Generative model for generating performance test data for user equipment side beam prediction

Abstract

Various aspects of the present disclosure generally relate to wireless communications. In some aspects, a test equipment (TE) may transmit Layer 1 (L1) Reference Signal Received Power (RSRP) or L1 Signal to Interference plus Noise Ratio (SINR) (L1-RSRP / L1-SINR) measurements associated with a first set of resources, where the L1-RSRP / L1-SINR measurements associated with the first set of resources are based at least in part on a generative model for test data using randomized parameters. The TE may receive beam prediction feedback associated with user equipment (UE) side beam prediction based at least in part on the L1-RSRP / L1-SINR measurements associated with the first set of resources, wherein the beam prediction feedback indicates the L1-RSRP / L1-SINR measurements associated with the second set of resources. Numerous other aspects are described.

Description

Background Technology

[0001] All aspects of this disclosure relate to wireless communication in general, and to techniques and apparatus for generating models for test data used in beam prediction.

[0002] Wireless communication systems are widely deployed to provide a variety of telecommunications services, such as telephone, video, data, messaging, and broadcasting. Typical wireless communication systems employ multiple access technologies that enable communication with multiple users by sharing available system resources (e.g., bandwidth, transmit power, etc.). Examples of such multiple access technologies include Code Division Multiple Access (CDMA) systems, Time Division Multiple Access (TDMA) systems, Frequency Division Multiple Access (FDMA) systems, Orthogonal Frequency Division Multiple Access (OFDMA) systems, Single Carrier Frequency Division Multiple Access (SC-FDMA) systems, Time Division Synchronous Code Division Multiple Access (TD-SCDMA) systems, and Long Term Evolution (LTE). LTE / LTE-Advanced is a set of enhancements to the Universal Mobile Telecommunications System (UMTS) mobile standard issued by the 3rd Generation Partnership Project (3GPP).

[0003] A wireless network may include one or more network nodes that support communication for wireless communication devices, such as user equipment (UE) or multiple UEs. A UE may communicate with network nodes via downlink and uplink communication. A "downlink" (or "DL") refers to the communication link from the network node to the UE, and an "uplink" (or "UL") refers to the communication link from the UE to the network node. Some wireless networks may support device-to-device communication, such as via local links (e.g., sidelinks (SL), wireless local area network (WLAN) links, and / or wireless personal area network (WPAN) links, etc.).

[0004] The aforementioned multiple access technologies have been adopted in various telecommunications standards to provide a common protocol that enables different UEs to communicate at the city, country, region, and / or global levels. New Radio (NR) (which may be referred to as 5G) is a set of enhancements to the LTE mobile standard issued by 3GPP. NR is designed to better support mobile broadband internet access by: improving spectrum efficiency; reducing costs; improving service; utilizing new spectrum; and better integrating with other open standards by using Orthogonal Frequency Division Multiplexing (OFDM) with Cyclic Prefix (CP) on the downlink (CP-OFDM), and CP-OFDM and / or Single Carrier Frequency Division Multiplexing (SC-FDM) (also known as Discrete Fourier Transform Extended OFDM (DFT-s-OFDM)) on the uplink; and supporting beamforming, Multiple-Input Multiple-Output (MIMO) antenna technologies and carrier aggregation. Further improvements to LTE, NR, and other radio access technologies remain useful as the demand for mobile broadband access continues to increase. Summary of the Invention

[0005] Some aspects described herein relate to an apparatus for wireless communication at a test equipment (TE). The apparatus may include one or more memories and one or more processors coupled to the one or more memories. The one or more processors may be configured to cause the TE to transmit a Layer 1 (L1) reference signal received power (RSRP) or L1 signal-to-interference-plus-noise ratio (SINR) (L1-RSRP / L1-SINR) measurement associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurement associated with the first set of resources is at least partially based on a generative model for test data using randomized parameters. The one or more processors may be configured to cause the TE to receive beam prediction feedback associated with user equipment (UE) side beam prediction, at least partially based on the L1-RSRP / L1-SINR measurement associated with the first set of resources, wherein the beam prediction feedback indicates an L1-RSRP / L1-SINR measurement associated with a second set of resources.

[0006] Some aspects described herein relate to an apparatus for wireless communication at a UE. The apparatus may include one or more memories and one or more processors coupled to the one or more memories. The one or more processors may be configured to cause the UE to receive L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are at least partially based on a generative model for test data using randomized parameters. The one or more processors may be configured to cause the UE to transmit beam prediction feedback indicating L1-RSRP / L1-SINR measurements associated with a second set of resources, based at least partially on the L1-RSRP / L1-SINR measurements associated with the first set of resources.

[0007] Some aspects described herein relate to a method for wireless communication performed at a TE. The method may include transmitting L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are at least partially based on a generative model for test data using randomized parameters. The method may also include receiving beam prediction feedback associated with UE-side beam prediction based at least partially on the L1-RSRP / L1-SINR measurements associated with the first set of resources, wherein the beam prediction feedback indicates L1-RSRP / L1-SINR measurements associated with a second set of resources.

[0008] Some aspects described herein relate to a method for wireless communication performed at a UE. The method may include receiving L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are at least partially based on a generative model for test data using randomized parameters. The method may also include transmitting beam prediction feedback indicating L1-RSRP / L1-SINR measurements associated with a second set of resources, based at least partially on the L1-RSRP / L1-SINR measurements associated with the first set of resources.

[0009] Some aspects described herein relate to a non-transitory computer-readable medium storing a set of instructions for wireless communication by a TE. When executed by one or more processors of the TE, the set of instructions enables the TE to transmit L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are based at least in part on a generative model for test data using randomized parameters. When executed by one or more processors of the TE, the set of instructions enables the TE to receive beam prediction feedback associated with UE-side beam prediction based at least in part on the L1-RSRP / L1-SINR measurements associated with the first set of resources, wherein the beam prediction feedback indicates L1-RSRP / L1-SINR measurements associated with a second set of resources.

[0010] Some aspects described herein relate to a non-transitory computer-readable medium storing a set of instructions for wireless communication by a UE. When executed by one or more processors of the UE, the set of instructions enables the UE to receive L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are at least partially based on a generative model for test data using randomized parameters. When executed by one or more processors of the UE, the set of instructions enables the UE to transmit beam prediction feedback indicating L1-RSRP / L1-SINR measurements associated with a second set of resources, based at least partially on the L1-RSRP / L1-SINR measurements associated with the first set of resources.

[0011] Some aspects described herein relate to an apparatus for wireless communication. The apparatus may include components for transmitting L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are at least partially based on a generative model for test data using randomized parameters. The apparatus may also include components for receiving beam prediction feedback associated with UE-side beam prediction based at least partially on the L1-RSRP / L1-SINR measurements associated with the first set of resources, wherein the beam prediction feedback indicates L1-RSRP / L1-SINR measurements associated with a second set of resources.

[0012] Some aspects described herein relate to an apparatus for wireless communication. The apparatus may include components for receiving L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are at least partially based on a generative model for test data using randomized parameters. The apparatus may also include components for transmitting beam prediction feedback indicating L1-RSRP / L1-SINR measurements associated with a second set of resources, based at least partially on the L1-RSRP / L1-SINR measurements associated with the first set of resources.

[0013] The aspects generally include methods, apparatus, systems, computer program products, non-transitory computer-readable media, user equipment, base stations, network entities, network nodes, wireless communication devices and / or processing systems as fully described with reference to the accompanying drawings and description and illustrated as illustrated in the accompanying drawings and description.

[0014] The features and technical advantages of the examples according to this disclosure have been summarized rather extensively above to facilitate a better understanding of the detailed description below. Additional features and advantages will be described below. The disclosed concepts and specific examples can be readily used as the basis for modifying or designing other structures for achieving the same purpose of this disclosure. Such equivalent constructions do not depart from the scope of the appended claims. The characteristics of the concepts disclosed herein (both their organization and manner of operation) and their associated advantages will be better understood in conjunction with the accompanying drawings, based on the following description. Each of the drawings provided is for illustrative and descriptive purposes and not as a definition of limitation of the claims. Attached Figure Description

[0015] To gain a full understanding of the foregoing features of this disclosure, a more specific description of the brief overview can be obtained by referring to various aspects, some of which are illustrated in the accompanying drawings. However, it should be noted that the drawings illustrate only certain typical aspects of this disclosure and are therefore not to be considered as limiting its scope, as other equally valid aspects may be acknowledged in this description. The same reference numerals in different drawings may identify the same or similar elements.

[0016] Figure 1 This is a diagram illustrating an example of a wireless network according to the present disclosure.

[0017] Figure 2 This is a diagram illustrating an example of communication between a network node and a user equipment (UE) in a wireless network according to the present disclosure.

[0018] Figure 3 This is a diagram illustrating an example decomposed base station architecture according to this disclosure.

[0019] Figure 4 This is a diagram illustrating an example of beam management according to this disclosure.

[0020] Figures 5 to 8 This is a diagram illustrating an example of a generative model associated with a performance test data for UE-side beam prediction according to this disclosure.

[0021] Figures 9 to 10 This is a diagram illustrating an example process associated with a generative model for generating performance test data for UE-side beam prediction, according to this disclosure.

[0022] Figure 11 This is a diagram of an example device for wireless communication according to the present disclosure.

[0023] Figure 12 This is a diagram illustrating an example of a hardware implementation of a device for employing a processing system according to the present disclosure.

[0024] Figure 13 These are illustrations of specific implementations of the code and circuitry for the apparatus according to this disclosure.

[0025] Figure 14 This is a diagram of an example device for wireless communication according to the present disclosure.

[0026] Figure 15 This is a diagram illustrating an example of a hardware implementation of a device for employing a processing system according to the present disclosure.

[0027] Figure 16 These are illustrations of specific implementations of the code and circuitry for the apparatus according to this disclosure.

[0028] Figure 17A and Figure 17B This is a diagram illustrating an example of a machine learning (ML) model for beam prediction according to this disclosure. Detailed Implementation

[0029] User equipment (UE) can be configured to perform UE-side beam prediction. Based at least in part on UE-side beam prediction, the UE can use historical beam measurements of past UE beams to determine predicted beam measurements for upcoming moments. UE-side beam prediction may involve determining predicted beam measurements for upcoming moments. According to one example, the UE can run a UE-side artificial intelligence and / or machine learning (AI / ML) model for UE-side beam prediction. The UE can use performance tests to evaluate the accuracy of UE-side beam prediction. UE-side beam prediction can be evaluated across different operating scenarios and / or environments. Different operating scenarios and / or environments may include indoor / outdoor environments, large / small delay spread scenarios, and / or high / low Doppler drift scenarios.

[0030] Performance testing can typically be performed using over-the-air (OTA) testing, which may involve testing the performance level of UE-side beam prediction. In OTA testing, the test equipment (TE) sends historical beam measurements to the UE via the air interface. The UE can use UE-side beam prediction, at least in part, based on the historical beam measurements, to determine the predicted beam measurements for an upcoming event. The predicted beam measurements can be derived using the historical beam measurements. The TE, which can store the actual beam measurements associated with the historical beam measurements, can compare the predicted beam measurements with the actual beam measurements to evaluate the accuracy of the UE-side beam prediction.

[0031] However, using OTA testing (or OTA setup) to perform tests for UE-side beam prediction may not be ideal. When using OTA testing to evaluate the accuracy of UE-side beam prediction, generating various scenarios and / or environments associated with indoor / outdoor, large / small delay spread, and / or high / low Doppler drift can be relatively complex. In OTA setups, it may be impossible to simulate such a wide range of scenarios and / or environments, potentially resulting in UE-side beam prediction not being adequately evaluated for the UE. Performance testing using OTA may not verify the accuracy of UE-side beam prediction when facing various scenarios and / or environments. Therefore, UE-side beam prediction may be insufficiently tested, and relatively inaccurate UE-side beam prediction may be used, thus degrading the overall performance of the UE.

[0032] Furthermore, using OTA testing, the historical measurements provided by the TE to the UE can be relatively uncomplicated due to the bandwidth limitations of OTA testing. The UE may be able to determine (or predetermine) the measurements to be provided by the TE. The AI / ML model can be trained, at least in part, based on the predetermined measurements, thus enabling the UE to generate relatively accurate predicted beam measurements. However, the AI / ML model can be insufficiently trained using other measurements. When the TE receives relatively accurate predicted beam measurements from the UE, it may incorrectly determine that the UE-side beam prediction is relatively accurate. In other words, by having prior information about the measurements to be provided by the TE, the UE may "cheat" its UE-side beam prediction, and therefore, the TE may incorrectly assess the accuracy of the UE-side beam prediction.

[0033] Alternatively or additionally, in some aspects described herein, the TE may use a generative model for the test data to generate measurements. The generative model for the test data may be an AI / ML model. Measurements may include Layer 1 (L1) Reference Signal Received Power (RSRP) or L1 Signal-to-Interference-plus-Noise Ratio (SINR) (L1-RSRP / L1-SINR) measurements. Measurements may be associated with a first set of resources. The first set of resources may be a Synchronization Block (SSB) and / or a Channel State Information Reference Signal (CSI-RS). The generative model may use randomization parameters when generating the test data. Randomization parameters may be associated with network node antenna configuration, delay spread, indoor environment, outdoor environment, urban environment, rural environment, cell type, Doppler drift, and / or UE speed. Randomization parameters can be used to generate test data for various scenarios and / or environments, where randomization parameters prevent the UE from having prior information about the measurements to be provided by the UE. The TE may transmit the measurements to the UE via a cable connecting the TE and the UE. The UE may send beam prediction feedback, including predicted beam measurements, to the TE, which may be at least partially based on measurements sent by the TE. The TE may evaluate the accuracy of beam prediction on the UE side based at least partially on the predicted beam measurements.

[0034] In some respects, by using generative models based on test data to perform performance testing of UE-side beam prediction, the accuracy of UE-side beam prediction can be evaluated without relying on OTA testing. Generative models based on test data can simulate different operating scenarios and / or environments associated with indoor / outdoor conditions, large / small delay spread, and / or high / low Doppler drift. The performance testing of UE-side beam prediction using generative models based on test data, and the performance tests performed, enable thorough testing of UE-side beam prediction, preventing the use of relatively inaccurate UE-side beam prediction and thus improving the overall performance of the UE.

[0035] In some respects, when using a generative model to generate test data, the test data can be randomly generated for different operating scenarios and / or environments (e.g., using randomization parameters). Because the number of possible values ​​for the test data is relatively large, the UE is unlikely to know the content of the test data, and therefore, the UE is unlikely to "cheat" on performance tests. When a generative model is used to generate test data using randomization parameters, the UE is unlikely to know the content of the test data, so beam prediction feedback based at least in part on the test data can be a more reliable reflection of the accuracy of the UE-side beam prediction. For example, when the UE-side beam prediction has relatively poor accuracy, the UE may not be able to generate favorable beam prediction feedback using information already available about the content of the test data. Performance tests are unlikely to incorrectly indicate that the UE-side beam prediction is relatively accurate when they are not true. Having information about the true accuracy of the UE-side beam prediction can improve overall system performance.

[0036] Various aspects of this disclosure are described more fully below with reference to the accompanying drawings. However, this disclosure may be embodied in many different forms and should not be construed as limited to any particular structure or function presented throughout this disclosure. Rather, these aspects are provided so that this disclosure will be comprehensive and complete, and will fully convey the scope of this disclosure to those skilled in the art. Those skilled in the art will appreciate that the scope of this disclosure is intended to cover any aspect of this disclosure disclosed herein, whether implemented independently of or in combination with any other aspect of this disclosure. For example, any number of aspects set forth herein may be used to implement an apparatus or practice. Furthermore, the scope of this disclosure is intended to cover such apparatuses or methods practiced using structures, functionalities, or structures and functionalities other than or different from the various aspects of the disclosure set forth herein. It should be understood that any aspect of the disclosure herein may be embodied by one or more elements of the claims.

[0037] Various devices and techniques will now be used to illustrate several aspects of a telecommunications system. These devices and techniques will be described in detail below and illustrated in the accompanying drawings by various boxes, modules, components, circuits, steps, processes, or algorithms (collectively, “elements”). These elements can be implemented using hardware, software, or a combination thereof. Whether such elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the system as a whole.

[0038] Although terms generally associated with 5G or New Radio (NR) Radio Access Technology (RAT) may be used herein to describe aspects, aspects of this disclosure may be applied to other RATs, such as 3G RAT, 4G RAT and / or 5G and later (e.g., 6G) RATs.

[0039] Figure 1 This is a diagram illustrating an example of a wireless network 100 according to the present disclosure. The wireless network 100 may be a 5G (e.g., NR) network and / or a 4G (e.g., LTE) network, or may include elements of a 5G (e.g., NR) network and / or elements of a 4G (e.g., LTE) network, etc. The wireless network 100 may include one or more network nodes 110 (shown as network node 110a, network node 110b, network node 110c, and network node 110d), one or more UEs 120 (shown as UE 120a, UE 120b, UE 120c, UE 120d, and UE 120e), and / or other entities. Network node 110 is a network node that communicates with UE 120. As shown, network node 110 may include one or more network nodes. For example, network node 110 can be an aggregated network node, meaning that an aggregated network node is configured to utilize a radio protocol stack that is physically or logically integrated within a single radio access network (RAN) node (e.g., within a single device or unit). As another example, network node 110 can be a decomposed network node (sometimes referred to as a decomposed base station), meaning that network node 110 is configured to utilize a protocol stack that is physically or logically distributed among two or more nodes (such as one or more central units (CUs), one or more distributed units (DUs), or one or more radio units (RUs)).

