Differential rsrp based performance monitoring for ai / ml model or functionality
Patent Information
- Authority / Receiving Office
- EP · EP
- Patent Type
- Applications
- Current Assignee / Owner
- LENOVO (BEIJING) LTD
- Filing Date
- 2023-08-04
- Publication Date
- 2026-06-10
Smart Images

Figure 1.1
Abstract
Description
DIFFERENTIAL RSRP BASED PERFORMANCE MONITORING FOR AI / ML MODEL OR FUNCTIONALITYTECHNICAL FIELD
[0001] The present disclosure relates to wireless communications, and more specifically to a user equipment, a base station, processors, methods for performing a differential reference signal receiving power (RSRP) based performance monitoring for an artificial intelligence (AI) / machine learning (ML) model or an AI / ML functionality.BACKGROUND
[0002] A wireless communications system may include one or multiple network communication devices, such as base stations, which may be otherwise known as an eNodeB (eNB) , a next-generation NodeB (gNB) , or other suitable terminology. Each network communication devices, such as a base station may support wireless communications for one or multiple user communication devices, which may be otherwise known as user equipment (UE) , or other suitable terminology. The wireless communications system may support wireless communications with one or multiple user communication devices by utilizing resources of the wireless communication system (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers) . Additionally, the wireless communications system may support wireless communications across various radio access technologies including third generation (3G) radio access technology, fourth generation (4G) radio access technology, fifth generation (5G) radio access technology, among other suitable radio access technologies beyond 5G (e.g., sixth generation (6G) ) .
[0003] The 3rd Generation Partnership Project (3GPP) is working on the study of the potential benefit by adopting artificial intelligence (AI) / machine learning (ML) model (s) or functionality (ies) for air interface in some use cases, such as employing AI / ML model (s) or functionality (ies) in beam management for NR system for beam prediction.SUMMARY
[0004] The present disclosure relates to devices, methods, and apparatuses that support communication with AI / ML model (s) or functionality (ies) . By performing the related process of present disclosure, the performance monitoring for AI / ML model or functionality for inference can be supported.
[0005] Some implementations of the method and apparatuses described herein may further include receiving, from a base station via the transceiver, a configuration on a resource setting containing one or more non-zero power channel state information reference signal (NZP CSI-RS) resource sets for an operation of the UE associated with an artificial intelligence (AI) / machine learning (ML) model or an AI / ML functionality; and transmitting, to the base station via the transceiver, an indication for a failure event of the AI / ML model or the AI / ML functionality in the case that the UE determines the failure event based on differential reference signal receiving power (RSRP) based performance monitoring for the AI / ML model or the AI / ML functionality.
[0006] In some implementations of the method and apparatuses described herein, the operation comprises one of the following: providing a channel state information (CSI) report, performing a beam prediction, or performing a CSI prediction.
[0007] Some implementations of the method and apparatuses described herein may further include receiving, from the base station via the transceiver, a CSI reporting configuration with the operation of AI / ML associated with the resource setting configuration; transmitting, to the base station via the transceiver, a beam report corresponding to the CSI reporting configuration, wherein the beam report indicates a set of transmit beams and corresponding predicted layer 1 reference signal receiving power (L1-RSRP) ; and receiving, from the base station via the transceiver, transmission on NZP CSI-RS resources corresponding to the resource setting associated with the set of reported transmit beams.
[0008] In some implementations of the method and apparatuses described herein, the beam report is transmitted in a first set of symbol (s) , the transmission on the NZP CSI-RS resource (s) is received in a second set of symbol (s) , and the duration between the last symbol of the first set of symbol (s) and the first symbol of the second set of symbol (s) is larger than a first threshold.
[0009] In some implementations of the method and apparatuses described herein, the resource setting configuration indicates one set of NZP CSI-RS resources, a first NZP CSI-RS resource at first position of the set of NZP CSI-RS is assumed to be transmitted by a first transmit beam at a first position of the set of transmit beams indicated in the associated beam report, and a second NZP CSI-RS at second position of the set of NZP CSI-RS resource is assumed to be transmitted by a second transmit beam at a second position of the set of transmit beams indicated in the associated beam report.
