

[0063] Figure 5 A simplified block diagram of an example cellular communication circuit according to one aspect of this disclosure is shown. It should be noted that... Figure 5 The block diagram of the cellular communication circuit is merely one example of a possible cellular communication circuit. According to the implementation, the cellular communication circuit 330 may be included in a communication device such as the communication device 106 described above. As mentioned above, among other devices, the communication device 106 may be a user equipment (UE) device, a mobile device or mobile station, a wireless device or wireless station, a desktop computer or computing device, a mobile computing device (e.g., a laptop computer, notebook computer, or portable computing device), a tablet computer, and / or a combination of these devices.

[0064] Cellular communication circuit 330 may (e.g., communicatively; directly or indirectly) be coupled to one or more antennas, such as ( Figure 3 Antennas 335 ab and 336 are shown in the diagram. In some embodiments, the cellular communication circuitry 330 may include dedicated receive chains for various RATs (including and / or coupled to (e.g., communication ground; directly or indirectly) dedicated processors and / or radio components) (e.g., a first receive chain for LTE and a second receive chain for 5G NR). For example, as shown... Figure 5 As shown, the cellular communication circuit 330 may include a modem 510 and a modem 520. The modem 510 may be configured for communication according to a first RAT (e.g., such as LTE or LTE-A), and the modem 520 may be configured for communication according to a second RAT (e.g., such as 5G NR).

[0065] As shown, modem 510 may include one or more processors 512 and memory 516 communicating with processors 512. Modem 510 may communicate with radio frequency (RF) front end 530. RF front end 530 may include circuitry for transmitting and receiving radio signals. For example, RF front end 530 may include receiver circuitry (RX) 532 and transmitter circuitry (TX) 534. In some embodiments, receiver circuitry 532 may communicate with downlink (DL) front end 550, which may include circuitry for receiving radio signals via antenna 335a.

[0066] Similarly, modem 520 may include one or more processors 522 and memory 526 communicating with processor 522. Modem 520 may communicate with RF front end 540. RF front end 540 may include circuitry for transmitting and receiving radio signals. For example, RF front end 540 may include receiving circuitry 542 and transmitting circuitry 544. In some embodiments, receiving circuitry 542 may communicate with DL front end 560, which may include circuitry for receiving radio signals via antenna 335b.

[0067] In some implementations, switch 570 may couple transmitting circuitry 534 to uplink (UL) front-end 572. Additionally, switch 570 may couple transmitting circuitry 544 to UL front-end 572. UL front-end 572 may include circuitry for transmitting radio signals via antenna 336. Therefore, when cellular communication circuitry 330 receives an instruction to transmit according to a first RAT (e.g., supported by modem 510), switch 570 may be switched to a first state allowing modem 510 to transmit signals according to the first RAT (e.g., via a transmission chain including transmitting circuitry 534 and UL front-end 572). Similarly, when cellular communication circuitry 330 receives an instruction to transmit according to a second RAT (e.g., supported by modem 520), switch 570 may be switched to a second state allowing modem 520 to transmit signals according to the second RAT (e.g., via a transmission chain including transmitting circuitry 544 and UL front-end 572).

[0068] As described herein, modem 510 may include hardware and software components for implementing the features described above or for selecting periodic resource portions for user equipment and base stations, as well as various other technologies described herein. For example, processor 512 may be configured to implement some or all of the features described herein by executing program instructions stored on a memory medium (e.g., a non-transitory computer-readable storage medium). Alternatively (or further), processor 512 may be configured as a programmable hardware element, such as an FPGA (Field-Programmable Gate Array) or an ASIC (Application-Specific Integrated Circuit). Alternatively (or further), processor 512 may be configured to implement some or all of the features described herein by combining with one or more of other components 530, 532, 534, 550, 570, 572, 335, and 336.

[0069] Furthermore, as described herein, processor 512 may include one or more processing elements. Therefore, processor 512 may include one or more integrated circuits (ICs) configured to perform the functions of processor 512. Additionally, each integrated circuit may include circuitry (e.g., a first circuit, a second circuit, etc.) configured to perform the functions of processor 512.