[0040] In some examples, network node 110 is or includes network nodes (such as RUs) that communicate with UE 120 via a radio access link. In some examples, network node 110 is or includes network nodes (such as DUs) that communicate with other network nodes 110 via a fronthaul or midhaul link. In some examples, network node 110 is or includes network nodes (such as CUs) that communicate with other network nodes 110 via a midhaul link or with the core network via a backhaul link. In some examples, network node 110 (such as aggregated network node 110 or decomposed network node 110) may include multiple network nodes, such as one or more RUs, one or more CUs, and / or one or more DUs. Network node 110 may include, for example, NR base stations, LTE base stations, Node Bs, eNBs (e.g., in 4G), gNBs (e.g., in 5G), access points, Transmit / Receive Points (TRPs), DUs, RUs, CUs, network mobility elements, core network nodes, network elements, network equipment, RAN nodes, or combinations thereof. In some examples, network nodes 110 can interconnect with each other or to one or more other network nodes 110 in the wireless network 100 using any suitable transport network through various types of fronthaul, midhaul, and / or backhaul interfaces (such as direct physical connections, air interfaces, or virtual networks).

[0041] In some examples, network node 110 may provide communication coverage for a specific geographic area. In the 3rd Generation Partnership Project (3GPP), depending on the context of terminology use, the term "cell" may refer to the coverage area of ​​network node 110 and / or the network node subsystem serving that coverage area. Network node 110 may provide communication coverage for macrocells, picocells, femtocells, and / or another type of cell. A macrocell may cover a relatively large geographic area (e.g., with a radius of several kilometers) and may allow unrestricted access by UE 120 with a service subscription. A picocell may cover a relatively small geographic area and may allow unrestricted access by UE 120 with a service subscription. A femtocell may cover a relatively small geographic area (e.g., a home) and may allow restricted access by UE 120 associated with the femtocell (e.g., UE 120 in a Closed Subscriber Group (CSG)). Network node 110 used for macrocells may be referred to as a macro network node. Network node 110 used for picocells may be referred to as a pico network node. The network node 110 used for femtocells can be referred to as a femtocell network node or a home network node. Figure 1In the example shown, network node 110a can be a macro network node for macro cell 102a, network node 110b can be a pico network node for pico cell 102b, and network node 110c can be a femto network node for femto cell 102c. Network nodes can support one or more (e.g., three) cells. In some examples, the cells may not necessarily be stationary, and the geographical area of ​​the cells may move depending on the location of the mobile network node 110 (e.g., a mobile network node).

[0042] In some aspects, the term "base station" or "network node" may refer to an aggregated base station, a decomposed base station, an integrated access and backhaul (IAB) node, a relay node, or one or more components thereof. For example, in some aspects, "base station" or "network node" may refer to a CU, DU, RU, a near real-time (near RT) RAN intelligent controller (RIC), or a non-real-time (non-RT) RIC, or a combination thereof. In some aspects, the term "base station" or "network node" may refer to a device configured to perform one or more functions (such as those described herein in conjunction with network node 110). In some aspects, the term "base station" or "network node" may refer to multiple devices configured to perform one or more functions. For example, in some distributed systems, each of multiple different devices (which may be located in the same geographical location or different geographical locations) may be configured to perform at least a portion of a function, or to repeatedly perform at least a portion of that function, and the term "base station" or "network node" may refer to any one or more of these different devices. In some aspects, the term "base station" or "network node" may refer to one or more virtual base stations or one or more virtual base station functions. For example, in some aspects, two or more base station functions can be instantiated on a single device. In some aspects, the term "base station" or "network node" may refer to one base station function rather than another. In this way, a single device may include more than one base station.

[0043] Wireless network 100 may include one or more relay stations. A relay station is a network node that can receive data transmissions from upstream nodes (e.g., network node 110 or UE 120) and transmit data to downstream nodes (e.g., UE 120 or network node 110). A relay station may be a UE 120 that can relay transmissions for other UE 120s. Figure 1 In the example shown, network node 110d (e.g., a relay network node) can communicate with network node 110a (e.g., a macro network node) and UE 120d to facilitate communication between network node 110a and UE 120d. The network node 110 for relay communication may be referred to as a relay station, relay base station, relay network node, relay node, repeater, etc.

[0044] Wireless network 100 can be a heterogeneous network, comprising different types of network nodes 110, such as macro network nodes, pico network nodes, femto network nodes, relay network nodes, etc. These different types of network nodes 110 may have different transmit power levels, different coverage areas, and / or different effects on interference in wireless network 100. For example, macro network nodes may have high transmit power levels (e.g., 5 watts to 40 watts), while pico network nodes, femto network nodes, and relay network nodes may have lower transmit power levels (e.g., 0.1 watts to 2 watts).

[0045] Network controller 130 may be coupled to or communicate with a group of network nodes 110, and may provide coordination and control for these network nodes 110. Network controller 130 may communicate with network nodes 110 via a backhaul or midhaul communication link. Network nodes 110 may also communicate directly with each other, or indirectly via a wireless or wired backhaul communication link. In some aspects, network controller 130 may be a CU or a core network device, or may include a CU or a core network device.

[0046] UE 120 may be distributed throughout the wireless network 100, and each UE 120 may be stationary or mobile. UE 120 may include, for example, access terminals, terminals, mobile stations, and / or subscriber units. UE 120 may be a cellular phone (e.g., a smartphone), a personal digital assistant (PDA), a wireless modem, a wireless communication device, a handheld device, a laptop computer, a cordless phone, a wireless local loop (WLL) station, a tablet computer, a camera, a gaming device, a netbook, a smartbook, an ultrabook, a medical device, a biometric device, a wearable device (e.g., a smartwatch, smart clothing, smart glasses, a smart wristband, smart jewelry (e.g., a smart ring or smart bracelet)), an entertainment device (e.g., a music device, a video device, and / or a satellite radio), a vehicle component or sensor, a smart meter / sensor, industrial manufacturing equipment, a GPS device, a UE function of a network node, and / or any other suitable device configured to communicate via wireless or wired media.

[0047] Some UEs 120 may be considered Machine-Type Communication (MTC) or Evolved or Enhanced Machine-Type Communication (eMTC) UEs. MTC UEs and / or eMTC UEs may include, for example, robots, unmanned aerial vehicles, remote devices, sensors, instruments, monitors, and / or location tags that can communicate with network nodes, another device (e.g., a remote device), or some other entity. Some UEs 120 may be considered Internet of Things (IoT) devices, and / or may be implemented as NB-IoT (Narrowband IoT) devices. Some UEs 120 may be considered customer premises equipment. UEs 120 may be contained within a housing that houses components of the UE 120, such as processor components and / or memory components. In some examples, the processor components and memory components may be coupled together. For example, the processor components (e.g., one or more processors) and memory components (e.g., memory) may be operatively coupled, communicatively coupled, electronically coupled, and / or electrically coupled.

[0048] Generally, any number of wireless networks 100 can be deployed in a given geographical area. Each wireless network 100 can support a specific RAT and can operate on one or more frequencies. A RAT may be referred to as a radio technology, air interface, etc. A frequency may be referred to as a carrier, frequency channel, etc. Each frequency in a given geographical area can support a single RAT to avoid interference between wireless networks using different RATs. In some cases, NR or 5G RAT networks can be deployed.

[0049] In some examples, two or more UEs 120 (e.g., shown as UE 120a and UE 120e) may communicate directly using one or more sidelink channels (e.g., without using network node 110 as an intermediary device to communicate with each other). For example, UE 120 may communicate using peer-to-peer (P2P) communication, device-to-device (D2D) communication, vehicle-to-everything (V2X) protocols (e.g., which may include vehicle-to-vehicle (V2V) protocols, vehicle-to-infrastructure (V2I) protocols, or vehicle-to-pedestrian (V2P) protocols) and / or mesh networks. In such examples, UE 120 may perform scheduling operations, resource selection operations, and / or other operations described elsewhere herein as being performed by network node 110.

[0050] The electromagnetic spectrum is typically subdivided into various categories, bands, channels, etc., by frequency / wavelength. In 5G NR, two initial operating bands have been designated as frequency ranges FR1 (410MHz-7.125GHz) and FR2 (24.25GHz-52.6GHz). It should be understood that although a portion of FR1 is greater than 6GHz, in various documents and articles, FR1 is often (interchangeably) referred to as the "sub-6GHz" band. Similar naming issues sometimes occur with FR2, which is often (interchangeably) referred to as the "millimeter wave" band in documents and articles, although this is different from the Extremely High Frequency (EHF) band (30GHz to 300GHz) designated as "millimeter wave" by the International Telecommunication Union (ITU).

[0051] The frequencies between FR1 and FR2 are generally referred to as mid-band frequencies. Recent 5G NR studies have identified the operating bands used for these mid-band frequencies as the frequency range designation FR3 (7.125 GHz to 24.25 GHz). Bands falling within FR3 can inherit FR1 and / or FR2 characteristics, and thus can effectively extend the features of FR1 and / or FR2 to mid-band frequencies. Furthermore, higher frequency bands are currently being explored to extend 5G NR operation beyond 52.6 GHz. For example, three higher operating frequency bands have been identified as the frequency range designations FR4a or FR4-1 (52.6 GHz to 71 GHz), FR4 (52.6 GHz to 114.25 GHz), and FR5 (114.25 GHz to 300 GHz). Each of these higher frequency bands falls within the EHF band.

[0052] Considering the examples above, unless otherwise specifically stated, it should be understood that if the term "below 6 GHz" is used herein, it can broadly refer to frequencies below 6 GHz, within FR1, or including intermediate frequency bands. Furthermore, unless otherwise specifically stated, it should be understood that if the term "millimeter wave" is used herein, it can broadly refer to frequencies that can include intermediate frequency bands, within FR2, FR4, FR4-a, or FR4-1 and / or FR5, or within the EHF band. Modifications to frequencies included in these operating frequency bands (e.g., FR1, FR2, FR3, FR4, FR4-a, FR4-1, and / or FR5) are contemplated, and the techniques described herein are applicable to those modified frequency ranges.

[0053] In some aspects, the TE (e.g., TE 122) may include a communication manager 150. As described in more detail elsewhere herein, the communication manager 150 may transmit L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are based at least in part on a generative model for test data using randomized parameters; and receive beam prediction feedback associated with UE-side beam prediction based at least in part on the L1-RSRP / L1-SINR measurements associated with the first set of resources, wherein the beam prediction feedback indicates L1-RSRP / L1-SINR measurements associated with a second set of resources. Additionally or alternatively, the communication manager 150 may perform one or more other operations described herein.

[0054] In some aspects, the UE (e.g., UE 120) may include a communication manager 140. As described in more detail elsewhere herein, the communication manager 140 may receive L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are based at least in part on a generative model for test data using randomized parameters; and transmit beam prediction feedback indicating L1-RSRP / L1-SINR measurements associated with a second set of resources, based at least in part on the L1-RSRP / L1-SINR measurements associated with the first set of resources. Additionally or alternatively, the communication manager 140 may perform one or more other operations described herein.

[0055] As indicated above, Figure 1 This is provided as an example. Other examples are available with reference to [the relevant information]. Figure 1 The examples described are different.

[0056] Figure 2 This is a diagram illustrating example 200 of communication between network node 110 and UE 120 in a wireless network 100 according to this disclosure. Network node 110 may be equipped with a set of antennas 234a to 234t, such as... T One antenna ( T ≥1). The UE 120 may be equipped with a set of antennas 252a to 252r, such as R One antenna ( R ≥1). Network node 110 of Example 200 includes one or more radio frequency components, such as antenna 234 and modem 232. In some examples, network node 110 may include an interface, communication components, or another component that facilitates communication with UE 120 or another network node. Some network node 110 may not include radio frequency components that facilitate direct communication with UE 120, such as one or more CUs or one or more DUs.

[0057] At network node 110, transmitting processor 220 can receive data from data source 212 intended for use by UE 120 (or a group of UEs 120). Transmitting processor 220 can select one or more modulation and decoding schemes (MCS) for UE 120 based at least in part on one or more channel quality indicators (CQIs) received from UE 120. Network node 110 can process (e.g., encode and modulate) the data for UE 120 based at least in part on the MCS selected for UE 120 and can provide data symbols for UE 120. Transmitting processor 220 can process system information (e.g., semi-static resource partitioning information (SRPI)) and control information (e.g., CQI requests, grants, and / or upper-layer signaling) and provide overhead symbols and control symbols. Transmitting processor 220 can generate reference symbols for reference signals (e.g., cell-specific reference signals (CRS) or demodulation reference signals (DMRS)) and synchronization signals (e.g., primary synchronization signal (PSS) or secondary synchronization signal (SSS)). The transmit (TX) multiple-input multiple-output (MIMO) processor 230 can perform spatial processing (e.g., pre-decoding) on ​​data symbols, control symbols, overhead symbols, and / or reference symbols where applicable, and can transmit a set of output symbol streams (e.g., T Each output symbol stream is provided to a corresponding set of modems 232 (e.g., ...). T Each modem 232a to 232t may be used to process a corresponding output symbol stream (e.g., for OFDM) to obtain an output sample stream. For example, each output symbol stream may be provided to a modulator component (MOD) of modem 232. Each modem 232 may use a corresponding modulator component to process the corresponding output symbol stream (e.g., for OFDM) to obtain an output sample stream. Each modem 232 may also use a corresponding modulator component to process the output sample stream (e.g., convert to analog, amplify, filter, and / or up-convert) to obtain a downlink signal. Modems 232a to 232t may be used via a corresponding set of antennas 234 (e.g., T Each antenna (shown as antennas 234a to 234t) is used to transmit a set of downlink signals (e.g., ...). T (One downlink signal).

[0058] At UE 120, a set of antennas 252 (shown as antennas 252a to 252r) can receive downlink signals from network node 110 and / or other network nodes 110 and can transmit a set of received signals (e.g., R The received signals are provided to a group of modems 254 (e.g., REach modem 254 (shown as modems 254a to 254r) may receive a signal. For example, each received signal may be provided to a demodulator component (shown as DEMOD) of modem 254. Each modem 254 may use a corresponding demodulator component to condition (e.g., filter, amplify, down-convert, and / or digitize) the received signal to obtain an input sample. Each modem 254 may use a demodulator component to further process the input sample (e.g., for OFDM) to obtain a received symbol. MIMO detector 256 may obtain the received symbols from modem 254, perform MIMO detection on the received symbols where applicable, and provide the detected symbols. Receiver processor 258 may process (e.g., demodulate and decode) the detected symbols, provide the decoded data for UE 120 to data sink 260, and provide the decoded control information and system information to controller / processor 280. The term "controller / processor" may refer to one or more controllers, one or more processors, or a combination thereof. The channel processor can determine parameters such as the Reference Signal Received Power (RSRP), Received Signal Strength Indicator (RSSI), Reference Signal Received Quality (RSRQ), and / or CQI. In some examples, one or more components of the UE 120 may be included in the housing 284.

[0059] Network controller 130 may include communication unit 294, controller / processor 290, and memory 292. Network controller 130 may include one or more devices, for example, in a core network. Network controller 130 may communicate with network node 110 via communication unit 294.

[0060] One or more antennas (e.g., antennas 234a to 234t and / or antennas 252a to 252r) may include one or more antenna panels, one or more antenna groups, one or more sets of antenna elements and / or one or more antenna arrays, etc., or may be included within one or more antenna panels, one or more antenna groups, one or more sets of antenna elements and / or one or more antenna arrays, etc. Antenna panels, antenna groups, sets of antenna elements and / or antenna arrays may include one or more antenna elements (within a single housing or multiple housings), a set of coplanar antenna elements, a set of non-coplanar antenna elements and / or coupled to one or more transmitting and / or receiving components (such as...). Figure 2 One or more antenna elements (one or more components in a )

[0061] On the uplink, at UE 120, the transmit processor 264 can receive and process data from data source 262 and control information from controller / processor 280 (e.g., for reporting including RSRP, RSSI, RSRQ, and / or CQI). The transmit processor 264 can generate reference symbols for one or more reference signals. The symbols from the transmit processor 264 can be pre-decoded by the TX MIMO processor 266, where applicable, further processed by the modem 254 (e.g., for DFT-s-OFDM or CP-OFDM), and transmitted to network node 110. In some examples, the modem 254 of UE 120 may include a modulator and demodulator. In some examples, UE 120 includes a transceiver. This transceiver may include any combination of antenna 252, modem 254, MIMO detector 256, receive processor 258, transmit processor 264, and / or TX MIMO processor 266. The transceiver may be used by a processor (e.g., controller / processor 280) and memory 282 to perform aspects of any of the methods described herein.

[0062] At network node 110, uplink signals from UE 120 and / or other UEs may be received by antenna 234, processed by modem 232 (e.g., demodulator component of modem 232 (shown as DEMOD)), detected by MIMO detector 236, and further processed by receiver processor 238 to obtain decoded data and control information transmitted by UE 120. Receiver processor 238 may provide the decoded data to data sink 239 and the decoded control information to controller / processor 240. Network node 110 may include communication unit 244 and may communicate with network controller 130 via communication unit 244. Network node 110 may include scheduler 246 to schedule one or more UEs 120 for downlink and / or uplink communication. In some examples, modem 232 of network node 110 may include modulator and demodulator. In some examples, network node 110 includes transceiver. The transceiver may include any combination of antenna 234, modem 232, MIMO detector 236, receive processor 238, transmit processor 220 and / or TX MIMO processor 230. The transceiver may be used by a processor (e.g., controller / processor 240) and memory 242 to perform aspects of any of the methods described herein.