[0010] In some implementations of the method and apparatuses described herein, the NZP CSI-RS resource (s) in the resource setting configuration is periodic in the case that the CSI report is a periodic CSI report.
[0011] In some implementations of the method and apparatuses described herein, the NZP CSI-RS resource (s) in the resource setting configuration is a semi-persistent in the case that the CSI report is one of the following: a semi-persistent CSI report, or a periodic CSI report.
[0012] In some implementations of the method and apparatuses described herein, he NZP CSI-RS resource (s) in the resource setting configuration is aperiodic in the case that the CSI report is one of the following: a semi-persistent CSI report, a periodic CSI report, or an aperiodic CSI report.
[0013] Some implementations of the method and apparatuses described herein may further include transmitting, to the base station via the transceiver, an aperiodic beam transmission request for performance monitoring in a beam report associated with AI / ML operation.
[0014] In some implementations of the method and apparatuses described herein, an AI / ML model failure instance or an AI / ML functionality failure instance is determined in the case that average differential RSRP of all beams in the set of transmit beams is worse than a second threshold.
[0015] In some implementations of the method and apparatuses described herein, determining the failure event based on differential RSRP based performance monitoring for the AI / ML model or the AI / ML functionality comprises: determining the failure event of the AI / ML model or the AI / ML functionality in the case that a number of the AI / ML model failure instances or the AI / ML functionality failure instances during a period is greater than a third threshold.
[0016] In some implementations of the method and apparatuses described herein, the failure event of the AI / ML model or the AI / ML functionality comprises at least one of the following: a measured L1-RSRP of each of the beams in the latest set of NZP CSI- RS resource for performance monitoring; whether there is another AI / ML model or functionality applicable to a current scenario or condition; or a recommended AI / ML model or functionality.
[0017] The present disclosure also relates to devices, methods, and apparatuses that support receiving, from the base station via the transceiver, a CSI reporting configuration associated with the resource setting configuration, the NZP CSI-RS resources in the NZP CSI-RS resource set for the resource setting is configured with a parameter of repetition; transmitting, to the base station via the transceiver, a beam report corresponding to the CSI reporting configuration, wherein the beam report comprises a set of beams and a corresponding L1-RSRP.
[0018] In some implementations of the method and apparatuses described herein, the resource setting configuration comprises one NZP CSI-RS resource set containing one or more NZP CSI-RS resource groups, transmissions on NZP CSI-RS resources in the same NZP CSI-RS resource group are assumed to be transmitted by a same transmit beam, and transmissions on NZP CSI-RS resources in different NZP CSI-RS resource groups are assumed to be transmitted by different transmit beams.
[0019] In some implementations of the method and apparatuses described herein, a first beam at a first position in the beam report corresponds to the transmit beam used for a first NZP CSI resource group of the NZP CSI-RS resource set, the corresponding L1-RSRP is the highest L1-RSRP corresponding to the first beam among the receive beams of the UE, a second beam in the beam report at a second position corresponds to the transmit beam used for a second NZP CSI resource group of the NZP CSI-RS resource set, and the corresponding L1-RSRP is the highest L1-RSRP corresponding to the second beam among the receive beams of the UE.
[0020] In some implementations of the method and apparatuses described herein, the resource setting containing a NZP CSI-RS resource set, and a transmission on an NZP CSI-RS resource in the NZP CSI-RS resource set is transmitted with a configured repetition times in a same number of the valid symbols.
[0021] In some implementations of the method and apparatuses described herein, transmissions on different NZP CSI-RS resources in the NZP CSI-RS resource set are transmitted in different slots.
[0022] Some implementations of the method and apparatuses described herein may further include transmitting, to a user equipment (UE) via the transceiver, a configuration on a resource setting containing one or more non-zero power channel state information reference signal (NZP CSI-RS) resource sets for an operation of the UE associated with an artificial intelligence (AI) / machine learning (ML) model or an AI / ML functionality; and receiving, from the UE via the transceiver, an indication for a failure event of the AI / ML model or the AI / ML functionality in the case that the UE determines the failure event based on differential reference signal receiving power (RSRP) based performance monitoring for the AI / ML model or the AI / ML functionality.