[0070] As described herein, modem 520 may include hardware and software components for implementing the features described above or for selecting periodic resource portions on a radio link between the UE and a base station, as well as various other technologies described herein. For example, processor 522 may be configured to implement some or all of the features described herein by executing program instructions stored on a memory medium (e.g., a non-transitory computer-readable memory medium). Alternatively (or further), processor 522 may be configured as a programmable hardware element, such as an FPGA (Field-Programmable Gate Array) or an ASIC (Application-Specific Integrated Circuit). Alternatively (or further), processor 522 may be configured to implement some or all of the features described herein by combining one or more of other components 540, 542, 544, 550, 570, 572, 335, and 336.

[0071] Furthermore, as described herein, processor 522 may include one or more processing elements. Therefore, processor 522 may include one or more integrated circuits (ICs) configured to perform the functions of processor 522. Additionally, each integrated circuit may include circuitry (e.g., a first circuit, a second circuit, etc.) configured to perform the functions of processor 522.

[0072] As already described, the research project (SI) of RP-213599 explores the benefits of leveraging features to augment the air interface, improving support for AI / ML-based algorithms to enhance performance and / or reduce complexity / overhead. However, from the UE's perspective, Radio Resource Management (RRM) and L1 measurement enhancements have not yet become the focus of existing Radio Access Network 1 (RAN1)-dominated SIs. It should be noted that in current New Radio (NR) designs, the overhead of the reference signals (RS) used for RRM (i.e., Synchronization Signal Block (SSB) and Channel State Reference Information Reference Signal (CSI-RS)) is quite high. For example, when the periodicity of the SSB-based Measurement Timing Configuration (SMTC) is 20ms, the associated SMTC overhead in the frequency range (FR2) is approximately 25%, which is very high. It would be quite beneficial to reduce the number of beams at both Tx and / or Rx in L1 / L3 associated measurements while maintaining existing delay and accuracy requirements. Furthermore, the number of training cycles required to perform beam alignment on millimeter waves results in high communication overhead (full search across Tx and Rx beams).

[0073] According to the implementation scheme described below, potential enhancements to RRM functionality can be achieved using AI / ML model functions implemented by UE 106. By specifically implementing the AI / ML scheme, L3 / L1 measurement latency can be reduced by minimizing the Rx beam scan set, and scheduling constraints can be reduced by minimizing L1 / 3 measurements. Scheduling constraints imposed during the training cycle of measurements performed by UE 106 can reduce throughput. RRM performance enhancements can be achieved by utilizing the implementation scheme of AI / ML algorithms implemented by UE 106, as described below.

[0074] In one implementation, to reduce overhead and increase throughput, it is preferable to reduce the training overhead from a full search performed by UE106 to a partial search. As an example, as will be described, the Reference Signal Received Power (RSRP) value across a complete Rx, Tx beam scan can be considered as an image where individual pixels represent the RSRP value for each Rx, Tx beam combination. The reduced measurement would result in subsampling of the complete image, and would represent a low-resolution image. Therefore, the proposed implementation could involve employing deep learning, where UE106 utilizes AI / ML algorithms to learn a mapping between low-resolution and high-resolution maps. In some examples, the AI / ML algorithm may include the use of convolutional neural networks.

[0075] refer to Figure 6 , Figure 6 A flowchart is shown for implementing Radio Resource Management (RRM) for a UE. Process 600 includes: selecting a subsample of beams received from a base station via the antenna of UE 106 (box 610). Based on the selection of the subsamples of beams, process 600 also includes UE 106's processor 302 implementing an artificial intelligence / machine learning function (box 615) to: generate a coarse training image map (box 620); generate a predicted image map from the coarse training image map (box 630); and select an optimal beam pair from the predicted image map for communication with base station 102 (box 640).

[0076] refer to Figure 7A and Figure 7B AI / ML-based enhancements can be implemented by UE 106 to reduce overhead. As will be described, UE 106 can subsample narrow or wide beams to achieve AI / ML-based enhancements. In some examples, AI / ML-based enhancements may include the use of convolutional neural networks.