[0063] The controller / processor 240 of network node 110, the controller / processor 280 of UE 120 and / or Figure 2Any other component may perform one or more techniques associated with the generative model used to generate performance test data for UE side beam prediction, as described in more detail elsewhere herein. In some respects, the TE described herein is UE 120, is included in UE 120, or includes Figure 2 One or more components of the UE 120 shown. For example, the controller / processor 240 of network node 110, the controller / processor 280 of UE 120, and / or Figure 2 Any other component that can execute or direct, for example Figure 9 The process 900 Figure 10 The operation of process 1000 and / or other processes as described herein. Memory 242 and memory 282 may store data and program code for network node 110 and UE 120, respectively. In some examples, memory 242 and / or memory 282 may include a non-transitory computer-readable medium storing one or more instructions (e.g., code and / or program code) for wireless communication. For example, the one or more instructions may cause the one or more processors, UE 120 and / or network node 110 to perform or direct, for example, when executed by one or more processors of network node 110 and / or UE 120 (e.g., directly, or after compilation, transformation and / or interpretation). Figure 9 The process 900 Figure 10 The operation of process 1000 and / or other processes as described herein. In some examples, the execution instructions may include run instructions, transform instructions, compile instructions and / or interpret instructions, etc.

[0064] In some aspects, the TE (e.g., TE 122) includes components for transmitting L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are at least partially based on a generative model for test data using randomized parameters; and / or components for receiving beam prediction feedback associated with UE-side beam prediction based at least partially on the L1-RSRP / L1-SINR measurements associated with the first set of resources, wherein the beam prediction feedback indicates L1-RSRP / L1-SINR measurements associated with a second set of resources. In some aspects, components for the TE to perform the operations described herein may include, for example, one or more of a communication manager 150, an antenna 252, a modem 254, a MIMO detector 256, a receive processor 258, a transmit processor 264, a TX MIMO processor 266, a controller / processor 280, or a memory 282.

[0065] In some aspects, the UE (e.g., UE 120) includes components for receiving L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are at least partially based on a generative model for test data using randomized parameters; and / or components for transmitting beam prediction feedback indicating L1-RSRP / L1-SINR measurements associated with a second set of resources, based at least partially on the L1-RSRP / L1-SINR measurements associated with the first set of resources. In some aspects, components for the UE to perform the operations described herein may include one or more of, for example, a communication manager 140, an antenna 252, a modem 254, a MIMO detector 256, a receive processor 258, a transmit processor 264, a TX MIMO processor 266, a controller / processor 280, or a memory 282.

[0066] Although Figure 2 The boxes in the diagram are illustrated as different components, but the functions described above with respect to these boxes may be implemented in a single hardware, software, or combined component, or in various combinations of components. For example, the functions described with respect to transmit processor 264, receive processor 258, and / or TX MIMO processor 266 may be performed by or under the control of controller / processor 280.

[0067] In some respects, a single processor can perform all the functions described as being performed by that one or more processors. In other respects, the one or more processors can jointly perform a set of functions. For example, a first group(s) of the one or more processors can perform a first function described as being performed by that one or more processors, and a second group(s) of the one or more processors can perform a second function described as being performed by that one or more processors. The first group and the second group of processors can be the same group of processors or can be different groups of processors. The reference to "one or more processors" should be understood as referring to a combination of functions. Figure 2 Any one or more processors described. The reference to "one or more memories" should be understood to refer to any one or more memories of the corresponding device, such as those in conjunction with... Figure 2 The memory described. For example, a function described as being performed by one or more memories can be performed by the same subset of the one or more memories or by different subsets of the one or more memories.

[0068] As indicated above, Figure 2 This is provided as an example. Other examples are available with reference to [the relevant information]. Figure 2 The examples described are different.

[0069] Communication systems (such as 5G NR systems) can be deployed in various ways with a variety of components or parts. In a 5G NR system or network, network nodes, network entities, network mobility elements, RAN nodes, core network nodes, network elements, base stations, or network equipment can be implemented in either a converged or decomposed architecture. For example, a base station (such as a Node B (NB), evolved NB (eNB), NR base station, 5G NB, access point (AP), TRP, or cell, etc.) or one or more units (or components) performing base station functionality can be implemented as a converged base station (also known as a standalone base station or monolithic base station) or a decomposed base station. A "network entity" or "network node" can refer to a decomposed base station or one or more units of a decomposed base station (such as one or more CUs, one or more DUs, one or more RUs, or combinations thereof).

[0070] Aggregated base stations (e.g., aggregated network nodes) can be configured to utilize a radio protocol stack that is physically or logically integrated within a single RAN node (e.g., within a single device or cell). Decomposed base stations (e.g., decomposed network nodes) can be configured to utilize a protocol stack that is physically or logically distributed across two or more cells (such as one or more CUs, one or more DUs, or one or more RUs). In some examples, the CU may be implemented within a network node, and one or more DUs may be co-located with the CU, or alternatively, may be geographically or virtually distributed across one or more other network nodes. DUs may be implemented to communicate with one or more RUs. Each of the CU, DU, and RU can also be implemented as a virtual cell, such as a Virtual Central Unit (VCU), a Virtual Distributed Unit (VDU), or a Virtual Radio Unit (VRU), etc.

[0071] Base station type operation or network design can take into account the aggregation characteristics of base station functionality. For example, decomposed base stations can be utilized in IAB networks, Open Radio Access Networks (O-RAN (such as network configurations initiated by the O-RAN Alliance)), or Virtualized Radio Access Networks (vRAN, also known as Cloud Radio Access Networks (C-RAN)) to facilitate the scaling of communication systems by separating base station functionality into one or more units that can be deployed independently. Decomposed base stations can include functionality implemented by two or more units across various physical locations, as well as functionality virtually implemented for at least one unit, which enables flexibility in network design. The various units of a decomposed base station can be configured for wired or wireless communication with at least one other unit of the decomposed base station.

[0072] Figure 3This is an illustration of an example disaggregated base station architecture 300 according to this disclosure. The disaggregated base station architecture 300 may include a CU 310, which may communicate directly with the core network 320 via a backhaul link, or indirectly with the core network 320 via one or more disaggregated control units (such as near-RT RIC 325 via an E2 link, or a non-RT RIC 315 associated with a Service Management and Orchestration (SMO) framework 305, or both). The CU 310 may communicate with one or more DUs 330 via a corresponding midhaul link (such as via an F1 interface). Each DU 330 may communicate with one or more RUs 340 via a corresponding fronthaul link. Each RU 340 may communicate with one or more UEs 120 via a corresponding radio frequency (RF) access link. In some implementations, a UE 120 may be served simultaneously by multiple RUs 340.

[0073] Each unit in the cells (including CU 310, DU 330, RU 340), as well as the near-RT RIC 325, non-RT RIC 315, and SMO frame 305, may include or be coupled to one or more interfaces configured to receive or transmit signals, data, or information (collectively, signals) via wired or wireless transmission media. Each unit in the cell, or an associated processor or controller providing instructions to one or more communication interfaces of the corresponding unit, may be configured to communicate with one or more units in other cells via transmission media. In some examples, each unit in the cell may include a wired interface and a wireless interface configured to receive signals via a wired transmission media or transmit signals to one or more units in other cells, and the wireless interface may include a receiver, transmitter, or transceiver (such as an RF transceiver) configured to receive signals via a wireless transmission media or transmit signals to one or more units in other cells, or both.

[0074] In some aspects, the CU 310 can host one or more higher-level control functions. Such control functions may include Radio Resource Control (RRC) functions, Packet Data Convergence Protocol (PDCP) functions, or Service Data Adaptation Protocol (SDAP) functions, etc. Each control function can be implemented using an interface configured to signal to other control functions hosted by the CU 310. The CU 310 can be configured to handle user plane functions (e.g., Central Unit-User Plane (CU-UP) functions), control plane functions (e.g., Central Unit-Control Plane (CU-CP) functions), or combinations thereof. In some implementations, the CU 310 can be logically split into one or more CU-UP units and one or more CU-CP units. When implemented in an O-RAN configuration, the CU-UP units can communicate bidirectionally with the CU-CP units via an interface such as an E1 interface. The CU 310 can be implemented to communicate with the DU 330 for network control and signaling purposes, as needed.

[0075] Each DU 330 may correspond to a logical unit comprising one or more base station functions for controlling the operation of one or more RU 340s. In some aspects, the DU 330 may, at least in part, host one or more of the Radio Link Control (RLC) layer, Medium Access Control (MAC) layer, and one or more high physical (PHY) layers, depending on functional splits (such as those defined by 3GPP). In some aspects, the one or more high PHY layers may be implemented by one or more modules for forward error correction (FEC) encoding and decoding, scrambling, and modulation and demodulation, etc. In some aspects, the DU 330 may also host one or more low PHY layers, such as those implemented by one or more modules for Fast Fourier Transform (FFT), Inverse FFT (iFFT), Digital Beamforming, or Physical Random Access Channel (PRACH) extraction and filtering, etc. Each layer (which may also be referred to as a module) may be implemented using an interface configured to communicate signals with other layers (and modules) hosted by the DU 330 or with control functions hosted by the CU 310.

[0076] Each RU 340 can implement lower-layer functionality. In some deployments, an RU 340 controlled by a DU 330 can correspond to a logical node that hosts RF processing functions or low-PHY layer functions, such as performing FFT, performing iFFT, digital beamforming, or PRACH extraction and filtering, based on function splitting (e.g., function splitting defined by 3GPP) (such as lower-layer function splitting). In this architecture, each RU 340 can be operated to handle OTA communication with one or more UEs 120. In some specific implementations, the real-time and non-real-time aspects of control plane and user plane communication with the RU 340 can be controlled by the corresponding DU 330. In some scenarios, this configuration allows each DU 330 and CU 310 to be implemented in a cloud-based RAN architecture, such as a vRAN architecture.

[0077] The SMO framework 305 can be configured to support RAN deployment and provisioning of both non-virtualized and virtualized network elements. For non-virtualized network elements, the SMO framework 305 can be configured to support the deployment of dedicated physical resources for RAN coverage requirements, which can be managed via operation and maintenance interfaces such as the O1 interface. For virtualized network elements, the SMO framework 305 can be configured to interact with cloud computing platforms such as the Open Cloud (O-Cloud) platform 390 to perform network element lifecycle management (such as instantiating virtualized network elements) via cloud computing platform interfaces such as the O2 interface. Such virtualized network elements may include, but are not limited to, CU 310, DU 330, RU 340, non-RT RIC 315, and near-RT RIC 325. In some specific implementations, the SMO framework 305 may communicate with hardware aspects of the 4G RAN, such as the Open eNB (O-eNB) 311, via the O1 interface. Additionally, in some implementations, the SMO framework 305 can communicate directly with each of one or more RUs 340 via a corresponding O1 interface. The SMO framework 305 may also include a non-RT RIC 315 configured to support the functionality of the SMO framework 305.

[0078] The non-RT RIC 315 can be configured to include logical functions enabling non-real-time control and optimization of RAN elements and resources, including AI / ML workflows for model training and updates, or policy-based guidance for applications / features in the near-RT RIC 325. The non-RT RIC 315 can be coupled to or communicate with the near-RT RIC 325, such as via an A1 interface. The near-RT RIC 325 can be configured to include logical functions enabling near real-time control and optimization of RAN elements and resources via data collection and actions through an interface such as an E2 interface, connecting one or more CU310s, one or more DU 330s, or both, and O-eNBs to the near-RT RIC 325.

[0079] In some implementations, to generate AI / ML models to be deployed in the near-RT RIC 325, the non-RT RIC 315 may receive parameters or external enrichment information from an external server. This information can be utilized by the near-RT RIC 325 and can be received from non-network data sources or network functions at the SMO framework 305 or the non-RT RIC 315. In some examples, the non-RT RIC 315 or the near-RT RIC 325 may be configured to tune RAN behavior or performance. For example, the non-RT RIC 315 may monitor long-term trends and patterns in performance and employ AI / ML models to perform corrective actions via the creation of the SMO framework 305 (such as reconfiguration via the O1 interface) or via RAN management policies (such as A1 interface policies).

[0080] As indicated above, Figure 3 This is provided as an example. Other examples are available with reference to [the relevant information]. Figure 3 The examples described are different.

[0081] Figure 4 This is a diagram illustrating example 400 of beam management according to this disclosure.

[0082] As shown by reference numeral 402, the UE can initially be in an RRC idle state or an RRC inactive state. As shown by reference numeral 404, the UE can perform initial access. As shown by reference numeral 406, the UE can perform beam management after entering the RRC connected state. Beam management can include P1, P2, and / or P3 beam management procedures. The P1 beam management procedure can be a beam selection procedure, an initial beam acquisition procedure, a beam scanning procedure, a cell search procedure, and / or a beam search procedure. The P2 beam management procedure can be a beam refinement procedure, a network node beam refinement procedure, a TRP beam refinement procedure, and / or a Tx beam refinement procedure. The P3 beam management procedure can be a beam refinement procedure, a UE beam refinement procedure, and / or a receive (Rx) beam refinement procedure. As shown by reference numeral 408, the UE can also perform beam management using AI / ML-based methods. Beam management using AI / ML-based methods can utilize AI / ML models in the spatial (SD), temporal (TD), and / or frequency (FD) domains, which can reduce signaling overhead and latency and improve beam selection accuracy. AI / ML models can be associated with lifecycle management, which may involve model training, model deployment, model inference, model monitoring, and / or model updates. As shown by reference numeral 410, the UE can perform beam failure detection (BFD), which may be based at least in part on measurements obtained during beam management after entering RRC connected mode. As shown by reference numeral 412, the UE can perform beam failure recovery (BFR) based at least in part on BFD. As shown by reference numeral 414, when BFR fails, the UE can declare a radio link failure (RLF).

[0083] As indicated above, Figure 4 This is provided as an example. Other examples are available with reference to [the relevant information]. Figure 4 The examples described are different.

[0084] For AI / ML-based beam management, a first beam management scenario and a second beam management scenario can be supported for characterization and baseline performance evaluation. The first beam management scenario may involve SD downlink beam prediction for a first set of beams (set A), based at least in part on measurements of a second set of beams (set B). The second beam management scenario may involve temporal downlink beam prediction for the first set of beams, based at least in part on historical measurements of the second set of beams. For both the first and second beam management scenarios, the beams in the first set and the beams in the second set of beams can be within the same frequency range.

[0085] In the first beam management scenario, in the first alternative, the second set of beams may be a subset of the first set of beams. In the first alternative, the first set and the second set of beams may each be associated with a defined number of beams. The second set of beams may be determined from the beams in the first set of beams, at least in part, based on a fixed or random pattern. In the second alternative, the first set of beams may differ from the second set of beams (e.g., the first set of beams may include narrow beams, and the second set of beams may include wide beams). In the second alternative, the first set and the second set of beams may each be associated with a defined number of beams. Quasi-co-location (QCL) relationships may be defined between the beams in the first set and the beams in the second set of beams. Furthermore, the first set of beams can be used for downlink beam prediction, and the second set of beams can be used for downlink beam measurement.

[0086] For the first beam management scenario and utilizing the UE-side AI / ML model, Layer 1 (L1) signaling can be used to report information associated with the AI / ML model inference to network nodes. This information may indicate one or more beams (e.g., the reported beams) based at least in part on the output of the AI / ML model inference. This information may also indicate the predicted L1-RSRP measurement corresponding to one or more beams.

[0087] For second-beam management scenarios and utilizing UE-side AI / ML models, L1 signaling can be used to report information associated with AI / ML model inferences to network nodes. This information can indicate... N One or more beams for an upcoming time instance, wherein the one or more beams may be at least partially based on the output inferred from an AI / ML model. Defineable N The value of . This information can indicate the predicted L1-RSRP measurement corresponding to one or more beams. This information can indicate the timestamp corresponding to one or more beams, wherein the timestamp can be indicated explicitly or implicitly.

[0088] For both first and second beam management scenarios utilizing UE-side AI / ML models, model monitoring can be employed. For UE-side model monitoring, the UE can monitor performance metrics. The UE can make decisions regarding model selection, activation, deactivation, switching, or rollback operations based at least partially on these performance metrics. For network-side model monitoring, network nodes can monitor performance metrics. Network nodes can make decisions regarding model selection, activation, deactivation, switching, or rollback operations based at least partially on these performance metrics. In hybrid model monitoring, the UE can monitor performance metrics, and network nodes can make decisions regarding model selection, activation, deactivation, switching, or rollback operations based at least partially on these performance metrics.

[0089] For both first and second beam management scenarios utilizing network-side AI / ML models, network-side model monitoring can be employed. Network nodes can monitor performance metrics, and can make decisions regarding model selection, activation, deactivation, switching, or rollback operations based at least partially on these performance metrics. For both first and second beam management scenarios utilizing network-side AI / ML models, beam measurements and reporting for model monitoring can be used. For both first and second beam management scenarios utilizing network-side AI / ML models, the UE can report measurement results for more than four beams in a single reporting instance, based at least partially on L1 beam reports used for AI / ML model inference.