[0023] In some implementations of the method and apparatuses described herein, the operation comprises one of the following: providing a channel state information (CSI) report, performing a beam prediction, or performing a CSI prediction.
[0024] Some implementations of the method and apparatuses described herein may further include transmitting, to the UE via the transceiver, CSI reporting configuration with the operation of AI / ML associated with the resource setting configuration; receiving, from the UE via the transceiver, a beam report corresponding to the CSI reporting configuration, wherein the beam report indicates a set of transmit beams and corresponding predicted layer 1 reference signal receiving power (L1-RSRP) ; and transmitting, to the UE via the transceiver, transmission on NZP CSI-RS resources corresponding to the resource setting associated with the set of reported transmit beams.
[0025] In some implementations of the method and apparatuses described herein, the beam report is received in a first set of symbol (s) , the transmission on the NZP CSI-RS resource (s) is transmitted in a second set of symbol (s) , and the duration between the last symbol of the first set of symbol (s) and the first symbol of the second set of symbol (s) is larger than a first threshold.
[0026] In some implementations of the method and apparatuses described herein, the resource setting configuration indicates one sets of NZP CSI-RS resources, a first NZP CSI-RS at first position of the set of NZP CSI-RS is assumed to be transmitted by a first transmit beam at a first position of the set of transmit beams indicated in the associated beam report, and a second NZP CSI-RS at second position of the set of NZP CSI-RS resource is assumed to be transmitted by a second transmit beam at a second position of the set of transmit beams indicated in the associated beam report.
[0027] In some implementations of the method and apparatuses described herein, the NZP CSI-RS resource (s) in the resource setting configuration is periodic in the case that the CSI report is a periodic CSI report.
[0028] In some implementations of the method and apparatuses described herein, the NZP CSI-RS resource (s) in the resource setting configuration is semi-persistent in the case that the CSI report is one of the following: a semi-persistent CSI report, or a periodic CSI report.
[0029] In some implementations of the method and apparatuses described herein, the NZP CSI-RS resource (s) in the resource setting configuration is aperiodic in the case that the CSI report is one of the following: a semi-persistent CSI report, a periodic CSI report, or an aperiodic CSI report.
[0030] Some implementations of the method and apparatuses described herein may further include receiving, from the UE via the transceiver, an aperiodic beam transmissione request for the performance monitoring in a beam report associated with AI / ML operation.
[0031] In some implementations of the method and apparatuses described herein, an AI / ML model failure instance or an AI / ML functionality failure instance is determined in the case that average differential RSRP of all beams in the set of transmit beams is worse than a second threshold.
[0032] In some implementations of the method and apparatuses described herein, determining the failure event based on differential RSRP based performance monitoring for the AI / ML model or the AI / ML functionality comprises: determining the failure event of the AI / ML model or the AI / ML functionality in the case that a number of the AI / ML model failure instances or the AI / ML functionality failure instances during a period is greater than a third threshold.
[0033] In some implementations of the method and apparatuses described herein, the failure event of the AI / ML model or the AI / ML functionality comprises at least one of the following: a measured L1-RSRP of each of the beams in the latest set of NZP CSI-RS resource for performance monitoring; whether there is another AI / ML model or functionality applicable to a current scenario or condition; or a recommended AI / ML model or functionality.
[0034] Some implementations of the method and apparatuses described herein may further include transmitting, to the UE via the transceiver, a CSI reporting configuration associated with the resource setting configuration, the NZP CSI-RS resources in the NZP CSI-RS resource set for the resource setting is configured with a parameter of repetition; receiving, from the UE via the transceiver, a beam report corresponding to the CSI reporting configuration, wherein the beam report comprises a set of beams and a corresponding L1-RSRP.
[0035] In some implementations of the method and apparatuses described herein, the resource setting configuration comprises one NZP CSI-RS resource set containing one or more NZP CSI-RS resource groups configuration, transmissions on NZP CSI-RS resources in the same NZP CSI-RS resource group are assumed to be transmitted by a same transmit beam, and transmissions on NZP CSI-RS resources in different NZP CSI-RS resource groups are assumed to be transmitted by different transmit beams.