[0077] As an example, in Figure 7AAs can be seen, base station 102 (e.g., gNB 102) can perform a scan of Tx beams [0, 1, 2, 3, 4, 5, 6, 7] (including the SSB index mapped to each beam) in a 5-millisecond (ms) burst set to one or more UEs (e.g., UE 106). UE 106 is performing measurements using different Rx beams for each burst set. It can be seen that UE 106 receives beams with different signal strengths. In this example, as... Figure 7A As shown, the UE receives 8 Rx beams [0, 1, 2, 3, 4, 5, 6, 7].

[0078] As an example, in Figure 7B As can be seen, base station 102 (e.g., gNB 102) can perform a scan of the Tx beam to one or more UEs (e.g., UE 106). In this example, as... Figure 7B As shown, UE 106 can perform measurements on wide Rx beams. UE 106 can perform measurements using different wide Rx beams for each burst set. It can be seen that UE 106 receives beams with different signal strengths.

[0079] According to an embodiment of the present invention, the AI / ML model function can be trained by UE 106 in an offline and supervised manner, so that UE 106 selects Tx, Rx pairs in a much more efficient manner than in previous implementations.

[0080] The AI / ML model functions for UE 106 can also be trained online for fine-tuning based on the environment in which the UE currently resides. Furthermore, the training data can be further divided into training data and validation data specifically for training the AI / ML model functions, in order to adjust the hyperparameters of the AI / ML model functions and to monitor the model's generalization ability.

[0081] To train the AI / ML model function of UE 106 offline and in a supervised manner, enabling UE 106 to select Tx, Rx pairs that should be trained with the training data in a much more efficient way, the training data consists of {X, Y} or {input, output} pairs, where X represents the overall subset beamp-to-reference signal received power (RSRP) measurement, and the output represents the true label of the full-search RSRP measurement. The AI / ML model function is trained to find the inverse function. AI / ML model functions can be trained to minimize the loss function. For inference and testing purposes, a separate test dataset can be used. To implement AI / ML modeling functions, a 3D beamforming scene can be utilized.

[0082] To implement the AI / ML model function in UE 106, a general-purpose 8×8 uniform planar array (UPA) Tx and a 4x4 Rx antenna array can be utilized. Furthermore, Tx and Rx beamcodebooks for both antenna arrays can be used. The wireless channel consists of multiple-input multiple-output (MIMO) scattering (clusters, rays) and path gain between Tx and Rx antenna elements. For each training data implementation, the 3D placement of the scattering clusters (angle of arrival (AoA), angle of departure (AoD)) and the gain of each cluster are randomized. For each channel implementation, a full Tx, Rx codebook beam scan provides a matrix of RSRP measurements. The RSRP matrix is ​​used as the real tag data points, and a subsampled noisy RSRP matrix is ​​used as the input X to the AI / ML model function.

[0083] As previously described, UE 106's AI / ML model function will infer the complete RSRP mapping. AI / ML model functions can be used to extract interpolation maps. Predicting the optimal or best {Tx,Rx} beam pairs, where return The optimal or best peak value. The optimal {Tx, Rx} beam is formed by... This indicates that AI / ML model functions can utilize and use various test data to infer optimal or best peak values. Specifically, this data can be used to simulate existing... The probability of.

[0084] Additional reference Figure 8 , Figure 8 Image mapping is illustrated to illustrate the description of training AI / ML model functions for UE 106. In Figure 8 As can be seen, image map 802 is a training image with coarse Tx and Rx beams from base station 102 to UE 106, used for modeling purposes. Image map 804 is the true RSRP image map. Image map 820 is the image map predicted by the UE's AI / ML model function.

[0085] Therefore, as an example, a training image map with Tx and Rx beams 802 can be considered as input X. As an example, the image map 802 with Tx and Rx beams can be 22 coarse Tx beams and 5 coarse Rx beams, which can be wide beams. As an example, refer to the illustration... Figure 7B This can be seen. Figure 7B The wide beam received by UE 106 is shown. It should be noted that this is compared to the full measurement readings of 64 Tx beams and 16 Rx beams.