[0090] UE performance testing can be used to evaluate the accuracy of UE-side beam prediction. Performance testing can indicate whether the UE-side beam prediction is relatively accurate or relatively inaccurate. UE-side beam prediction may include AI / ML-based L1-RSRP / L1-SINR prediction and / or AI / ML-based top K resource prediction. This UE-side beam prediction can be validated through performance testing across different operating scenarios and / or environments. Different operating scenarios and / or environments may include indoor / outdoor environments, large / small delay spread scenarios, and / or high / low Doppler drift scenarios.

[0091] Over-the-air (OTA) testing is typically used for performance testing. OTA testing can be used for L1-RSRP / L1-SINR measurement testing, which can be considered at least partially based on a relatively simple indoor environment. However, using OTA testing (or OTA setup) to perform tests targeting UE-side beam prediction may not be appropriate. When using OTA testing to evaluate the accuracy of UE-side beam prediction, generating various scenarios and / or environments associated with indoor / outdoor, large / small delay spread, and / or high / low Doppler drift can be relatively complex. In an OTA setup, it may be impossible to simulate such a variety of scenarios and / or environments, potentially resulting in UE-side beam prediction not being adequately evaluated for the UE. When facing various scenarios and / or environments, performance testing using OTA may not verify the accuracy of UE-side beam prediction. Therefore, UE-side beam prediction may not be adequately tested, and relatively inaccurate UE-side beam prediction may be used, thus degrading the overall performance of the UE.

[0092] In various aspects of the techniques and apparatus described herein, the TE can use a generative model for test data, at least in part based on randomization parameters, to generate L1-RSRP / L1-SINR measurements associated with a first set of resources. The generative model for test data can use randomization parameters when deriving the L1-RSRP / L1-SINR measurements associated with the first set of resources. The TE can send the L1-RSRP / L1-SINR measurements associated with the first set of resources to the UE. The TE can use the generative model for test data to generate reproduced L1-RSRP / L1-SINR measurements associated with a second set of resources. The UE can determine the L1-RSRP / L1-SINR measurements associated with the second set of resources, at least in part based on the L1-RSRP / L1-SINR measurements associated with the first set of resources and at least in part based on UE-side beam prediction. The TE can receive beam prediction feedback from the UE indicating the L1-RSRP / L1-SINR measurements associated with the second set of resources. The UE can perform a comparison of reproduced L1-RSRP / L1-SINR measurements associated with a second set of resources and L1-RSRP / L1-SINR measurements associated with the second set of resources received from the UE. The UE can determine the accuracy of UE-side beam prediction based at least in part on the comparison.

[0093] In some aspects, performance testing of UE-side beam prediction (e.g., AI / ML-based beam prediction) may be based at least in part on the performance tests performed and a generative model (or multiple generative models) for the test data. The UE may be connected to the TE via cable. Instead of measuring signals via OTA, the UE may receive test data from the TA via cable. The test data may be in the form of measurements of a wide beam (e.g., a set of B beams). The UE may send beam prediction feedback to the TE via cable or via an air interface using OTA. The prediction results may be based at least in part on the test data. The TE may receive the prediction results from the UE. The TE may compare the prediction results with true values ​​(e.g., values ​​that should be derived given the test data), and based at least in part on the comparison, the TE may determine the prediction accuracy performance of the UE-side beam prediction.

[0094] In some aspects, the generative model for the test data can be defined in a standard that allows the TE to prepare test data (e.g., a test dataset) following uniform rules. Test data that can be associated with the measurement results of set B can be generated in a predefined manner according to the standard. In some aspects, an interface for transferring test data between the UE and the TE can be defined. Rules for transferring test data generated by the generative model from the TE to the UE, as well as connections regarding defined beam prediction feedback mechanisms, can be defined. For example, associations can define which L1-RSRP / L1-SINR measurements are associated with which defined beam prediction feedback timing.

[0095] In some respects, performance testing of UE-side beam prediction can be performed using generative models based on test data and the resulting performance tests, allowing for the evaluation of UE-side beam prediction accuracy without relying on OTA testing. Generative models based on test data can simulate different operating scenarios and / or environments associated with indoor / outdoor conditions, large / small delay spread, and / or high / low Doppler drift. Using generative models based on test data for UE-side beam prediction performance testing and the resulting performance tests ensure thorough testing of UE-side beam prediction, preventing the use of relatively inaccurate UE-side beam prediction and thus improving the overall performance of the UE.

[0096] In some respects, when using a generative model to derive test data, the test data can be randomly generated for different operating scenarios and / or environments (e.g., using randomization parameters). Because the number of possible values ​​for the test data is large, the UE is unlikely to know the content of the test data, and therefore, the UE is unlikely to "cheat" on performance tests. For example, UE-side beam prediction may have relatively poor accuracy, but when the UE-side beam prediction knows the test data, the UE may produce favorable beam prediction feedback because the test data is known to the UE. Performance tests may incorrectly indicate that the UE-side beam prediction is relatively accurate, even if this is not true. On the other hand, when a generative model is used to generate test data using randomization parameters, the UE is unlikely to know the content of the test data, and therefore beam prediction feedback based at least in part on the test data can be a more reliable reflection of the accuracy of the UE-side beam prediction.

[0097] Figure 5 This is a diagram illustrating an example 500 associated with a generative model used to generate performance test data for UE-side beam prediction, according to this disclosure. Figure 5 As shown, Example 500 includes communication between a TE (e.g., TE 122) and a UE (e.g., UE 120). In some aspects, the TE and UE may be included in a wireless network (such as wireless network 100).

[0098] As shown by reference numeral 502 in the attached figure, the TE can use a generative model for the test data, at least in part based on randomization parameters, to generate L1-RSRP / L1-SINR measurements associated with a first set of resources. The generative model for the test data, or the parameters associated with it, can be at least in part defined in a standard (e.g., a 3GPP specification). In some aspects, the generative model for the test data can be defined at least in part based on analytical or statistical expressions to generate L1-RSRP / L1-SINR measurements associated with a first set of resources, utilizing randomization parameters. The randomization parameters can be modified by the TE. The randomization parameters can be associated with network node antenna configuration, delay spread, indoor environment, outdoor environment, urban environment, rural environment, cell type, Doppler drift, and / or UE speed. In some aspects, the generative model for the test data can be defined at least in part based on an AI / ML model. Inputs to the AI / ML model can include randomization parameters. AI / ML model inputs can be modified by the TE. In some respects, the L1-RSRP / L1-SINR measurement associated with the first set of resources may be correlated with one or more historical TD events. The L1-RSRP / L1-SINR measurement associated with the first set of resources may be based at least in part on changes in the randomization parameter across one or more historical TD events.

[0099] In some aspects, a generative model for the test data may be specified in the standard, and / or the parameters of the generative model for the test data may be specified in the standard, either fully or partially. In some aspects, the generative model for the test data may be defined at least in part based on explicit expressions, analytical expressions, and / or statistical expressions to reproduce L1-RSRP / L1-SINR measurements, and may utilize certain randomization parameters that can be changed by the TE. Variations of certain randomization parameters may be at least partially transparent to the UE. Assumptions may be made at least in part based on explicit expressions, analytical expressions, and / or statistical expressions regarding network node and UE antenna configurations, UE orientation, UE movement direction / speed, and / or channel propagation behavior between the UE and network nodes. L1-RSRP / L1-SINR measurements may be reproduced at least in part based on such assumptions. Parameters associated with the UE may be compatible with the configuration associated with the UE. Randomization parameters may include network node antenna configuration, delay spread, indoor / outdoor environment, urban / rural environment, macro / microcell, Doppler drift, and / or speeds associated with the UE and / or network nodes.

[0100] In some aspects, a particular L1-RSRP / L1-SINR measurement received by the UE can be associated with randomization parameters, and this association can be transparent to the UE. For example, a first L1-RSRP / L1-SINR measurement received by the UE can be associated with a 20ns delay spread, and a second L1-RSRP / L1-SINR measurement received by the UE can be associated with a 300ns delay spread, but the UE may not be aware that the first and second L1-RSRP / L1-SINR measurements are associated with 20ns and 300ns delay spreads, respectively. In some aspects, the TE can indicate to the UE certain randomization parameters along with the L1-RSRP / L1-SINR measurements. For example, the TE can indicate to the UE whether a particular L1-RSRP / L1-SINR measurement is associated with an indoor / outdoor scenario, a UE's movement speed, and / or a network node's antenna downtilt angle.

[0101] In some respects, the generative model for the test data may be defined at least in part based on an AI / ML model. The AI / ML model input may include at least randomized parameters. The TE may change such AI / ML model input, but changes to the AI / ML model input may be at least partially transparent to the UE. The TE may or may not notify the UE of changes to the AI / ML model input regarding specific L1-RSRP / L1-SINR measurements associated with the test data. The structure, weights, and / or biases associated with the AI / ML model may be defined in a standard. The AI / ML model may be a Generative Adversarial Network (GAN) model and / or another type of advanced generative AI / ML model.

[0102] In some aspects, the L1-RSRP / L1-SINR measurement associated with a first set of resources may include a first portion and a second portion of the L1-RSRP / L1-SINR measurement. In some aspects, both the first and second portions of the L1-RSRP / L1-SINR measurement may be associated with a generative model for the test data defined at least partially based on an analytical or statistical expression. In some aspects, both the first and second portions of the L1-RSRP / L1-SINR measurement may be associated with a generative model for the test data defined at least partially based on an AI / ML model. In some aspects, the first portion of the L1-RSRP / L1-SINR measurement may be associated with a generative model for the test data defined at least partially based on an analytical or statistical expression, and the second portion of the L1-RSRP / L1-SINR measurement may be associated with a generative model for the test data defined at least partially based on an AI / ML model.

[0103] In some aspects, for UE-side beam prediction performance testing, the UE can receive L1-RSRP / L1-SINR measurements generated using different methods. For example, some L1-RSRP / L1-SINR measurements can be generated using a generative model for the test data defined at least in part based on explicit expressions, analytical expressions, and / or statistical expressions (e.g., the first method), while other L1-RSRP / L1-SINR measurements can be generated using a generative model for the test data defined at least in part based on an AI / ML model (e.g., the second method). The mixing ratio of different methods can be defined in the standard (e.g., as...). Figure 7 (As shown).

[0104] In some respects, when L1-RSRP / L1-SINR measurements are generated using a generative model of test data defined at least in part based on explicit expressions, analytical expressions, and / or statistical expressions, the UE can receive measurements based at least in part on the first delay spread. X % L1-RSRP / L1-SINR measurements, and at least in part based on the second delay spread. Y % L1-RSRP / L1-SINR measurement. X and Y The values ​​of L1-RSRP / L1-SINR, as well as the values ​​of the first and second delay spreads, can be defined in the standard or provided to the UE by the TE. However, the UE may not be informed that a particular L1-RSRP / L1-SINR measurement is associated with a particular delay spread value.

[0105] In some respects, when generating L1-RSRP / L1-SINR measurements using a generative model defined for test data that is at least partially based on an AI / ML model, the UE may receive at least partially based on the AI / ML model output associated with the model input, including a first delay spread. X % L1-RSRP / L1-SINR measurements, and at least in part based on the AI / ML model output associated with the model input, including the second delay extension. Y % L1-RSRP / L1-SINR measurement. X and Y The values ​​of L1-RSRP / L1-SINR, as well as the values ​​of the first and second delay spreads, can be defined in the standard or provided to the UE by the TE. However, the UE may not be informed that a particular L1-RSRP / L1-SINR measurement is associated with a particular delay spread value.

[0106] In some aspects, L1-RSRP / L1-SINR measurements can be generated using generative models for test data that are defined at least in part based on explicit expressions, analytical expressions, and / or statistical expressions, and L1-RSRP / L1-SINR measurements can be generated at least in part based on AI / ML models (e.g., considering both the first and second methods together). The UE can receive measurements based at least in part on the first method. X % L1-RSRP / L1-SINR measurement, and at least in part based on the second method Y %L1-RSRP / L1-SINR measurement. X and Y The values ​​and at least some of the parameters used by both methods may be defined in the standard or may be notified to the UE by the TE. However, the UE may be unaware of the specific L1-RSRP / L1-SINR measurement associated with a particular method.

[0107] In some respects, when generating L1-RSRP / L1-SINR measurements using a generative model for test data defined at least in part based on explicit expressions, analytical expressions, and / or statistical expressions, or at least in part based on an AI / ML model, such methods for generating L1-RSRP / L1-SINR measurements can be applied to both a first set of resources and a second set of resources, which can be at least in part based on the same or different sets of methods or randomization parameters for the two sets of resources. Furthermore, the TE may or may not indicate parameters for the second set of resources to the UE.

[0108] As shown by reference numeral 504 in the attached figure, the TE may send to the UE L1-RSRP / L1-SINR measurements associated with a first set of resources. The L1-RSRP / L1-SINR measurements associated with the first set of resources may be derived, at least in part, based on a generative model of test data using randomized parameters. The L1-RSRP / L1-SINR measurements associated with the first set of resources may be transmitted via a cable between the TE and the UE. In some aspects, the TE may send to the UE an indication of the association between the first set of resources and a second set of resources. The indication may indicate the QCL, relative beam pointing direction, relative beamwidth, absolute beam point direction, and / or absolute beamwidth regarding the association between the first set of resources and the second set of resources. In some aspects, the TE may send to the UE an indication of the randomized parameters used by the generative model of test data to generate the L1-RSRP / L1-SINR measurements associated with the first set of resources.

[0109] In some aspects, a generative model for test data can be defined for UE-side beam prediction performance testing. To test beam prediction performance, the UE can receive test data from the TE. The test data may include L1-RSRP / L1-SINR measurements for a first set of resources. The first set of resources may be SSB and / or CSI-RS. The UE can receive from the TE indications of associations between the first set of resources and a second set of resources, which may be based at least in part on QCL, relative beam pointing direction or beamwidth, absolute beam pointing direction or beamwidth, and / or antenna panel identifier (ID). The UE can receive L1-RSRP / L1-SINR measurements and / or indications of associations between the first set of resources and the second set of resources from the TE via a cable connecting the UE and the TE. The L1-RSRP / L1-SINR measurements for the first set of resources may be associated with one or more historical TD timings.

[0110] In some aspects, L1-RSRP / L1-SINR measurements received by the UE from the TE and associated with a first set of resources may be associated with multiple historical TD timings. For example, different randomization parameters associated with UE movement speed / direction and / or UE orientation may vary across different historical TD timings. L1-RSRP / L1-SINR measurements may be generated at least in part based on changes in randomization parameters (e.g., UE movement direction) across TD timings. Figure 8 (As shown). Although the rules for changing such randomization parameters may be defined in the standard, the TE may or may not indicate to the UE the exact values ​​of the randomization parameters associated with different historical TD timings.

[0111] As shown by reference numeral 506 in the attached figure, the TE can use a generative model for the test data to generate recurring L1-RSRP / L1-SINR measurements associated with a second set of resources. The L1-RSRP / L1-SINR measurements associated with a first set of resources and the recurring L1-RSRP / L1-SINR measurements associated with the second set of resources can be associated with the same randomization parameter. In some aspects, the recurring L1-RSRP / L1-SINR measurements associated with the second set of resources can be associated with multiple future TD opportunities, and these multiple future TD opportunities can be associated with the same prediction instance. For example, a first randomization parameter associated with a first TD opportunity among the multiple future TD opportunities can correspond to a second randomization parameter associated with a second TD opportunity among the multiple future TD opportunities.

[0112] In some respects, when considering L1-RSRP / L1-SINR measurements of two different future TD timings associated with the same predicted instance from a second set of resources, the same randomization parameter may be associated with two different future TD timings, or different randomization parameters may be associated with two different future TD timings. As an example, different randomization parameters associated with UE movement speed / direction and / or UE orientation may vary across different future TD timings, regardless of whether the generative model for the test data is defined at least in part based on explicit expressions, analytical expressions, and / or statistical expressions, or at least in part based on AI / ML models.

[0113] As shown by reference numeral 508 in the accompanying figure, the UE may determine the L1-RSRP / L1-SINR measurement associated with a second set of resources based at least in part on the L1-RSRP / L1-SINR measurement associated with a first set of resources. The UE may determine the L1-RSRP / L1-SINR measurement associated with the second set of resources based at least in part on UE-side beam prediction. The UE may perform UE-side beam prediction using an AI / ML model for beam prediction running on the UE. In some aspects, the L1-RSRP / L1-SINR measurements associated with the first set of resources and the L1-RSRP / L1-SINR measurements associated with the second set of resources are associated with the same TD timing, and the first set of resources and the second set of resources may be non-overlapping resources. In some aspects, the L1-RSRP / L1-SINR measurements associated with the second set of resources are associated with future TD timing, and the first set of resources and the second set of resources may be overlapping resources.

[0114] As shown by reference numeral 510 in the attached figure, the UE can send beam prediction feedback associated with the UE-side beam prediction to the TE. The beam prediction feedback can indicate L1-RSRP / L1-SINR measurements associated with a second set of resources. The L1-RSRP / L1-SINR measurements associated with the second set of resources can be sent via cable or via the air interface between the TE and the UE.