[0036] In some implementations of the method and apparatuses described herein, a first beam at a first position in the beam report corresponds to the transmit beam used for a first NZP CSI resource group of the NZP CSI-RS resource set, the corresponding L1-RSRP is the highest L1-RSRP corresponding to the first beam among the receive beams of the UE, a second beam in the beam report at a second position corresponds to the transmit beam used for a second NZP CSI resource group of the NZP CSI-RS resource, and the corresponding L1-RSRP is the highest L1-RSRP corresponding to the second beam among the receive beams of the UE.
[0037] In some implementations of the method and apparatuses described herein, the resource setting containing a NZP CSI-RS resource set, and a transmission on an NZP CSI-RS resource in the NZP CSI-RS resource set is transmitted with a configured repetition times in a same number of the valid symbols.
[0038] In some implementations of the method and apparatuses described herein, transmissions on different NZP CSI-RS resources in the NZP CSI-RS resource set are transmitted in different slots.BRIEF DESCRIPTION OF THE DRAWINGS
[0039] FIG. 1 illustrates an example of a wireless communications system that supports AI / ML inference for communication in accordance with aspects of the present disclosure.
[0040] FIG. 2 illustrates an example of signaling flow that supports AI / ML inference for communication in accordance with aspects of the present disclosure.
[0041] FIG. 3 illustrates an example of a procedure that supports AI / ML inference for communication in accordance with aspects of the present disclosure.
[0042] FIG. 4 illustrates an example of a procedure that supports transmission for performance monitoring in accordance with aspects of the present disclosure.
[0043] FIG. 5 illustrates an example of a procedure that supports transmission for performance monitoring in accordance with aspects of the present disclosure.
[0044] FIG. 6 illustrates an example of a procedure that supports AI / ML inference for communication in accordance with aspects of the present disclosure.
[0045] FIG. 7 illustrates an example of a device that supports AI / ML inference for communication in accordance with aspects of the present disclosure.
[0046] FIG. 8 illustrates an example of a device that supports AI / ML inference for communication in accordance with aspects of the present disclosure.
[0047] FIG. 9 illustrates an example of a processor that supports AI / ML inference for communication in accordance with aspects of the present disclosure.
[0048] FIG. 10 illustrates an example of a processor that supports AI / ML inference for communication in accordance with aspects of the present disclosure.
[0049] FIG. 11 illustrates flowchart of method that supports AI / ML inference for communication in accordance with aspects of the present disclosure.
[0050] FIG. 12 illustrates flowchart of method that supports AI / ML inference for communication in accordance with aspects of the present disclosure.DETAILED DESCRIPTION
[0051] Principles of the present disclosure will now be described with reference to some embodiments. It is to be understood that these embodiments are described only for the purpose of illustration and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitation as to the scope of the disclosure. The disclosure described herein may be implemented in various manners other than the ones described below.
[0052] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skills in the art to which this disclosure belongs.
[0053] References in the present disclosure to “one embodiment, ” “an example embodiment, ” “an embodiment, ” “some embodiments, ” and the like indicate that the embodiment (s) described may include a particular feature, structure, or characteristic, but it is not necessary that every embodiment includes the particular feature, structure, or characteristic. Moreover, such phrases do not necessarily refer to the same embodiment (s) . Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.
[0054] It shall be understood that although the terms “first” and “second” or the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, a first element could also be termed as a second element, and similarly, a second element could also be termed as a first element, without departing from the scope of embodiments. As used herein, the term “and / or” includes any and all combinations of one or more of the listed terms.
[0055] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a” , “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises” , “comprising” , “has” , “having” , “includes” and / or “including” , when used herein, specify the presence of stated features, elements, and / or components etc., but do not preclude the presence or addition of one or more other features, elements, components and / or combinations thereof.