[0086] By inputting the image mapping 802 readings into the following AI / ML model function equations of UE 106: The AI / ML model function will be derived from the inverse AI / ML model function. The complete AI / ML predicted RSRP image map 820 is inferred. It can be seen that the AI / ML predicted RSRP image map 820 is very close to the real RSRP image map 804.

[0087] Furthermore, as previously described, the AI / ML model functions implemented by UE 106 can be used to extract interpolation maps. Predicting the optimal or best {Tx,Rx} beam pairs, where return The optimal or best peak value is obtained (where the interpolation mapping is the AI / ML predicted image mapping 820). Therefore, based on the trained coarse Tx, Rx beam input to UE 106 shown in image mapping 802, the AI / ML model function equation of UE 106 can be used to generate the AI / ML predicted RSRP image mapping 820, and from the AI / ML predicted RSRP image mapping 820, the optimal beam pair can be selected for UE 106. As an example, coarse resolution input image mapping 828 shows the image mapping of the region of coarse resolution input, and super-resolution prediction 830 is based on the interpolation mapping. It shows the best or optimal The optimal or best beam pair 832 of the {Tx,Rx} beam pair. In this way, a very accurate AI / ML prediction image map 820 can be generated, and the optimal beam pair can be selected for UE 106.

[0088] Training can be implemented using either wide or narrow beams, and the selection of the optimal beam pair for UE 106 can also be implemented using either wide or narrow beams. The previous example illustrates the use of wide beams. As described in the previous example, using wide beams (e.g., 5 wide beams), UE 106 can utilize its AI / ML model function to perform training to generate coarse-trained image maps and AI / ML model function-predicted image maps, and select the optimal beam pair. Using this data, the AI / ML model function and image maps can be fine-tuned and the optimal beam pair can be identified in an even more efficient manner in the subsequent selection of beam pairs for communication with the base station.

[0089] It should be understood that the same type of training and optimal beam pair selection for UE 106 can be achieved using narrow beams. As an example, a narrow beam subset (e.g., narrow beams 1, 4, 7) Figure 7AThe image mapping 802 can be used as input to the trained route Tx, Rx beam inputs. The AI / ML model function equations of UE 106 can be used to generate the AI / ML predicted RSRP image mapping 820, and from the AI / ML predicted RSRP image mapping 820, the optimal beam pair can be selected for UE 106 based on the narrow beam. Therefore, similar to the wide beam example, the narrow beam can be used to enable UE 106 to perform training using the AI / ML model function of UE 106 to generate a coarse-trained image mapping and an AI / ML model function predicted image mapping, and to select the optimal beam pair. Using this data, the AI / ML model function and the image mapping can be fine-tuned and the optimal beam pair can be identified in an even more efficient manner in the subsequent selection of beam pairs for communication with the base station.

[0090] refer to Figure 9A The diagram illustrates the accuracy of the previously described method. For wide-beam training, using two wide beams, as shown in line 905, the probability of a hit (e.g., finding the optimal beam pair (e.g., N=4 beam pairs)) is typically higher than 95%. For narrow-beam training, as shown in line 910, the probability of a hit (e.g., finding the optimal beam pair (e.g., N=4 beam pairs)) is typically in the range of 65%–90%. Reference Figure 9B The diagram illustrates the accuracy of the previously described method. For wide-beam training, using two wide beams, as shown in line 915, the probability of a hit (e.g., finding the optimal beam pair (e.g., N=8 beam pairs)) is typically 97.5%–100%. For narrow-beam training, as shown in line 920, the probability of a hit (e.g., finding the optimal beam pair (e.g., N=8 beam pairs)) is typically in the range of 75%–95%.

[0091] In one implementation, to select between wide beam scanning and narrow beam scanning for the AI / ML modeling function of UE 106, two additional fields can be inserted into the RRC configuration, including the following specifications: (1) wide beam scanning versus narrow beam scanning and (2) the size of the wide beam. This can be seen from the following programming:

[0092]

[0093] As previously described, the base station 102 (e.g., gNB) configuration is mapped to the SSB index of the Tx beam. Based on this, the UE 106 performs measurements on a subset of those SSB beams. Based on this, the AI / ML modeling function interpolates between the subset beams to recover the complete set (e.g., AI / ML predicts RSRP image mapping 820). Thus, as already described, in one implementation, the optimal subset has been determined offline and used to train the AI / ML modeling function.