[0115] In some aspects, the UE may send beam prediction feedback to the TE. The beam prediction feedback may be associated with beam prediction results. The beam prediction feedback may indicate predicted channel characteristics associated with a second set of resources. The beam prediction feedback may be at least partially based on a first set of resources. The predicted channel characteristics may be associated with SSBs, CSI-RS, and / or virtual resources. The UE may send the beam prediction feedback to the TE via cable or via an air interface. The air interface may be a designated air interface for sending the beam prediction feedback. The predicted channel characteristics may include L1-RSRP / L1-SINR measurements associated with the second set of resources or the top K resources based on L1-RSRP / L1-SINR measurements. When the predicted channel characteristics are about the same TD timing associated with L1-RSRP / L1-SINR measurements received by the UE or about future TD timing, the first set of resources and the second set of resources may be non-overlapping. When the predicted channel characteristics are about future TD timing, the first set of resources and the second set of resources may overlap.

[0116] In some aspects, for time-based UE-side beam prediction performance testing, L1-RSRP / L1-SINR measurements associated with multiple future TD timings for a second set of resources can be reproduced using a generative model based on the test data. The TE can use the generative model based on the test data to reproduce the L1-RSRP / L1-SINR measurements associated with the second set of resources. Additionally, the UE can use UE-side beam prediction to predict the L1-RSRP / L1-SINR measurements associated with the second set of resources. The UE can send beam prediction feedback to the TE indicating the predicted L1-RSRP / L1-SINR measurements.

[0117] As shown by reference numeral 512 in the attached figure, the TE can perform a comparison of reproduced L1-RSRP / L1-SINR measurements associated with a second set of resources and L1-RSRP / L1-SINR measurements associated with the second set of resources, as received from the UE. In other words, the TE can compare reproduced L1-RSRP / L1-SINR measurements associated with a second set of resources (which the UE can assume to be genuine L1-RSRP / L1-SINR measurements) with L1-RSRP / L1-SINR measurements received from the UE.

[0118] As shown by reference numeral 514 in the attached figure, the TE can determine the accuracy of the UE-side beam prediction based at least in part on comparison. When the L1-RSRP / L1-SINR measurement received from the UE is relatively close to the reproduced L1-RSRP / L1-SINR measurement, the TE can determine that the UE-side beam prediction is relatively accurate. When the L1-RSRP / L1-SINR measurement received from the UE differs from the reproduced L1-RSRP / L1-SINR measurement by at least a certain threshold, the TE can determine that the UE-side beam prediction is relatively inaccurate.

[0119] In some aspects, the TE can generate L1-RSRP / L1-SINR measurements for a first set of resources, at least in part, based on a generative model (or multiple models) for the test data. In other words, the TE can generate the test data using one or more generative models. The generative model for the test data, either directly or in whole or in part, specifies parameters that are defined in a standard (e.g., a 3GPP specification). Furthermore, the TE can reproduce L1-RSRP / L1-SINR measurements associated with a second set of resources via the generative model for the test data. The TE can compare the reproduced L1-RSRP / L1-SINR measurements associated with the second set of resources with beam prediction feedback indicating predicted channel characteristics associated with the second set of resources, and based at least in part on this comparison, the TE can evaluate the beam prediction feedback received from the UE.

[0120] As indicated above, Figure 5 This is provided as an example. Other examples are available with reference to [the relevant information]. Figure 5 The examples described are different.

[0121] Figure 6 This is an illustration of Example 600, which is associated with a generative model for generating performance test data for UE-side beam prediction according to this disclosure.

[0122] like Figure 6As shown, the UE can connect to the TE. The UE can connect to the TE via cable and / or air interface. The TE can store a generation model (or multiple generation models for the test data) for the test data. The generation model for the test data can be used to generate L1-RSRP / L1-SINR measurements associated with a first set of resources (e.g., set B beam). Randomization parameters can be used to generate L1-RSRP / L1-SINR measurements associated with the first set of resources. The TE may or may not indicate the randomization parameters to the UE. The generation model for the test data and / or the parameters that at least partially specify the generation model for the test data can be defined in a standard. The generation model for the test data can also be used to generate L1-RSRP / L1-SINR measurements associated with a second set of resources (e.g., set A beam) (e.g., reproducible L1-RSRP / L1-SINR measurements associated with the second set of resources).

[0123] In some aspects, the TE may indicate to the UE via a cable the L1-RSRP / L1-SINR measurements associated with a first set of resources. Using UE-side beam prediction based at least in part on an AI / ML model running on the UE, the UE may determine the beam prediction result based at least in part on the L1-RSRP / L1-SINR measurements associated with the first set of resources. The beam prediction result may include predicted L1-RSRP / L1-SINR measurements for a second set of resources or the first K resources based on L1-RSRP / L1-SINR measurements. The UE may indicate the beam prediction result to the TE via a cable or air interface. The TE may compare the beam prediction result (e.g., the L1-RSRP / L1-SINR measurements associated with the second set of resources) received from the UE with the reproduced L1-RSRP / L1-SINR measurements associated with the second set of resources. The TE may determine the accuracy of the UE-side beam prediction based at least in part on the comparison.

[0124] As indicated above, Figure 6 This is provided as an example. Other examples are available with reference to [the relevant information]. Figure 6 The examples described are different.

[0125] Figure 7 This is an illustration of Example 700, which is associated with a generative model for generating performance test data for UE-side beam prediction according to this disclosure.

[0126] like Figure 7As shown, the TE can mix L1-RSRP / L1-SINR measurements generated using different methods. The TE can mix the L1-RSRP / L1-SINR measurements before sending them to the UE. The TE can mix the L1-RSRP / L1-SINR measurements according to a certain ratio, which can be defined in the specification. For example, approximately 70% of the L1-RSRP / L1-SINR measurements can be at least partially based on a 30ns delay spread, and approximately 30% of the L1-RSRP / L1-SINR measurements can be at least partially based on a 100ns delay spread.

[0127] As indicated above, Figure 7 This is provided as an example. Other examples are available with reference to [the relevant information]. Figure 7 The examples described are different.

[0128] Figure 8 This is an illustration of Example 800, which is associated with a generative model for generating performance test data for UE-side beam prediction according to this disclosure.

[0129] like Figure 8 As shown, L1-RSRP / L1-SINR measurements associated with a first set of resources can be generated, at least in part, based on changes in randomization parameters across TD timings. For example, the randomization parameters can be changed, at least in part, based on the UE's direction of movement. The first set of L1-RSRP / L1-SINR measurements associated with the first set of TD timings may be for when the UE is moving north, the second set of L1-RSRP / L1-SINR measurements associated with the second set of TD timings may be for when the UE is moving east, and the third set of L1-RSRP / L1-SINR measurements associated with the third set of TD timings may be for when the UE is moving south.

[0130] As indicated above, Figure 8 This is provided as an example. Other examples are available with reference to [the relevant information]. Figure 8 The examples described are different.

[0131] Figure 9 This is a diagram illustrating an example process 900 performed, for example, at a TE or a device of a TE, according to this disclosure. Example process 900 is an example in which a device or TE (e.g., TE 122) performs operations associated with generating a generative model for generating performance test data for UE-side beam prediction.

[0132] like Figure 9As shown, in some aspects, process 900 may include sending L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are at least partially based on a generative model for the test data using randomization parameters (box 910). For example, TE (e.g., using...) Figure 11 The communication manager 150 and / or the transmitting component 1104 depicted herein may transmit L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are based at least in part on a generative model for the test data using randomized parameters, as described above.

[0133] like Figure 9 Further shown, in some aspects, process 900 may include receiving beam prediction feedback associated with UE-side beam prediction based at least in part on L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the beam prediction feedback indicates L1-RSRP / L1-SINR measurements associated with a second set of resources (box 920). For example, TE (e.g., using...) Figure 11 The communication manager 150 and / or receiving component 1102 depicted herein may receive beam prediction feedback associated with UE-side beam prediction based at least in part on L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the beam prediction feedback indicates L1-RSRP / L1-SINR measurements associated with a second set of resources, as described above.

[0134] Process 900 may include additional aspects, such as any single aspect or any combination of aspects described below and / or in conjunction with one or more other processes described elsewhere herein.

[0135] In the first aspect, process 900 includes generating L1-RSRP / L1-SINR measurements associated with a first set of resources, based at least in part on a generative model for test data and at least in part on randomization parameters.

[0136] In the second aspect, either alone or in combination with the first aspect, the generative model for the test data or the parameters associated with the generative model for the test data are defined at least in part in the 3GPP specifications.

[0137] In a third aspect, either alone or in combination with one or more of the first and second aspects, process 900 includes: generating, at least in part, reproducible L1-RSRP / L1-SINR measurements associated with a second set of resources based on a generative model for test data; and determining the accuracy of UE-side beam prediction based at least in part on a comparison of the reproducible L1-RSRP / L1-SINR measurements associated with the second set of resources and the L1-RSRP / L1-SINR measurements associated with the second set of resources.

[0138] In a fourth aspect, either alone or in combination with one or more of the first to third aspects, process 900 includes sending an indication of the association between a first set of resources and a second set of resources, wherein the indication indicates one or more of QCL, relative beam pointing direction, relative beamwidth, absolute beam point direction, or absolute beamwidth.

[0139] In the fifth aspect, either alone or in combination with one or more of the first to fourth aspects, the L1-RSRP / L1-SINR measurement associated with the first set of resources is transmitted via a cable between the TE and the UE, and the L1-RSRP / L1-SINR measurement associated with the second set of resources is received via a cable or via an air interface between the TE and the UE.

[0140] In the sixth aspect, either alone or in combination with one or more of the first to fifth aspects, at least in part, based on L1-RSRP / L1-SINR measurements associated with the first set of resources and L1-RSRP / L1-SINR measurements associated with the second set of resources, which are associated with the same time-domain timing and are non-overlapping.

[0141] In the seventh aspect, either alone or in combination with one or more of the first to sixth aspects, at least in part, the first set of resources and the second set of resources are associated with future time-domain timing based on L1-RSRP / L1-SINR measurements related to the second set of resources, which overlap.

[0142] In the eighth aspect, either alone or in combination with one or more of the first to seventh aspects, the generative model for the test data is defined at least in part based on an analytical or statistical expression and utilizes randomization parameters that can be changed by the TE.

[0143] In the ninth aspect, the randomization parameter is associated, either alone or in combination with one or more of the first to eighth aspects, with one of the following: network node antenna configuration, delay spread, indoor environment, outdoor environment, urban environment, rural environment, cell type, Doppler drift, or UE speed.

[0144] In the tenth aspect, either alone or in combination with one or more of the first to ninth aspects, process 900 includes sending an indication of randomization parameters used by a generative model for test data to generate L1-RSRP / L1-SINR measurements associated with a first set of resources.

[0145] In the eleventh aspect, either alone or in combination with one or more of the first to tenth aspects, the generative model for the test data is defined at least in part based on an AI / ML model, the AI / ML model input including randomization parameters, and the AI / ML model input being modifiable by TE.

[0146] In the twelfth aspect, alone or in combination with one or more of the first to eleventh aspects, the L1-RSRP / L1-SINR measurement associated with the first set of resources includes a first portion of the L1-RSRP / L1-SINR measurement and a second portion of the L1-RSRP / L1-SINR measurement.

[0147] In the thirteenth aspect, either alone or in combination with one or more of the first to twelfth aspects, the first portion of the L1-RSRP / L1-SINR measurement and the second portion of the L1-RSRP / L1-SINR measurement are associated with a generative model for the test data that is defined at least in part based on an analytical expression or a statistical expression.

[0148] In the fourteenth aspect, either alone or in combination with one or more of the first to thirteenth aspects, the first portion of the L1-RSRP / L1-SINR measurement and the second portion of the L1-RSRP / L1-SINR measurement are associated with a generative model for the test data that is defined at least in part based on an AI / ML model.

[0149] In the fifteenth aspect, either alone or in combination with one or more of the first to fourteenth aspects, a first portion of the L1-RSRP / L1-SINR measurement is associated with a generative model for the test data that is defined at least in part based on an analytical expression or a statistical expression, and a second portion of the L1-RSRP / L1-SINR measurement is associated with a generative model for the test data that is defined at least in part based on an AI / ML model.

[0150] In the sixteenth aspect, alone or in combination with one or more of the first to fifteenth aspects, the L1-RSRP / L1-SINR measurement associated with the first set of resources and the recurring L1-RSRP / L1-SINR measurement associated with the second set of resources are associated with randomization parameters.

[0151] In the seventeenth aspect, either alone or in combination with one or more of the first to sixteenth aspects, the L1-RSRP / L1-SINR measurements associated with the second set of resources are reproduced as being associated with multiple future time-domain opportunities, and the multiple future time-domain opportunities are associated with the same prediction instance.

[0152] In the eighteenth aspect, either alone or in combination with one or more of the first to seventeenth aspects, the first randomization parameter associated with a first time-domain timing among a plurality of future time-domain timings corresponds to a second randomization parameter associated with a second time-domain timing among a plurality of future time-domain timings.

[0153] In the nineteenth aspect, either alone or in combination with one or more of the first to eighteenth aspects, the L1-RSRP / L1-SINR measurement associated with the first set of resources is associated with one or more historical time-domain moments, and the L1-RSRP / L1-SINR measurement associated with the first set of resources is based at least in part on changes in the randomization parameter across one or more historical time-domain moments.

[0154] although Figure 9 An example box of process 900 is shown, but in some respects, process 900 may include... Figure 9 The boxes depicted in the diagram may be compared to additional boxes, fewer boxes, different boxes, or boxes arranged in a different manner. Alternatively, two or more boxes in the process 900 may be executed in parallel.

[0155] Figure 10 This is a diagram illustrating an example process 1000 performed, for example, at a UE or a device of a UE, according to this disclosure. Example process 1000 is an example in which a device or UE (e.g., UE 120) performs operations associated with generating a generative model for generating performance test data for UE-side beam prediction.

[0156] like Figure 10 As shown, in some aspects, process 1000 may include receiving L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are at least partially based on a generative model for test data using randomization parameters (box 1010). For example, the UE (e.g., using...) Figure 12 The communication manager 140 and / or receiving component 1102 depicted herein may receive L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are based at least in part on a generative model for the test data using randomized parameters, as described above.

[0157] like Figure 10 Further shown, in some aspects, process 1000 may include transmitting beam prediction feedback (box 1020) indicating L1-RSRP / L1-SINR measurements associated with a second set of resources, based at least in part on L1-RSRP / L1-SINR measurements associated with a first set of resources. For example, the UE (e.g., using...) Figure 12 The communication manager 140 and / or transmission component 1104 depicted herein may transmit beam prediction feedback indicating L1-RSRP / L1-SINR measurements associated with a second set of resources, as described above, based at least in part on L1-RSRP / L1-SINR measurements associated with a first set of resources.

[0158] Process 1000 may include additional aspects, such as any single aspect or any combination of aspects described below and / or in conjunction with one or more other process descriptions elsewhere herein.

[0159] In the first aspect, the generative model for the test data, or the parameters associated with the generative model for the test data, are defined at least in part in the 3GPP specifications.

[0160] In a second aspect, either alone or in combination with the first aspect, process 1000 includes receiving an indication of an association between a first set of resources and a second set of resources, wherein the indication indicates one or more of QCL, relative beam pointing direction, relative beamwidth, absolute beam point direction, or absolute beamwidth.

[0161] In the third aspect, either alone or in combination with one or more of the first and second aspects, L1-RSRP / L1-SINR measurements associated with the first set of resources are received via a cable between the UE and the TE, and L1-RSRP / L1-SINR measurements associated with the second set of resources are transmitted via a cable or via an air interface between the UE and the TE.

[0162] In the fourth aspect, either alone or in combination with one or more of the first to third aspects, at least in part, based on L1-RSRP / L1-SINR measurements associated with the first set of resources and L1-RSRP / L1-SINR measurements associated with the second set of resources, which are associated with the same time-domain timing and are non-overlapping.

[0163] In the fifth aspect, either alone or in combination with one or more of the first to fourth aspects, at least in part, the first set of resources and the second set of resources are associated with future time-domain timing based on L1-RSRP / L1-SINR measurements related to the second set of resources, which overlap.

[0164] In the sixth aspect, either alone or in combination with one or more of the first to fifth aspects, the generative model for the test data is defined at least in part based on an analytical or statistical expression and utilizes variable randomization parameters.

[0165] In the seventh aspect, either alone or in combination with one or more of the first to sixth aspects, the randomization parameter is associated with one of the following: network node antenna configuration, delay spread, indoor environment, outdoor environment, urban environment, rural environment, cell type, Doppler drift, or UE speed.

[0166] In the eighth aspect, either alone or in combination with one or more of the first to seventh aspects, process 1000 includes receiving an indication of randomization parameters used by a generative model for test data to generate L1-RSRP / L1-SINR measurements associated with a first set of resources.

[0167] In the ninth aspect, either alone or in combination with one or more of the first to eighth aspects, the generative model for the test data is defined at least in part based on an AI / ML model whose inputs include randomization parameters and are variable.

[0168] In the tenth aspect, alone or in combination with one or more of the first to ninth aspects, the L1-RSRP / L1-SINR measurement associated with the first set of resources includes a first portion of the L1-RSRP / L1-SINR measurement and a second portion of the L1-RSRP / L1-SINR measurement.