[0056] As used herein, the term “communication network” refers to a network following any suitable communication standards, such as, 5G NR, long term evolution (LTE) , LTE-advanced (LTE-A) , wideband code division multiple access (WCDMA) , high-speed packet access (HSPA) , narrow band internet of things (NB-IoT) , and so on. Further, the communications between a terminal device and a network device in the communication network may be performed according to any suitable generation communication protocols, including but not limited to, the first generation (1G) , the second generation (2G) , 2.5G, 2.75G, the third generation (3G) , the fourth generation (4G) , 4.5G, the fifth generation (5G) communication protocols, and / or any other protocols either currently known or to be developed in the future. Embodiments of the present disclosure may be applied in various communication systems. Given the rapid development in communications, there will also be future type communication technologies and systems in which the present disclosure may be embodied. It should not be seen as limiting the scope of the present disclosure to only the aforementioned systems.
[0057] As used herein, the term “network device” generally refers to a node in a communication network via which a terminal device can access the communication network and receive services therefrom. The network device may refer to a base station (BS) or an access point (AP) , for example, a node B (NodeB or NB) , a radio access network (RAN) node, an evolved NodeB (eNodeB or eNB) , a NR NB (also referred to as a gNB) , a remote radio unit (RRU) , a radio header (RH) , an infrastructure device for a V2X (vehicle-to-everything) communication, a transmission and reception point (TRP) , a reception point (RP) , a remote radio head (RRH) , a relay, an integrated access and backhaul (IAB) node, a low power node such as a femto BS, a pico BS, and so forth, depending on the applied terminology and technology.
[0058] As used herein, the term “terminal device” generally refers to any end device that may be capable of wireless communications. By way of example rather than a limitation, a terminal device may also be referred to as a communication device, a user equipment (UE) , an end user device, a subscriber station (SS) , an unmanned aerial vehicle (UAV) , a portable subscriber station, a mobile station (MS) , or an access terminal (AT) . The terminal device may include, but is not limited to, a mobile phone, a cellular phone, a smart phone, a voice over IP (VoIP) phone, a wireless local loop phone, a tablet, a wearable terminal device, a personal digital assistant (PDA) , a portable computer, a desktop computer, an image capture terminal device such as a digital camera, a gaming terminal device, a music storage and playback appliance, a vehicle-mounted wireless terminal device, a wireless endpoint, a mobile station, laptop-embedded equipment (LEE) , laptop-mounted equipment (LME) , a USB dongle, a smart device, wireless customer-premises equipment (CPE) , an internet of things (loT) device, a watch or other wearable, a head-mounted display (HMD) , a vehicle, a drone, a medical device (for example, a remote surgery device) , an industrial device (for example, a robot and / or other wireless devices operating in an industrial and / or an automated processing chain contexts) , a consumer electronics device, a device operating on commercial and / or industrial wireless networks, and the like. In the following description, the terms: “terminal device, ” “communication device, ” “terminal, ” “user equipment” and “UE, ” may be used interchangeably.
[0059] 3GPP is working on the study on AI / ML for beam management (BM) for reference signal (RS) overhead reduction and beam training latency reduction. Based on the evaluation results, it can be observed that AI / ML based beam prediction in spatial domain and AI / ML based beam prediction in time domain can significantly reduce the RS overhead as well as the beam management latency companied with traditional beam management procedure.
[0060] There are two typical use cases, named BM-Case1 and BM Case2, to demonstrate the potentialities of AI / ML for beam management. BM-Case1 refers to spatial domain beam prediction, where the network (NW) or UE can measure less beams in a measurement beam set B to predict the best K beams in another prediction beam set A with larger number of beams by AI / ML inference. The number of beams in set B is less than that in set A to reduce the RS overhead and beam measurement latency. BM-Case2 refers to temporal domain beam prediction, where the NW or UE can predict the best K beams for F future time instance by AI inference with the AI / ML model (s) input the past N measurement instance. One or more AI / ML models may be deployed for NW or UE side. And in Release 18, only single side AI / ML is considered for beam management use cases. AI / ML is a data driven method for inference / prediction, as a result, an AI / ML model may only be suitable for some scenarios with certain conditions. In other words, when the scenario or the condition is changed, the current AI / ML model may no longer be applicable. Performance monitoring is a key part of the life cycle management for AI / ML functionality of a UE or NW with AI / ML capability. Performance monitoring targets to monitor whether the current AI / ML models are applicable to the current scenario or channel conditions, or whether the current AI / ML models are still valid.