[0094] To enable UE 106 to perform measurements that will feed the AI / ML modeling function, UE 106 can also determine which SSB indices in the SSB index correspond to the training subset of the SSB indices used by AI / ML for training. In some implementations, to achieve this, another field can be added within the RRC configuration, where some spatial information is specified for the SSB burst sequence. In this way, UE 106 knows at which SSBs it will need to perform measurements and feed the AI / ML modeling function.

[0095] In one implementation, the SSB index j of the network (NW) is received by UE 106 via base station 102, which signals the information Xaz, Yel, w / n to UE 106. X is a number indicating the spatial direction order of the beam in the azimuth angle. Y is a number indicating the spatial direction order of the beam in the elevation angle. And w / n indicates whether the beam is narrow or wide.

[0096] Additional reference Figure 10 , Figure 10 The display shows various SSB index points, including the beam's X, Y, and Z measurements, as well as whether the beam is narrow or wide. The X, Y, and Z measurements correspond to Tx codebook entries. Using this information, UE 106 can determine the SSB indices to be used as input measurements to AI / ML modeling functions. UE 106 can select / optimize the SSB indices to optimize performance. Figure 10 Each diamond shape in the diagram shows an SSB index point that includes its X, Y, Z measurements and whether the beam is narrow or wide.

[0097] For example, if the UE 106 only measures 8 beams (out of 64), it can optimize beam sampling based on this information (selecting 8 from the 64 beams), such as... Figure 10 As shown. The w / n field should indicate the functional mode of the AI / ML modeling function (e.g., whether it is wide-beam or narrow-beam). If all beams are narrow (64 narrow beams), the AI / ML modeling function can interpolate between the measured beams (e.g., less than 64). If the w / n field indicates a wide-beam, the AI / ML can be fed by measurements of all beams, and then amplified in those regions to perform super-resolution and predict the narrow-beam response.

[0098] The AI / ML modeling function predicts the first N beams in both cases. These first N beams are represented in the Xaz, Yel coordinate system. When the SSB burst is transmitted next, it will measure the first N beams at the location indicated by the transmitted signal to select the optimal or best beam.

[0099] In one implementation, an additional field can be included within the RRC configuration, where spatial information is specified for the SSB burst sequence (e.g., coordinate system xax, yel). In this way, the UE 106 will know at which SSBs it will need to perform measurements and feed the AI / ML model.

[0100] Here is an example of a program that can achieve this:

[0101]

[0102] refer to Figure 11 , Figure 11 A flowchart is shown for implementing a process 1100 for Radio Resource Management (RRM) for a UE. Process 1100 includes: selecting a subsample of beams received from a base station via the antenna of UE 106 based on the X and Y spatial coordinates from the SSB index point (box 1110). Based on the selection of the subsample of beams according to the X and Y spatial coordinates from the SSB index point, process 1100 also includes a processor 302 of UE 106 implementing artificial intelligence / machine learning functions (box 1115) to: generate a coarse training image map (box 1120); generate a predicted image map from the coarse training image map (box 1130); and select an optimal beam pair from the predicted image map for communication with base station 102 (box 1140).

[0103] In this way, the previously described process is optimized by using an additional processing step to select a subsample of the beams received from the base station via the antenna of UE 106 based on the X and Y spatial coordinates from the SSB index point. As previously described, training can be implemented using either a wide or narrow beam, and the selection of the optimal beam pair for UE 106 can also be implemented using either a wide or narrow beam. As previously described using either a wide or narrow beam, UE 106 can perform training using its AI / ML model function to generate a coarse-trained image map and an AI / ML model function-predicted image map, and select the optimal beam pair. Using this data, the AI / ML model function and the image map can be fine-tuned and the optimal beam pair can be identified in an even more efficient manner in the subsequent selection of beam pairs for communication with the base station.