[0169] In the eleventh aspect, either alone or in combination with one or more of the first to tenth aspects, the first portion of the L1-RSRP / L1-SINR measurement and the second portion of the L1-RSRP / L1-SINR measurement are associated with a generative model for the test data that is defined at least in part based on an analytical expression or a statistical expression.

[0170] In the twelfth aspect, either alone or in combination with one or more of the first to eleventh aspects, the first portion of the L1-RSRP / L1-SINR measurement and the second portion of the L1-RSRP / L1-SINR measurement are associated with a generative model for the test data that is defined at least in part based on an AI / ML model.

[0171] In the thirteenth aspect, either alone or in combination with one or more of the first to twelfth aspects, the first portion of the L1-RSRP / L1-SINR measurement is associated with a generative model for the test data that is defined at least in part based on an analytical expression or a statistical expression, and the second portion of the L1-RSRP / L1-SINR measurement is associated with a generative model for the test data that is defined at least in part based on an AI / ML model.

[0172] In the fourteenth aspect, alone or in combination with one or more of the first to thirteenth aspects, the L1-RSRP / L1-SINR measurement associated with the first set of resources and the recurring L1-RSRP / L1-SINR measurement associated with the second set of resources are associated with randomization parameters.

[0173] In the fifteenth aspect, either alone or in combination with one or more of the first to fourteenth aspects, the L1-RSRP / L1-SINR measurements associated with the second set of resources are reproduced as being associated with multiple future time-domain opportunities, and the multiple future time-domain opportunities are associated with the same prediction instance.

[0174] In the sixteenth aspect, either alone or in combination with one or more of the first to fifteenth aspects, the first randomization parameter associated with a first time-domain timing among a plurality of future time-domain timings corresponds to a second randomization parameter associated with a second time-domain timing among a plurality of future time-domain timings.

[0175] In the seventeenth aspect, either alone or in combination with one or more of the first to sixteenth aspects, the L1-RSRP / L1-SINR measurement associated with the first set of resources is associated with one or more historical time-domain moments, and the L1-RSRP / L1-SINR measurement associated with the first set of resources is based at least in part on changes in the randomization parameter across one or more historical time-domain moments.

[0176] although Figure 10 An example box of process 1000 is shown, but in some aspects, process 1000 may include... Figure 10 The boxes depicted in the diagram may be compared to additional boxes, fewer boxes, different boxes, or boxes arranged in a different manner. Alternatively, two or more boxes in the process 1000 may be executed in parallel.

[0177] Figure 11This is a diagram of an example device 1100 for wireless communication according to the present disclosure. Device 1100 may be a TE, or a TE may include device 1100. In some aspects, device 1100 includes a receiving component 1102 and a transmitting component 1104, which can communicate with each other (e.g., via one or more buses and / or one or more other components). As shown, device 1100 may use the receiving component 1102 and the transmitting component 1104 to communicate with another device 1106 (such as a UE, a base station, or another wireless communication device). As further shown, device 1100 may include a communication manager 140. Communication manager 140 may include one or more of a generating component 1108 or a determining component 1110, etc.

[0178] In some respects, device 1100 can be configured to perform the functions described herein. Figures 5 to 8 The one or more operations described herein. Additionally or alternatively, the device 1100 may be configured to perform one or more processes described herein, such as Figure 9 The process is 900. In some respects, Figure 11 The illustrated device 1100 and / or one or more components may include a combination Figure 2 One or more components of the described TE. Additionally or alternatively, Figure 11 One or more components shown can be combined Figure 2 Implementation within one or more of the described components. Alternatively or concurrently, one or more components in the set of components may be implemented at least partially as software stored in one or more memories. For example, a component (or a portion thereof) may be implemented as instructions or code stored in a non-transitory computer-readable medium and executable by one or more controllers or one or more processors to perform the function or operation of the component.

[0179] Receiver 1102 may receive communications from device 1106, such as reference signals, control information, data communications, or combinations thereof. Receiver 1102 may provide the received communications to one or more other components of device 1100. In some aspects, receiver 1102 may perform signal processing on the received communications (such as filtering, amplification, demodulation, analog-to-digital conversion, demultiplexing, deinterleaving, demapping, equalization, interference cancellation, or decoding, etc.), and may provide the processed signal to one or more other components of device 1100. In some aspects, receiver 1102 may include combinations of... Figure 2 The described TE includes one or more antennas, one or more modems, one or more demodulators, one or more MIMO detectors, one or more receiver processors, one or more controllers / processors, one or more memories, or combinations thereof.

[0180] Transmitting component 1104 may transmit communications, such as reference signals, control information, data communications, or combinations thereof, to device 1106. In some aspects, one or more other components of device 1100 may generate communications and provide the generated communications to transmitting component 1104 for transmission to device 1106. In some aspects, transmitting component 1104 may perform signal processing (such as filtering, amplification, modulation, digital-to-analog conversion, multiplexing, interleaving, mapping, or encoding, etc.) on the generated communications and may transmit the processed signals to device 1106. In some aspects, transmitting component 1104 may include combinations of... Figure 2 The described TE includes one or more antennas, one or more modems, one or more modulators, one or more transmit MIMO processors, one or more transmit processors, one or more controllers / processors, one or more memories, or combinations thereof. In some aspects, the transmit component 1104 may co-located with the receive component 1102 in one or more transceivers.

[0181] Transmitting component 1104 can transmit L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are based at least in part on a generative model for test data using randomized parameters. Receiving component 1102 can receive beam prediction feedback associated with UE-side beam prediction based at least in part on the L1-RSRP / L1-SINR measurements associated with the first set of resources, wherein the beam prediction feedback indicates L1-RSRP / L1-SINR measurements associated with a second set of resources.

[0182] Generation component 1108 may generate L1-RSRP / L1-SINR measurements associated with a first set of resources, based at least in part on a generation model for test data and at least in part on randomization parameters. Generation component 1108 may also generate reproduced L1-RSRP / L1-SINR measurements associated with a second set of resources, based at least in part on a generation model for test data. Determination component 1110 may determine the accuracy of UE-side beam prediction based at least in part on a comparison between reproduced L1-RSRP / L1-SINR measurements associated with the second set of resources and L1-RSRP / L1-SINR measurements associated with the second set of resources.

[0183] Transmitting component 1104 can transmit an indication of the association between a first set of resources and a second set of resources, wherein the indication indicates one or more of QCL, relative beam pointing direction, relative beamwidth, absolute beam point direction, or absolute beamwidth. Transmitting component 1104 can also transmit an indication of randomization parameters used by a generative model based on test data to generate L1-RSRP / L1-SINR measurements associated with the first set of resources.

[0184] Figure 11 The number and arrangement of components shown are provided as an example. In reality, they can exist in combination with... Figure 11 The components shown are compared to additional components, fewer components, different components, or components arranged in a different manner. Furthermore, Figure 11 The two or more components shown can be implemented within a single component, or Figure 11 The single component shown can be implemented as multiple distributed components. Alternatively, Figure 11 The set (one or more) components shown are executable and described as being composed of Figure 11 The other set of components shown in the diagram performs one or more functions.

[0185] Figure 12 This is a diagram illustrating an example 1200 of a hardware implementation of an apparatus 1205 employing a processing system 1210 according to the present disclosure. Apparatus 1205 may be a TE.

[0186] Processing system 1210 may be implemented using a bus architecture generally represented by bus 1215. Bus 1215 may include any number of interconnect buses and bridges, depending on the specific application of processing system 1210 and overall design constraints. Bus 1215 links together various circuits including one or more processors and / or hardware components (represented by processor (or processing circuitry) 1220, illustrated components, and computer-readable medium / memory (or memory circuitry) 1225). Processor 1220 may include multiple processors, such as processor 1220a, memory 1220b, and memory 1220c. Memory 1225 may include multiple memories, such as memory 1225a, memory 1225b, and memory 1225c. Bus 1215 may also link various other circuits, such as timing sources, peripherals, voltage regulators, and / or power management circuitry.

[0187] Processing system 1210 may be coupled to transceiver 1230. Transceiver 1230 is coupled to one or more antennas 1235. Transceiver 1230 provides components for communicating with various other devices via a transmission medium. Transceiver 1230 receives signals from one or more antennas 1235, extracts information from the received signals, and provides the extracted information to processing system 1210 (specifically, receiving component 1102). Furthermore, transceiver 1230 receives information from processing system 1210 (specifically, transmitting component 1104) and generates signals to be applied to one or more antennas 1235, at least in part, based on the received information.

[0188] Processing system 1210 includes a processor 1220 coupled to a computer-readable medium / memory 1225. Processor 1220 is responsible for general processing, including executing software stored on the computer-readable medium / memory 1225. When executed by processor 1220, the software causes processing system 1210 to perform the various functions described herein with respect to any particular device. Computer-readable medium / memory 1225 can also be used to store data manipulated by processor 1220 during software execution. The processing system also includes at least one of the illustrated components. A component may be: a software module running in processor 1220, residing in / stored in computer-readable medium / memory 1225, one or more hardware modules coupled to processor 1220, or some combination thereof.

[0189] In some aspects, processing system 1210 may be a component of TE 122 and may include memory 282, and / or at least one of TXMIMO processor 266, Rx processor 258, and / or controller / processor 280. In some aspects, apparatus 1205 for wireless communication includes: components for transmitting L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are at least partially based on a generative model for test data using randomized parameters; and / or components for receiving beam prediction feedback associated with UE-side beam prediction based at least partially on the L1-RSRP / L1-SINR measurements associated with the first set of resources, wherein the beam prediction feedback indicates L1-RSRP / L1-SINR measurements associated with a second set of resources. The aforementioned components may be one or more of the aforementioned components of apparatus 1100 and / or processing system 1210 of apparatus 1205 configured to perform the functions stated by the aforementioned components. As described elsewhere herein, the processing system 1210 may include a TX MIMO processor 266, an Rx processor 258, and / or a controller / processor 280. In one configuration, the aforementioned components may be the TX MIMO processor 266, the Rx processor 258, and / or the controller / processor 280 configured to perform the functions and / or operations described herein.

[0190] Figure 12 This is provided as an example. Other examples can be combined with it. Figure 12 The examples described are different.

[0191] Figure 13 This is a diagram illustrating an example 1300 of a specific implementation of code and circuitry for device 1305 according to the present disclosure. The circuitry may include processing circuitry and memory circuitry. Device 1305 may be a TE, or a TE may include device 1305.

[0192] like Figure 13 As shown, apparatus 1305 may include circuitry for transmitting L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are at least partially based on a generative model for the test data using randomized parameters (circuit 1320). For example, circuit 1320 may enable apparatus 1305 to transmit L1-RSRP / L1-SINR measurements associated with the first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are at least partially based on a generative model for the test data using randomized parameters.

[0193] like Figure 13As shown, apparatus 1305 may include code stored in computer-readable medium 1225 for transmitting L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are based at least in part on a generative model for test data using randomized parameters (code 1325). For example, when executed by processor 1220, code 1325 may cause processor 1220 to cause transceiver 1230 to transmit L1-RSRP / L1-SINR measurements associated with the first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are based at least in part on a generative model for test data using randomized parameters.

[0194] like Figure 13 As shown, apparatus 1305 may include circuitry for receiving beam prediction feedback associated with UE-side beam prediction based at least in part on L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the beam prediction feedback indicates L1-RSRP / L1-SINR measurements associated with a second set of resources (circuit 1330). For example, circuit 1330 may enable apparatus 1305 to receive beam prediction feedback associated with UE-side beam prediction based at least in part on L1-RSRP / L1-SINR measurements associated with the first set of resources, wherein the beam prediction feedback indicates L1-RSRP / L1-SINR measurements associated with the second set of resources.

[0195] like Figure 13 As shown, apparatus 1305 may include code stored in computer-readable medium 1225 for receiving beam prediction feedback associated with UE-side beam prediction based at least in part on L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the beam prediction feedback indicates L1-RSRP / L1-SINR measurements associated with a second set of resources (code 1335). For example, when executed by processor 1220, code 1335 may cause processor 1220 to cause transceiver 1230 to receive beam prediction feedback associated with UE-side beam prediction based at least in part on L1-RSRP / L1-SINR measurements associated with the first set of resources, wherein the beam prediction feedback indicates L1-RSRP / L1-SINR measurements associated with the second set of resources.

[0196] Figure 13 This is provided as an example. Other examples can be combined with it. Figure 13 The examples described are different.

[0197] Figure 14This is a diagram of an example device 1400 for wireless communication according to the present disclosure. Device 1400 may be a UE, or a UE may include device 1400. In some aspects, device 1400 includes a receiving component 1402 and a transmitting component 1404, which can communicate with each other (e.g., via one or more buses and / or one or more other components). As shown, device 1400 can use the receiving component 1402 and the transmitting component 1404 to communicate with another device 1406 (such as a UE, a base station, or another wireless communication device). As further shown, device 1400 may include a communication manager 140.

[0198] In some respects, device 1400 can be configured to perform the functions described herein. Figures 5 to 8 One or more operations described herein. Additionally or alternatively, the device 1400 may be configured to perform one or more processes described herein, such as Figure 10 The process is 1000. In some respects, Figure 14 The illustrated device 1400 and / or one or more components may include a combination Figure 2 One or more components of the described UE. Additionally or alternatively, Figure 14 One or more components shown can be combined Figure 2 Implementation within one or more of the described components. Alternatively or concurrently, one or more components in the set of components may be implemented at least partially as software stored in one or more memories. For example, a component (or a portion thereof) may be implemented as instructions or code stored in a non-transitory computer-readable medium and executable by one or more controllers or one or more processors to perform the function or operation of the component.

[0199] Receiver 1402 may receive communications from device 1406, such as reference signals, control information, data communications, or combinations thereof. Receiver 1402 may provide the received communications to one or more other components of device 1400. In some aspects, receiver 1402 may perform signal processing on the received communications (such as filtering, amplification, demodulation, analog-to-digital conversion, demultiplexing, deinterleaving, demapping, equalization, interference cancellation, or decoding, etc.) and may provide the processed signals to one or more other components of device 1400. In some aspects, receiver 1402 may include combinations of... Figure 2 The described UE includes one or more antennas, one or more modems, one or more demodulators, one or more MIMO detectors, one or more receiver processors, one or more controllers / processors, one or more memories, or combinations thereof.

[0200] Transmitting component 1404 may transmit communications, such as reference signals, control information, data communications, or combinations thereof, to device 1406. In some aspects, one or more other components of device 1400 may generate communications and provide the generated communications to transmitting component 1404 for transmission to device 1406. In some aspects, transmitting component 1404 may perform signal processing (such as filtering, amplification, modulation, digital-to-analog conversion, multiplexing, interleaving, mapping, or encoding, etc.) on the generated communications and may transmit the processed signals to device 1406. In some aspects, transmitting component 1404 may include combinations of... Figure 2 The described UE may include one or more antennas, one or more modems, one or more modulators, one or more transmit MIMO processors, one or more transmit processors, one or more controllers / processors, one or more memories, or combinations thereof. In some aspects, the transmit component 1404 may co-located with the receive component 1402 in one or more transceivers.

[0201] The receiving component 1402 can receive L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are based at least in part on a generative model for test data using randomized parameters. The transmitting component 1404 can transmit beam prediction feedback indicating L1-RSRP / L1-SINR measurements associated with a second set of resources, based at least in part on the L1-RSRP / L1-SINR measurements associated with the first set of resources.

[0202] The receiving component 1402 may receive an indication of the association between a first set of resources and a second set of resources, wherein the indication indicates one or more of QCL, relative beam pointing direction, relative beamwidth, absolute beam point direction, or absolute beamwidth. The receiving component 1402 may also receive an indication of randomization parameters used by a generative model based on test data to generate L1-RSRP / L1-SINR measurements associated with the first set of resources.

[0203] Figure 14 The number and arrangement of components shown are provided as an example. In reality, they can exist in combination with... Figure 14 The components shown are compared to additional components, fewer components, different components, or components arranged in a different manner. Furthermore, Figure 14 The two or more components shown can be implemented within a single component, or Figure 14 The single component shown can be implemented as multiple distributed components. Alternatively, Figure 14 The set (one or more) components shown are executable and described as being composed of Figure 14The other set of components shown in the diagram performs one or more functions.

[0204] Figure 15 This is a diagram illustrating an example 1500 of a hardware implementation of an apparatus 1505 employing a processing system 1510 according to the present disclosure. The apparatus 1505 may be a UE (User Equipment).

[0205] Processing system 1510 may be implemented using a bus architecture generally represented by bus 1515. Bus 1515 may include any number of interconnect buses and bridges, depending on the specific application of processing system 1510 and overall design constraints. Bus 1515 links together various circuits including one or more processors and / or hardware components (represented by processor (or processing circuitry) 1520, illustrated components, and computer-readable medium / memory (or memory circuitry) 1525). Processor 1520 may include multiple processors, such as processor 1520a, memory 1520b, and memory 1520c. Memory 1525 may include multiple memories, such as memory 1525a, memory 1525b, and memory 1525c. Bus 1515 may also link various other circuits, such as timing sources, peripherals, voltage regulators, and / or power management circuitry.

[0206] Processing system 1510 may be coupled to transceiver 1530. Transceiver 1530 is coupled to one or more antennas 1535. Transceiver 1530 provides components for communicating with various other devices via a transmission medium. Transceiver 1530 receives signals from one or more antennas 1535, extracts information from the received signals, and provides the extracted information to processing system 1510 (specifically, receiving component 1402). Furthermore, transceiver 1530 receives information from processing system 1510 (specifically, transmitting component 1404) and generates signals to be applied to one or more antennas 1535, at least in part, based on the received information.