[0061] Based on the current discussion, Top-K transmitter (Tx) beam IDs are the basic AI / ML model output, and most companies proposed the AI / ML models can provide the predicted RSRP as well corresponding to each of the Top-K Tx Beams. Top-K Tx beams correspond to the best K beams have the best performance, e.g., have higher predicted RSRP. L1-RSRP difference by comparing measured RSRP and predicted RSRP of a same Tx beam is one of the most import metrics for performance monitoring. In some embodiments of the present application, it is assumed that the AI / ML model can provide the predicted L1-RSRP for each of the predicted Tx beam with a specific Rx beam or the L1-RSRP for a TX / RX beam pair. And it is also assumed that the AI / ML models have been trained and are ready for AI / ML inference for the NW or UE. Measurement beam set is the beam set to provide model input, which is denoted as measurement beam Set B. Prediction beam set is the beam set to provide the model output, i.e., the predicted beams of the model output are selected from prediction beam set, which is denoted as prediction beam Set A. A Tx beam is represented by a CSI-RS resource used for beam management or a system synchronization block (SSB) resource. The CSI-RS resource used for beam management has one or two ports and may be configured with repetition. A Tx beam ID is represented by a CSI-RS resource indicator (CRI) or a SSB resource indicator (SSBRI) . A Tx beam corresponds to a downlink spatial domain transmission filter. A Rx beam corresponds to a downlink spatial domain reception filter.
[0062] Some embodiments of the present application provide the detail solutions to support differential RSRP based performance monitoring for AI / ML based beam management. For UE-side AI / ML inference, we provide an enhanced beam measurement procedure to support the UE obtaining the differential RSRP for a set of predicted beams. Based on the obtained differential RSRP, the UE further determine whether to report a AI / ML Model / Functionality failure event to the NW. In detail, for the differential RSRP calculation at the UE side, the gNB configured a CSI resource configuration for a UE, wherein the CSI resource configuration contains at least one NZP CSI-RS resource set and the CSI resource configuration is associated with a CSI report configuration for beam report with AI / ML inference. The UE assumes that the CSI-RS resources in the NZP CSI-RS resource set are transmitted with the same Tx beams as the UE reported in the beam report prior to the NZP CSI-RS transmission. An L1 / L2 procedure on the AI / ML Model / Functionality failure event report was provided. For NW-side AI / ML inference, we provide an enhanced CSI report procedure for the UE to report the best L1-RSRP among all its Rx beams for certain Tx beams to the NW for the NW to do performance monitoring.
[0063] Aspects of the present disclosure are described in the context of a wireless communications system.
[0064] FIG. 1 illustrates an example of a wireless communications system 100 that supports AI / ML inference for communication in accordance with aspects of the present disclosure. The wireless communications system 100 may include one or more network entities 102 (also referred to as network equipment (NE) ) , one or more UEs 104, a core network 106, and a packet data network 108. The wireless communications system 100 may support various radio access technologies. In some implementations, the wireless communications system 100 may be a 4G network, such as an LTE network or an LTE-Advanced (LTE-A) network. In some other implementations, the wireless communications system 100 may be a 5G network, such as an NR network. In other implementations, the wireless communications system 100 may be a combination of a 4G network and a 5G network, or other suitable radio access technology including Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi) , IEEE 802.16 (WiMAX) , IEEE 802.20. The wireless communications system 100 may support radio access technologies beyond 5G. Additionally, the wireless communications system 100 may support technologies, such as time division multiple access (TDMA) , frequency division multiple access (FDMA) , or code division multiple access (CDMA) , etc.
[0065] The one or more network entities 102 may be dispersed throughout a geographic region to form the wireless communications system 100. One or more of the network entities 102 described herein may be or include or may be referred to as a network node, a base station, a network element, a radio access network (RAN) , a base transceiver station, an access point, a NodeB, an eNodeB (eNB) , a next-generation NodeB (gNB) , or other suitable terminology. A network entity 102 and a UE 104 may communicate via a communication link 110, which may be a wireless or wired connection. For example, a network entity 102 and a UE 104 may perform wireless communication (e.g., receive signaling, transmit signaling) over a Uu interface.