[0104] It should be understood that in some implementations, the previously described process can be performed at UE 106 to implement the previously described process, the UE including: processor, communication interface, antenna, radio components, etc.

[0105] This article describes several exemplary implementations.

[0106] Example 1 is a method for radio resource management (RRM) for user equipment (UE) communicating with a base station, the method comprising: selecting a subsample of beams from the base station; implementing an artificial intelligence / machine learning (AI / ML) model function based on the selection of the subsamples of beams to: generate a coarse training image map; generate a predicted image map from the coarse training image map; and select an optimal beam pair from the predicted image map for communication with the base station.

[0107] Example 2 is the method according to Example 1, wherein the method may optionally include: the subsample of the beam includes a narrow beam.

[0108] Example 3 is the method according to Example 1, wherein the method may optionally include: the sub-samples of the beam include a wide beam.

[0109] Example 4 is the method according to Example 1, wherein the method may optionally include: the AI / ML model function is based on an 8×8 uniform planar array (UPA) Tx and a 4×4 Rx antenna array.

[0110] Example 5 is the method according to Example 1, wherein the method may optionally include: the optimal beam pair from the predicted image map for communication with the base station includes a Tx, Rx pair.

[0111] Example 6 is the method according to Example 5, wherein the method may optionally include: the coarse training image mapping is generated based on training data {X input, Y output} pairs, wherein the X input represents a subset of beam-to-reference signal received power (RSRP) measurements, and the Y output represents the true full-search RSRP measurements.

[0112] Example 7 is the method according to Example 6, wherein the method may optionally include: the AI / ML model function being trained to find the inverse function: ,in X corresponds to the predicted image mapping, and X corresponds to the coarse training image mapping.

[0113] Example 8 is the method according to Example 7, wherein the method may optionally include the AI / ML model function based on interpolation mapping. To predict the optimal beam pair {Tx,Rx}, where Return the image corresponding to the predicted image mapping. The optimal peak value.

[0114] Example 9 is the method according to Example 1, the method optionally including: the subsample of the beam includes a wide beam, and the wide beam is identified in an RRC configuration including wide beam scanning and the size of the wide beam.

[0115] Example 10 is a user equipment (UE) for implementing radio resource management (RRM) for the UE, the UE being coupled to a base station, the UE comprising: at least one antenna; at least one radio component configured to communicate with the base station using the at least one antenna; and at least one processor coupled to the at least one radio component, wherein the at least one processor is configured to perform operations including: selecting a subsample of a beam received from the base station via the antenna; implementing an artificial intelligence / machine learning (AI / ML) model function based on the selection of the subsample of the beam to: generate a coarse-trained image map; generate a predicted image map from the coarse-trained image map; and select an optimal beam pair from the predicted image map for communication with the base station.

[0116] Example 11 is a UE according to Example 10, wherein the UE may optionally include: the sub-samples of the beam include narrow beams.

[0117] Example 12 is a UE according to Example 10, wherein the UE may optionally include: the sub-samples of the beam include a wide beam.

[0118] Example 13 is a UE according to Example 10, wherein the UE may optionally include: the AI / ML model function is based on an 8×8 uniform planar array (UPA) Tx and a 4×4 Rx antenna array.

[0119] Example 14 is a UE according to Example 10, wherein the UE may optionally include: the optimal beam pair from the predicted image mapping for communication with the base station includes a Tx, Rx pair.

[0120] Example 15 is a UE according to Example 14, wherein the UE may optionally include: the coarse training image mapping is generated based on training data {X input, Y output} pairs, wherein the X input represents a subset of beam pair reference signal received power (RSRP) measurements, and the Y output represents the true full search RSRP measurement.

[0121] Example 16 is a UE according to Example 15, wherein the UE may optionally include: the AI / ML model function is trained to find an inverse function: ,in X corresponds to the predicted image mapping, and X corresponds to the coarse training image mapping.

[0122] Example 17 is a UE according to Example 16, wherein the UE may optionally include the AI / ML model function based on interpolation mapping. To predict the optimal beam pair {Tx,Rx}, where Return the image corresponding to the predicted image mapping. The optimal peak value.