[0207] Processing system 1510 includes a processor 1520 coupled to a computer-readable medium / memory 1525. Processor 1520 is responsible for general processing, including executing software stored on the computer-readable medium / memory 1525. When executed by processor 1520, the software causes processing system 1510 to perform the various functions described herein with respect to any particular device. Computer-readable medium / memory 1525 can also be used to store data manipulated by processor 1520 during software execution. The processing system also includes at least one of the illustrated components. A component may be: a software module running in processor 1520, residing in / stored in computer-readable medium / memory 1525, one or more hardware modules coupled to processor 1520, or some combination thereof.

[0208] In some aspects, processing system 1510 may be a component of UE 120 and may include memory 282, and / or at least one of TXMIMO processor 266, Rx processor 258, and / or controller / processor 280. In some aspects, apparatus 1505 for wireless communication includes: components for receiving L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are at least partially based on a generative model for test data using randomized parameters; and / or components for transmitting beam prediction feedback indicating L1-RSRP / L1-SINR measurements associated with a second set of resources, based at least partially on the L1-RSRP / L1-SINR measurements associated with the first set of resources. The aforementioned components may be one or more of the aforementioned components of apparatus 1400 and / or processing system 1510 of apparatus 1505, configured to perform the functions stated by the aforementioned components. As described elsewhere herein, the processing system 1510 may include a TX MIMO processor 266, an Rx processor 258, and / or a controller / processor 280. In one configuration, the aforementioned components may be the TX MIMO processor 266, the Rx processor 258, and / or the controller / processor 280 configured to perform the functions and / or operations described herein.

[0209] Figure 15 This is provided as an example. Other examples can be combined with it. Figure 15 The examples described are different.

[0210] Figure 16 This is an illustration of an example 1600 of a specific implementation of code and circuitry for device 1605 according to the present disclosure. The circuitry may include processing circuitry and memory circuitry. Device 1605 may be a UE, or a UE may include device 1605.

[0211] like Figure 16 As shown, device 1605 may include circuitry for receiving L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are at least partially based on a generative model for the test data using randomized parameters (circuit 1620). For example, circuit 1620 may enable device 1605 to receive L1-RSRP / L1-SINR measurements associated with the first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are at least partially based on a generative model for the test data using randomized parameters.

[0212] like Figure 16As shown, apparatus 1605 may include code stored in computer-readable medium 1525 for receiving L1-RSRP / L1-SINR measurements associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are at least partially based on a generative model for test data using randomized parameters (code 1625). For example, when executed by processor 1520, code 1625 may cause processor 1520 to cause transceiver 1530 to receive L1-RSRP / L1-SINR measurements associated with the first set of resources, wherein the L1-RSRP / L1-SINR measurements associated with the first set of resources are at least partially based on a generative model for test data using randomized parameters.

[0213] like Figure 16 As shown, apparatus 1605 may include circuitry (circuit 1630) for transmitting beam prediction feedback indicating L1-RSRP / L1-SINR measurements associated with a second set of resources, based at least in part on L1-RSRP / L1-SINR measurements associated with a first set of resources. For example, circuitry 1630 may enable apparatus 1605 to transmit beam prediction feedback indicating L1-RSRP / L1-SINR measurements associated with a second set of resources, based at least in part on L1-RSRP / L1-SINR measurements associated with the first set of resources.

[0214] like Figure 16 As shown, apparatus 1605 may include code (code 1635) stored in computer-readable medium 1525 for transmitting beam prediction feedback indicating L1-RSRP / L1-SINR measurements associated with a second set of resources, based at least in part on L1-RSRP / L1-SINR measurements associated with a first set of resources. For example, when executed by processor 1520, code 1635 may cause processor 1520 to cause transceiver 1530 to transmit beam prediction feedback indicating L1-RSRP / L1-SINR measurements associated with a second set of resources, based at least in part on L1-RSRP / L1-SINR measurements associated with the first set of resources.

[0215] Figure 16 This is provided as an example. Other examples can be combined with it. Figure 16 The examples described are different.

[0216] Figure 17A and Figure 17B This is an illustration of Example 1700 of an ML model for beam prediction according to this disclosure.

[0217] like Figure 17AAs shown, the ML model for beam prediction can be run at the network node. The UE can feed back CSI with beam reporting. The UE can feed back a sounding reference signal (SRS). The network node can run the ML model for beam prediction based at least in part on the feedback received from the UE. The network node can use the ML model for beam prediction to determine the beam prediction result. The network node can perform scheduling decisions for the UE based at least in part on the beam prediction result. The ML model for beam prediction can be run at the network node when the UE's power and / or computing power are limited.

[0218] like Figure 17B As shown, the ML model for beam prediction can be run at the UE. The ML model for beam prediction can be configured by the network node. The UE can run the ML model for beam prediction based at least in part on local measurements and signaling from the network node. The UE can report beam prediction results to the network node based at least in part on configuration or triggering conditions. The UE can run the ML model for beam prediction because the UE typically has more measurements than the network node, and running the ML model for beam prediction at the UE involves less overhead for reporting. However, running the ML model for beam prediction at the UE may involve higher computational power at the UE.

[0219] As indicated above, 17A and 17B are provided as examples. Other examples are available in conjunction with [the relevant documentation / information]. Figure 17A and Figure 17B The examples described are different.

[0220] The following provides an overview of some aspects of this disclosure:

[0221] Aspect 1: A method of wireless communication performed at a test equipment (TE), the method comprising: transmitting a Layer 1 (L1) reference signal received power (RSRP) or L1 signal-to-interference-plus-noise ratio (SINR) (L1-RSRP / L1-SINR) measurement associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurement associated with the first set of resources is at least partially based on a generative model for test data using randomized parameters; and receiving beam prediction feedback associated with user equipment (UE) side beam prediction based at least partially on the L1-RSRP / L1-SINR measurement associated with the first set of resources, wherein the beam prediction feedback indicates an L1-RSRP / L1-SINR measurement associated with a second set of resources.

[0222] Aspect 2: According to the method of aspect 1, the method further includes: generating the L1-RSRP / L1-SINR measurement associated with the first set of resources, based at least in part on the generative model for the test data and at least in part on the randomization parameters.

[0223] Aspect 3: The method according to any one of Aspects 1 to 2, wherein the generative model for the test data or the parameters associated with the generative model for the test data are defined at least in part in the 3rd Generation Partnership Project (3GPP) specification.

[0224] Aspect 4: The method according to any one of Aspects 1 to 3, the method further comprising: generating a reproduced L1-RSRP / L1-SINR measurement associated with the second set of resources based at least in part on the generative model for test data; and determining the accuracy of the UE-side beam prediction based at least in part on a comparison between the reproduced L1-RSRP / L1-SINR measurement associated with the second set of resources and the L1-RSRP / L1-SINR measurement associated with the second set of resources.

[0225] Aspect 5: The method according to any one of Aspects 1 to 4, the method further comprising: sending an indication of an association between the first set of resources and the second set of resources, wherein the indication indicates one or more of alignment colocation (QCL), relative beam pointing direction, relative beamwidth, absolute beam point direction, or absolute beamwidth.

[0226] Aspect 6: The method according to any one of Aspects 1 to 5, wherein: the L1-RSRP / L1-SINR measurement associated with the first set of resources is transmitted via a cable between the TE and the UE; and the L1-RSRP / L1-SINR measurement associated with the second set of resources is received via the cable or via an air interface between the TE and the UE.

[0227] Aspect 7: The method according to any one of Aspects 1 to 6, wherein at least in part, the L1-RSRP / L1-SINR measurements associated with the first set of resources and the L1-RSRP / L1-SINR measurements associated with the second set of resources are associated with the same time-domain timing, and the first set of resources and the second set of resources are non-overlapping.

[0228] Aspect 8: The method according to any one of Aspects 1 to 7, wherein the L1-RSRP / L1-SINR measurement associated with the second set of resources is associated with future time-domain timing, and the first set of resources and the second set of resources overlap.

[0229] Aspect 9: The method according to any one of Aspects 1 to 8, wherein the generative model for the test data is defined at least in part based on an analytical expression or a statistical expression, and utilizes the randomization parameter that can be changed by the TE.

[0230] Aspect 10: The method according to any one of Aspects 1 to 9, wherein the randomization parameter is associated with one of the following: network node antenna configuration, delay spread, indoor environment, outdoor environment, urban environment, rural environment, cell type, Doppler drift, or UE speed.

[0231] Aspect 11: The method according to any one of Aspects 1 to 10, the method further comprising: sending an indication of the randomization parameters used by the generative model for test data to generate the L1-RSRP / L1-SINR measurements associated with the first set of resources.

[0232] Aspect 12: The method according to any one of Aspects 1 to 11, wherein the generative model for the test data is defined at least in part based on an artificial intelligence (AI) or machine learning (ML) (AI / ML) model, the AI / ML model input including the randomization parameters, and the AI / ML model input being modifiable by the TE.

[0233] Aspect 13: The method according to any one of Aspects 1 to 12, wherein the L1-RSRP / L1-SINR measurement associated with the first set of resources includes a first portion of the L1-RSRP / L1-SINR measurement and a second portion of the L1-RSRP / L1-SINR measurement.

[0234] Aspect 14: The method according to aspect 13, wherein the first portion of the L1-RSRP / L1-SINR measurement and the second portion of the L1-RSRP / L1-SINR measurement are associated with the generative model for the test data, which is defined at least in part based on an analytical expression or a statistical expression.

[0235] Aspect 15: The method according to aspect 13, wherein the first portion of the L1-RSRP / L1-SINR measurement and the second portion of the L1-RSRP / L1-SINR measurement are associated with the generative model for the test data, which is defined at least in part based on an artificial intelligence (AI) or machine learning (ML) (AI / ML) model.

[0236] Aspect 16: The method according to aspect 13, wherein the first portion of the L1-RSRP / L1-SINR measurement is associated with the generative model for the test data defined at least in part based on an analytical expression or a statistical expression, and the second portion of the L1-RSRP / L1-SINR measurement is associated with the generative model for the test data defined at least in part based on an artificial intelligence (AI) or machine learning (ML) (AI / ML) model.

[0237] Aspect 17: The method according to any one of Aspects 1 to 5416, wherein the L1-RSRP / L1-SINR measurement associated with the first set of resources and the reproducible L1-RSRP / L1-SINR measurement associated with the second set of resources are associated with the randomization parameter.

[0238] Aspect 18: The method according to any one of Aspects 1 to 17, wherein the recurring L1-RSRP / L1-SINR measurements associated with the second set of resources are associated with a plurality of future time-domain opportunities, and the plurality of future time-domain opportunities are associated with the same prediction instance.

[0239] Aspect 19: According to the method of aspect 18, wherein the first randomization parameter associated with a first time-domain timing among the plurality of future time-domain timings corresponds to a second randomization parameter associated with a second time-domain timing among the plurality of future time-domain timings.

[0240] Aspect 20: The method according to any one of Aspects 1 to 19, wherein the L1-RSRP / L1-SINR measurement associated with the first set of resources is associated with one or more historical time-domain moments, and the L1-RSRP / L1-SINR measurement associated with the first set of resources is based at least in part on changes in the randomization parameter across the one or more historical time-domain moments.

[0241] Aspect 21: A method of wireless communication performed at a user equipment (UE), the method comprising: receiving a Layer 1 (L1) reference signal received power (RSRP) or L1 signal-to-interference-plus-noise ratio (SINR) (L1-RSRP / L1-SINR) measurement associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurement associated with the first set of resources is at least partially based on a generative model for test data using randomized parameters; and transmitting beam prediction feedback indicating a L1-RSRP / L1-SINR measurement associated with a second set of resources, based at least partially on the L1-RSRP / L1-SINR measurement associated with the first set of resources.

[0242] Aspect 22: The method according to aspect 21, wherein the generative model for the test data or the parameters associated with the generative model for the test data are defined at least in part in the 3rd Generation Partnership Project (3GPP) specification.

[0243] Aspect 23: The method according to any one of aspects 21 to 22, the method further comprising: receiving an indication of an association between the first set of resources and the second set of resources, wherein the indication indicates one or more of alignment colocation (QCL), relative beam pointing direction, relative beamwidth, absolute beam point direction, or absolute beamwidth.

[0244] Aspect 24: The method according to any one of Aspects 21 to 23, wherein: the L1-RSRP / L1-SINR measurement associated with the first set of resources is received via a cable between the UE and the test equipment (TE); and the L1-RSRP / L1-SINR measurement associated with the second set of resources is transmitted via the cable or via an air interface between the UE and the TE.

[0245] Aspect 25: The method according to any one of Aspects 21 to 24, wherein at least in part, the L1-RSRP / L1-SINR measurements associated with the first set of resources and the L1-RSRP / L1-SINR measurements associated with the second set of resources are associated with the same time-domain timing, and the first set of resources and the second set of resources are non-overlapping.

[0246] Aspect 26: The method according to any one of Aspects 21 to 25, wherein the L1-RSRP / L1-SINR measurement associated with the second set of resources is associated with future time-domain timing, and the first set of resources and the second set of resources overlap.

[0247] Aspect 27: The method according to any one of Aspects 21 to 26, wherein the generative model for the test data is defined at least in part based on an analytical expression or a statistical expression, and utilizes the variable randomization parameters.

[0248] Aspect 28: The method according to any one of Aspects 21 to 27, wherein the randomization parameter is associated with one of the following: network node antenna configuration, delay spread, indoor environment, outdoor environment, urban environment, rural environment, cell type, Doppler drift, or UE speed.

[0249] Aspect 29: The method according to any one of aspects 21 to 28, the method further comprising: receiving an indication of the randomization parameters used by the generative model for test data to generate the L1-RSRP / L1-SINR measurements associated with the first set of resources.

[0250] Aspect 30: The method according to any one of Aspects 21 to 29, wherein the generative model for the test data is defined at least in part based on an artificial intelligence (AI) or machine learning (ML) (AI / ML) model, the AI / ML model input including the randomization parameters, and the AI / ML model input is variable.

[0251] Aspect 31: The method according to any one of Aspects 21 to 30, wherein the L1-RSRP / L1-SINR measurement associated with the first set of resources includes a first portion of the L1-RSRP / L1-SINR measurement and a second portion of the L1-RSRP / L1-SINR measurement.

[0252] Aspect 32: According to the method of aspect 31, the first portion of the L1-RSRP / L1-SINR measurement and the second portion of the L1-RSRP / L1-SINR measurement are associated with the generative model for the test data, which is defined at least in part based on an analytical expression or a statistical expression.

[0253] Aspect 33: The method according to aspect 31, wherein the first portion of the L1-RSRP / L1-SINR measurement and the second portion of the L1-RSRP / L1-SINR measurement are associated with the generative model for the test data, which is defined at least in part based on an artificial intelligence (AI) or machine learning (ML) (AI / ML) model.

[0254] Aspect 34: The method according to aspect 31, wherein the first portion of the L1-RSRP / L1-SINR measurement is associated with the generative model for the test data defined at least in part based on an analytical expression or a statistical expression, and the second portion of the L1-RSRP / L1-SINR measurement is associated with the generative model for the test data defined at least in part based on an artificial intelligence (AI) or machine learning (ML) (AI / ML) model.

[0255] Aspect 35: The method according to any one of Aspects 21 to 34, wherein the L1-RSRP / L1-SINR measurement associated with the first set of resources and the reproducible L1-RSRP / L1-SINR measurement associated with the second set of resources are associated with the randomization parameter.

[0256] Aspect 36: The method according to any one of Aspects 21 to 35, wherein the recurring L1-RSRP / L1-SINR measurements associated with the second set of resources are associated with a plurality of future time-domain opportunities, and the plurality of future time-domain opportunities are associated with the same prediction instance.

[0257] Aspect 37: According to the method of aspect 36, the first randomization parameter associated with a first time-domain timing among the plurality of future time-domain timings corresponds to a second randomization parameter associated with a second time-domain timing among the plurality of future time-domain timings.

[0258] Aspect 38: The method according to any one of Aspects 21 to 37, wherein the L1-RSRP / L1-SINR measurement associated with the first set of resources is associated with one or more historical time-domain moments, and the L1-RSRP / L1-SINR measurement associated with the first set of resources is based at least in part on changes in the randomization parameter across the one or more historical time-domain moments.

[0259] Aspect 39: An apparatus for wireless communication at a device, the apparatus comprising: one or more processors; one or more memories coupled to the one or more processors; and instructions stored in the one or more memories and executable by the one or more processors to cause the apparatus to perform the method according to one or more of aspects 1 to 20.

[0260] Aspect 40: An apparatus for wireless communication at a device, the apparatus including one or more memories and one or more processors coupled to the one or more memories, the one or more processors being configured to cause the device to perform the method according to one or more of aspects 1 to 20.

[0261] Aspect 41: An apparatus for wireless communication, the apparatus comprising at least one component for performing the method according to one or more of aspects 1 to 20.

[0262] Aspect 42: A non-transitory computer-readable medium storing code for wireless communication, the code including instructions executable by one or more processors to perform the method according to one or more of aspects 1 to 20.