[0123] Example 18 is a UE according to Example 10, wherein the UE may optionally include: the subsample of the beam includes a wide beam, and the wide beam is identified in an RRC configuration including wide beam scanning and the size of the wide beam.

[0124] Example 19 is a UE baseband processor configured to cause the UE to perform one or more methods according to Examples 1 to 9.

[0125] Parts of the content described above can be implemented using logic circuits such as dedicated logic circuits or using microcontrollers or other forms of processing cores that execute program code instructions. Thus, the processes taught in the above discussion can be executed using program code such as machine-executable instructions, which cause the machine to execute these instructions to perform certain functions. In this context, "machine" can be a machine that translates intermediate (or "abstract") instructions into processor-specific instructions (e.g., abstract execution environments such as "virtual machines" (e.g., Java Virtual Machines), interpreters, Common Language Runtimes, high-level language virtual machines, etc.), and / or electronic circuits disposed on semiconductor chips (e.g., "logic circuits" implemented using transistors) designed to execute instructions, such as general-purpose processors and / or dedicated processors. The processes taught in the above discussion can also be executed (as an alternative to or in conjunction with a machine) by electronic circuits designed to execute processes (or parts thereof) without executing program code.

[0126] For example, the operations of the previously described embodiments can be stored as instructions on a non-transitory computer-readable medium for execution by a computer (e.g., a UE). The invention also relates to an apparatus for performing the operations described herein. This apparatus may be specifically configured for a desired purpose or may comprise a general-purpose computer selectively activated or reconfigured by a computer program stored in a computer. Such a computer program may be stored in a computer-readable storage medium, such as, but not limited to, any type of disk, including floppy disks, optical disks, CD-ROMs and magneto-optical disks, read-only memory (ROM), RAM, EPROM, EEPROM, magnetic cards or optical cards, or any type of medium suitable for storing electronic instructions, and each of these is coupled to a computer system bus.

[0127] Machine-readable media include any means by which information is stored or transmitted in a machine-readable (e.g., computer) form. Examples of machine-readable media include read-only memory (“ROM”); random access memory (“RAM”); magnetic disk storage media; optical storage media; flash memory devices; and so on.

[0128] The article of manufacture may be used to store program code. The article of manufacture storing program code may be implemented as, but is not limited to, one or more memories (e.g., one or more flash memories, random access memory (static, dynamic, or other)), optical discs, CD-ROMs, DVD-ROMs, EPROMs, EEPROMs, magnetic cards or optical cards, or other types of machine-readable media suitable for storing electronic instructions. Program code may also be downloaded from a remote computer (e.g., a server) to a requesting computer (e.g., a client) by means of data signals contained in a transmission medium (e.g., via a communication link (e.g., a network connection)).

[0129] The foregoing detailed description has been presented according to the algorithms and symbolic representations used to manipulate data bits within computer memory. These algorithmic descriptions and representations are tools used by those skilled in the art of data processing, and these tools are also the most effective means of communicating the essence of their work to others skilled in the art. An algorithm here and generally refers to a self-consistent sequence of operations that leads to a desired result. These operations are those that require physical manipulation of physical quantities. Often, but not necessarily, these quantities take the form of electrical or magnetic signals that can be stored, transmitted, combined, compared, and otherwise manipulated. It has proven convenient to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, etc., primarily for general reasons.

[0130] However, it should be remembered that all these and similar terms are associated with appropriate physical quantities and are merely convenient labels applied to those quantities. Unless otherwise specifically stated, it is evident from the foregoing discussion that, throughout this specification, discussions using terms such as “select,” “determine,” “receive,” “form,” “group,” “aggregate,” “generate,” “remove,” etc., refer to the actions and processing of computer systems or similar electronic computing devices that can manipulate data represented as physical (electronic) quantities in the registers and memories of the computer system and convert them into other data similarly represented as physical quantities in the computer system's memory or registers or other such information storage, transmission, or display devices.

[0131] The processes and displays presented herein are not inherently related to any particular computer or other device. Various general-purpose systems can be used with programs based on the teachings herein, or can prove convenient for constructing more specialized devices to perform the operations described herein. The necessary structures for various such systems will be apparent from the description below. Furthermore, the invention is not described with reference to any particular programming language. It should be understood that various programming languages ​​can be used to implement the teachings of the invention as described herein.

[0132] The foregoing discussion has only described some exemplary embodiments of the invention. Those skilled in the art will readily recognize from these discussions, drawings, and claims that various modifications can be made without departing from the spirit and scope of the invention.

Claims

1. A method for radio resource management (RRM) of a user equipment (UE) communicating with a base station, the method comprising: Select a subsample of the beam from the base station; Based on the selection of the sub-samples of the beam, an artificial intelligence / machine learning (AI / ML) model function is implemented to: Generate coarse training image mappings; Generate a predicted image map from the coarse-trained image map; and The optimal beam pair is selected from the predicted image map for communication with the base station.

2. The method of claim 1, wherein the subsample of the beam comprises a narrow beam.

3. The method of claim 1, wherein the subsample of the beam comprises a wide beam.

4. The method according to claim 1, wherein the AI / ML model function is based on an 8×8 uniform planar array (UPA) Tx and a 4×4 Rx antenna array.

5. The method of claim 1, wherein the optimal beam pair from the predicted image map for communication with the base station includes a Tx, Rx pair.

6. The method of claim 5, wherein the coarse training image mapping is generated based on training data {X input, Y output} pairs, wherein the X input represents a subset of beam-to-reference signal received power (RSRP) measurements, and the Y output represents the true full-search RSRP measurements.

7. The method of claim 6, wherein the AI / ML model function is trained to find the inverse function: ,in X corresponds to the predicted image mapping, and X corresponds to the coarse training image mapping.

8. The method of claim 7, wherein the AI / ML model function is based on interpolation mapping. To predict the optimal beam pair {Tx,Rx}, where Return the image corresponding to the predicted image mapping. The optimal peak value.

9. The method of claim 1, wherein the subsample of the beam comprises a wide beam, and the wide beam is identified in an RRC configuration that includes a wide beam scan and the size of the wide beam.

10. A user equipment (UE) for implementing radio resource management (RRM) for the UE, the UE being coupled to a base station, the UE comprising: At least one antenna; At least one radio component, wherein the at least one radio component is configured to communicate with the base station using the at least one antenna; and At least one processor coupled to the at least one radio component, wherein the at least one processor is configured to perform operations including: Select a subsample of the beam received from the base station via the antenna; Based on the selection of the sub-samples of the beam, an artificial intelligence / machine learning (AI / ML) model function is implemented to: Generate coarse training image mappings; Generate a predicted image map from the coarse-trained image map; and The optimal beam pair is selected from the predicted image map for communication with the base station.

11. The UE of claim 10, wherein the sub-sample of the beam comprises a narrow beam.

12. The UE of claim 10, wherein the subsample of the beam comprises a wide beam.

13. The UE of claim 10, wherein the AI / ML model function is based on an 8×8 uniform planar array (UPA) Tx and a 4×4 Rx antenna array.

14. The UE of claim 10, wherein the optimal beam pair from the predicted image map for communication with the base station includes a Tx, Rx pair.

15. The UE of claim 14, wherein the coarse training image mapping is generated based on training data {X input, Y output} pairs, wherein the X input represents a subset of beam-to-reference signal received power (RSRP) measurements, and the Y output represents a true full-search RSRP measurement.

16. The UE of claim 15, wherein the AI / ML model function is trained to find the inverse function: ,in X corresponds to the predicted image mapping, and X corresponds to the coarse training image mapping.

17. The UE of claim 16, wherein the AI / ML model function is based on interpolation mapping. To predict the optimal beam pair {Tx,Rx}, where Return the image corresponding to the predicted image mapping. The optimal peak value.

18. The UE of claim 10, wherein the subsample of the beam includes a wide beam, and the wide beam is identified in an RRC configuration that includes a wide beam scan and the size of the wide beam.

19. A UE baseband processor, the UE baseband processor being configured to cause a UE to perform one or more methods according to claims 1 to 9.

Images