[0263] Aspect 43: A non-transitory computer-readable medium storing a set of instructions for wireless communication, the set of instructions comprising one or more instructions that, when executed by one or more processors of a device, cause the device to perform the method according to one or more of aspects 1 to 20.

[0264] Aspect 44: A device for wireless communication, the device including a processing system comprising one or more processors and one or more memories coupled to the one or more processors, the processing system being configured to cause the device to perform the method according to one or more of aspects 1 to 20.

[0265] Aspect 45: A test apparatus (TE) for wireless communication, the test apparatus (TE) comprising: a processing system including processor circuitry and memory circuitry, the memory circuitry storing code and coupled to the processor circuitry, the processing system being configured to cause the TE to perform the method according to one or more of aspects 1 to 20.

[0266] Aspect 46: An apparatus for wireless communication at a test equipment (TE), the apparatus comprising one or more memories and one or more processors coupled to the one or more memories, the one or more processors being configured individually or jointly to cause the TE to perform the method according to one or more of aspects 1 to 20.

[0267] Aspect 47: An apparatus for wireless communication at a test equipment (TE), the apparatus comprising: a processing system including processor circuitry and memory circuitry, the memory circuitry storing code and coupled to the processor circuitry, the processing system being configured to cause the TE to perform the method according to one or more of aspects 1 to 20.

[0268] Aspect 48: An apparatus for wireless communication at a device, the apparatus comprising: one or more processors; one or more memories coupled to the one or more processors; and instructions stored in the one or more memories and executable by the one or more processors to cause the apparatus to perform the method according to one or more of aspects 21 to 28.

[0269] Aspect 49: An apparatus for wireless communication at a device, the apparatus comprising one or more memories and one or more processors coupled to the one or more memories, the one or more processors being configured to cause the device to perform the method according to one or more of aspects 21 to 28.

[0270] Aspect 50: An apparatus for wireless communication, the apparatus comprising at least one component for performing the method according to one or more of aspects 21 to 28.

[0271] Aspect 51: A non-transitory computer-readable medium storing code for wireless communication, the code including instructions executable by one or more processors to perform the method according to one or more of aspects 21 to 28.

[0272] Aspect 52: A non-transitory computer-readable medium storing a set of instructions for wireless communication, the set of instructions comprising one or more instructions that, when executed by one or more processors of a device, cause the device to perform the method according to one or more of aspects 21 to 28.

[0273] Aspect 53: A device for wireless communication, the device including a processing system comprising one or more processors and one or more memories coupled to the one or more processors, the processing system being configured to cause the device to perform the method according to one or more of aspects 21 to 28.

[0274] Aspect 54: A user equipment (UE) for wireless communication, the user equipment (UE) comprising: a processing system including processor circuitry and memory circuitry, the memory circuitry storing code and coupled to the processor circuitry, the processing system being configured to cause the UE to perform one or more of the methods according to aspects 21 to 28.

[0275] Aspect 55: An apparatus for wireless communication at a user equipment (UE), the apparatus comprising one or more memories and one or more processors coupled to the one or more memories, the one or more processors being configured to individually or jointly cause the UE to perform one or more of the methods according to aspects 21 to 28.

[0276] Aspect 56: An apparatus for wireless communication at a user equipment (UE), the apparatus comprising: a processing system including processor circuitry and memory circuitry, the memory circuitry storing code and coupled to the processor circuitry, the processing system being configured to cause the UE to perform one or more of the methods described in aspects 21 to 28.

[0277] While the foregoing disclosure provides examples and descriptions, it is not intended to be exhaustive or to limit aspects to the precise form disclosed. Modifications and variations can be made based on the foregoing disclosure, or from various aspects of practice.

[0278] As used herein, the term "component" is intended to be interpreted broadly as hardware and / or a combination of hardware and software. Whether referred to as software, firmware, middleware, microcode, hardware description language, or other names, "software" should be interpreted broadly as meaning instructions, instruction sets, code, code segments, program code, programs, subroutines, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, and / or functions, etc. As used herein, a "processor" is implemented in hardware and / or a combination of hardware and software. It will be apparent to those skilled in the art that the systems and / or methods described herein can be implemented in various forms of hardware and / or combinations of hardware and software. The actual dedicated control hardware or software code used to implement these systems and / or methods is not limiting in any way. Therefore, no specific software code is referenced in this document to describe the operation and behavior of the systems and / or methods, as those skilled in the art will understand that the software and hardware can be designed, at least in part, based on the descriptions herein, to implement the systems and / or methods.

[0279] Hardware and data processing means for implementing the various exemplary logic, logic blocks, modules, and circuits described herein can be implemented or executed using general-purpose single-chip or multi-chip processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor can be a microprocessor, or any conventional processor, controller, microcontroller, or state machine. A processor can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors combined with a DSP core, or any other such configuration. In some aspects, specific processes and methods can be performed by circuitry dedicated to a given function.

[0280] As used in this article, depending on the context, "meeting the threshold" can mean a value greater than the threshold, greater than or equal to the threshold, less than the threshold, less than or equal to the threshold, equal to the threshold, not equal to the threshold, etc.

[0281] Although specific combinations of features are set forth in the claims and / or disclosed in the specification, these combinations are not intended to limit the disclosure of various aspects. Many of these features may be combined in ways not specifically set forth in the claims and / or not disclosed in the specification. The disclosure of various aspects includes each dependent claim in combination with each other claim in the set of claims. As used herein, the phrase referring to “at least one of” the list of entries means any combination of these entries, including a single member. As an example, “at least one of a, b, or c” is intended to cover: a, b, c, a+b, a+c, b+c, and a+b+c, as well as any combination having multiple identical elements (e.g., a+a, a+a+a, a+a+b, a+a+c, a+b+b, a+c+c, b+b, b+b+b, b+b+c, c+c, and c+c+c, or any other ordering of a, b, and c).

[0282] No element, action, or instruction used herein should be construed as essential or necessary unless explicitly stated otherwise. Furthermore, as used herein, the articles “a” and “an” are intended to include one or more items and are used interchangeably with “one or more.” Furthermore, as used herein, the article “described” is intended to include one or more items mentioned in connection with the article “described” and is used interchangeably with “one or more.” Furthermore, as used herein, the terms “group” and “cluster” are intended to include one or more items and are used interchangeably with “one or more.” If only one item is desired, the phrase “only one” or similar terminology will be used. Furthermore, as used herein, the terms “have,” “possess,” “have,” etc., are intended to be open-ended terms that do not limit the elements they modify (e.g., an element “having” A may also have B). Furthermore, the phrase “based on” is intended to mean “at least partially based on” unless otherwise explicitly stated. Furthermore, as used herein, the term “or” is intended to be inclusive when used in a series and is interchangeable with “and / or” unless otherwise explicitly stated (e.g., in the case of its use in conjunction with “any” or “only one”).

Claims

1. An apparatus for wireless communication at a test equipment (TE), the apparatus comprising: One or more memory units; and One or more processors, said one or more processors being coupled to said one or more memories and configured to cause the TE: Transmit a Layer 1 (L1) reference signal received power (RSRP) or L1 signal-to-interference-plus-noise ratio (SINR) (L1-RSRP / L1-SINR) measurement associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurement associated with the first set of resources is at least partially based on a generative model for the test data using randomized parameters; and Beam prediction feedback associated with user equipment (UE) side beam prediction is received at least in part based on the L1-RSRP / L1-SINR measurement associated with the first set of resources, wherein the beam prediction feedback indicates the L1-RSRP / L1-SINR measurement associated with the second set of resources.

2. The apparatus of claim 1, wherein the one or more processors are further configured to cause the TE: The L1-RSRP / L1-SINR measurements associated with the first set of resources are generated, at least in part based on the generative model for the test data and at least in part based on the randomization parameters.

3. The apparatus of claim 1, wherein the generation model for the test data or the parameters associated with the generation model for the test data are defined at least in part in the 3rd Generation Partnership Project (3GPP) specifications.

4. The apparatus of claim 1, wherein the one or more processors are further configured to cause the TE: At least in part, based on the generative model for the test data, reproduced L1-RSRP / L1-SINR measurements associated with the second set of resources are generated; and The accuracy of the UE-side beam prediction is determined at least in part based on a comparison between the reproduced L1-RSRP / L1-SINR measurements associated with the second set of resources and the L1-RSRP / L1-SINR measurements associated with the second set of resources.

5. The apparatus of claim 1, wherein the one or more processors are further configured to cause the TE: Sending an indication of the association between the first set of resources and the second set of resources, wherein the indication indicates one or more of alignment colocation (QCL), relative beam pointing direction, relative beamwidth, absolute beam point direction, or absolute beamwidth.

6. The apparatus according to claim 1, wherein: The L1-RSRP / L1-SINR measurements associated with the first set of resources are transmitted via the cable between the TE and the UE; and The L1-RSRP / L1-SINR measurement associated with the second set of resources is received via the cable or via the air interface between the TE and the UE.

7. The apparatus of claim 1, wherein at least in part, the L1-RSRP / L1-SINR measurements associated with the first set of resources and the L1-RSRP / L1-SINR measurements associated with the second set of resources are associated with the same time-domain timing, and the first set of resources and the second set of resources are non-overlapping.

8. The apparatus of claim 1, wherein the L1-RSRP / L1-SINR measurement associated with the second set of resources is at least partially associated with future time-domain timing, and the first set of resources and the second set of resources overlap.

9. The apparatus of claim 1, wherein the generation model for the test data is defined at least in part based on an analytical or statistical expression, and utilizes the randomization parameter that can be changed by the TE.

10. The apparatus of claim 1, wherein the randomization parameter is associated with one of the following: network node antenna configuration, delay spread, indoor environment, outdoor environment, urban environment, rural environment, cell type, Doppler drift, or UE speed.

11. The apparatus of claim 1, wherein the one or more processors are further configured to cause the TE: Send an indication of the randomization parameters used by the generative model for the test data to generate the L1-RSRP / L1-SINR measurements associated with the first set of resources.

12. The apparatus of claim 1, wherein the generative model for the test data is defined at least in part based on an artificial intelligence (AI) or machine learning (ML) (AI / ML) model, the AI / ML model input including the randomization parameters, and the AI / ML model input being modifiable by the TE.

13. The apparatus of claim 1, wherein the L1-RSRP / L1-SINR measurement associated with the first set of resources includes a first portion of the L1-RSRP / L1-SINR measurement and a second portion of the L1-RSRP / L1-SINR measurement.

14. The apparatus of claim 13, wherein the first portion of the L1-RSRP / L1-SINR measurement and the second portion of the L1-RSRP / L1-SINR measurement are associated with the generative model for the test data, which is defined at least in part based on an analytical expression or a statistical expression.

15. The apparatus of claim 13, wherein the first portion of the L1-RSRP / L1-SINR measurement and the second portion of the L1-RSRP / L1-SINR measurement are associated with the generative model for the test data, which is defined at least in part based on an artificial intelligence (AI) or machine learning (ML) (AI / ML) model.

16. The apparatus of claim 13, wherein the first portion of the L1-RSRP / L1-SINR measurement is associated with the generative model for the test data, which is defined at least in part based on an analytical expression or a statistical expression, and the second portion of the L1-RSRP / L1-SINR measurement is associated with the generative model for the test data, which is defined at least in part based on an artificial intelligence (AI) or machine learning (ML) (AI / ML) model.

17. The apparatus of claim 1, wherein the L1-RSRP / L1-SINR measurement associated with the first set of resources and the reproduced L1-RSRP / L1-SINR measurement associated with the second set of resources are associated with the randomization parameter.

18. The apparatus of claim 1, wherein the recurring L1-RSRP / L1-SINR measurements associated with the second set of resources are associated with a plurality of future time-domain opportunities, and the plurality of future time-domain opportunities are associated with the same prediction instance.

19. The apparatus of claim 18, wherein the first randomization parameter associated with a first time-domain timing among the plurality of future time-domain timings corresponds to a second randomization parameter associated with a second time-domain timing among the plurality of future time-domain timings.

20. The apparatus of claim 1, wherein the L1-RSRP / L1-SINR measurement associated with the first set of resources is associated with one or more historical time-domain moments, and the L1-RSRP / L1-SINR measurement associated with the first set of resources is based at least in part on changes in the randomization parameter across the one or more historical time-domain moments.

21. An apparatus for wireless communication at a user equipment (UE), the apparatus comprising: One or more memory units; and One or more processors, said one or more processors coupled to said one or more memories and configured to cause the UE to: Receive a Layer 1 (L1) reference signal received power (RSRP) or L1 signal-to-interference-plus-noise ratio (SINR) (L1-RSRP / L1-SINR) measurement associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurement associated with the first set of resources is based at least in part on a generative model for test data using randomized parameters; and Beam prediction feedback indicating L1-RSRP / L1-SINR measurements associated with a second set of resources is transmitted, based at least in part on the L1-RSRP / L1-SINR measurements associated with the first set of resources.

22. The apparatus of claim 21, wherein the one or more processors are further configured to cause the UE to: Receive an indication of association between the first set of resources and the second set of resources, wherein the indication indicates one or more of alignment colocation (QCL), relative beam pointing direction, relative beamwidth, absolute beam point direction, or absolute beamwidth.

23. The apparatus according to claim 21, wherein: The L1-RSRP / L1-SINR measurements associated with the first set of resources are received via a cable between the UE and the test equipment (TE); and The L1-RSRP / L1-SINR measurements associated with the second set of resources are transmitted via the cable or via the air interface between the UE and the TE.

24. The apparatus of claim 21, wherein: At least in part, based on the L1-RSRP / L1-SINR measurements associated with the first set of resources and the L1-RSRP / L1-SINR measurements associated with the second set of resources being associated with the same time-domain timing, the first set of resources and the second set of resources are non-overlapping; or At least in part, the L1-RSRP / L1-SINR measurements associated with the second set of resources are correlated with future time-domain timing, and the first set of resources and the second set of resources overlap.

25. The apparatus according to claim 21, wherein: The generative model for the test data is defined at least in part based on an analytical or statistical expression and utilizes the variable randomization parameters; or The generative model for the test data is defined at least in part based on an artificial intelligence (AI) or machine learning (ML) (AI / ML) model, the AI / ML model input including the randomization parameters, and the AI / ML model input is variable.

26. The apparatus of claim 21, wherein the one or more processors are further configured to cause the UE to: Receive an indication of the randomization parameters used by the generative model for test data to generate the L1-RSRP / L1-SINR measurements associated with the first set of resources, wherein the randomization parameters are associated with one of the following: network node antenna configuration, delay spread, indoor environment, outdoor environment, urban environment, rural environment, cell type, Doppler drift, or UE speed.

27. The apparatus of claim 21, wherein: The L1-RSRP / L1-SINR measurement associated with the first set of resources includes a first portion of the L1-RSRP / L1-SINR measurement and a second portion of the L1-RSRP / L1-SINR measurement; and The first portion of the L1-RSRP / L1-SINR measurement and the second portion of the L1-RSRP / L1-SINR measurement are associated with the generative model for the test data, which is defined at least in part based on analytical or statistical expressions; The first portion of the L1-RSRP / L1-SINR measurement and the second portion of the L1-RSRP / L1-SINR measurement are associated with the generative model for the test data, which is defined at least in part based on an artificial intelligence (AI) or machine learning (ML) (AI / ML) model; or The first portion of the L1-RSRP / L1-SINR measurement is associated with the generative model for the test data, which is defined at least in part based on the analytical expression or the statistical expression, and the second portion of the L1-RSRP / L1-SINR measurement is associated with the generative model for the test data, which is defined at least in part based on the AI / ML model.

28. The apparatus according to claim 21, wherein: The L1-RSRP / L1-SINR measurements associated with the first set of resources and the reproducible L1-RSRP / L1-SINR measurements associated with the second set of resources are associated with the randomization parameter; The recurring L1-RSRP / L1-SINR measurements associated with the second set of resources are associated with multiple future time-domain opportunities, and the multiple future time-domain opportunities are associated with the same prediction instance; or The L1-RSRP / L1-SINR measurement associated with the first set of resources is associated with one or more historical time-domain moments, and the L1-RSRP / L1-SINR measurement associated with the first set of resources is based at least in part on changes in the randomization parameter across the one or more historical time-domain moments.

29. A method for wireless communication performed at a test apparatus (TE), the method comprising: Transmit a Layer 1 (L1) reference signal received power (RSRP) or L1 signal-to-interference-plus-noise ratio (SINR) (L1-RSRP / L1-SINR) measurement associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurement associated with the first set of resources is at least partially based on a generative model for the test data using randomized parameters; and Beam prediction feedback associated with user equipment (UE) side beam prediction is received at least in part based on the L1-RSRP / L1-SINR measurement associated with the first set of resources, wherein the beam prediction feedback indicates the L1-RSRP / L1-SINR measurement associated with the second set of resources.

30. A method for wireless communication performed at a user equipment (UE), the method comprising: Receive a Layer 1 (L1) reference signal received power (RSRP) or L1 signal-to-interference-plus-noise ratio (SINR) (L1-RSRP / L1-SINR) measurement associated with a first set of resources, wherein the L1-RSRP / L1-SINR measurement associated with the first set of resources is based at least in part on a generative model for test data using randomized parameters; and Beam prediction feedback indicating L1-RSRP / L1-SINR measurements associated with a second set of resources is transmitted, based at least in part on the L1-RSRP / L1-SINR measurements associated with the first set of resources.

Images