[0066] A network entity 102 may provide a geographic coverage area 112 for which the network entity 102 may support services (e.g., voice, video, packet data, messaging, broadcast, etc. ) for one or more UEs 104 within the geographic coverage area 112. For example, a network entity 102 and a UE 104 may support wireless communication of signals related to services (e.g., voice, video, packet data, messaging, broadcast, etc. ) according to one or multiple radio access technologies. In some implementations, a network entity 102 may be moveable, for example, a satellite associated with a non-terrestrial network. In some implementations, different geographic coverage areas 112 associated with the same or different radio access technologies may overlap, but the different geographic coverage areas 112 may be associated with different network entities 102. Information and signals described herein may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be referenced throughout the description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.
[0067] The one or more UEs 104 may be dispersed throughout a geographic region of the wireless communications system 100. A UE 104 may include or may be referred to as a mobile device, a wireless device, a remote device, a remote unit, a handheld device, or a subscriber device, or some other suitable terminology. In some implementations, the UE 104 may be referred to as a unit, a station, a terminal, or a client, among other examples. Additionally, or alternatively, the UE 104 may be referred to as an Internet-of-Things (IoT) device, an Internet-of-Everything (IoE) device, or machine-type communication (MTC) device, among other examples. In some implementations, a UE 104 may be stationary in the wireless communications system 100. In some other implementations, a UE 104 may be mobile in the wireless communications system 100.
[0068] The one or more UEs 104 may be devices in different forms or having different capabilities. Some examples of UEs 104 are illustrated in FIG. 1. A UE 104 may be capable of communicating with various types of devices, such as the network entities 102, other UEs 104, or network equipment (e.g., the core network 106, the packet data network 108, a relay device, an integrated access and backhaul (IAB) node, or another network equipment) , as shown in FIG. 1. Additionally, or alternatively, a UE 104 may support communication with other network entities 102 or UEs 104, which may act as relays in the wireless communications system 100.
[0069] A UE 104 may also be able to support wireless communication directly with other UEs 104 over a communication link 114. For example, a UE 104 may support wireless communication directly with another UE 104 over a device-to-device (D2D) communication link. In some implementations, such as vehicle-to-vehicle (V2V) deployments, vehicle-to-everything (V2X) deployments, or cellular-V2X deployments, the communication link 114 may be referred to as a sidelink. For example, a UE 104 may support wireless communication directly with another UE 104 over a PC5 interface.
[0070] A network entity 102 may support communications with the core network 106, or with another network entity 102, or both. For example, a network entity 102 may interface with the core network 106 through one or more backhaul links 116 (e.g., via an S1, N2, N2, or another network interface) . The network entities 102 may communicate with each other over the backhaul links 116 (e.g., via an X2, Xn, or another network interface) . In some implementations, the network entities 102 may communicate with each other directly (e.g., between the network entities 102) . In some other implementations, the network entities 102 may communicate with each other or indirectly (e.g., via the core network 106) . In some implementations, one or more network entities 102 may include subcomponents, such as an access network entity, which may be an example of an access node controller (ANC) . An ANC may communicate with the one or more UEs 104 through one or more other access network transmission entities, which may be referred to as a radio heads, smart radio heads, or transmission-reception points (TRPs) .
[0071] In some implementations, a network entity 102 may be configured in a disaggregated architecture, which may be configured to utilize a protocol stack physically or logically distributed among two or more network entities 102, such as an integrated access backhaul (IAB) network, an open RAN (O-RAN) (e.g., a network configuration sponsored by the O-RAN Alliance) , or a virtualized RAN (vRAN) (e.g., a cloud RAN (C-RAN) ) . For example, a network entity 102 may include one or more of a central unit (CU) , a distributed unit (DU) , a radio unit (RU) , a RAN Intelligent Controller (RIC) (e.g., a Near-Real Time RIC (Near-RT RIC) , a Non-Real Time RIC (Non-RT RIC) ) , a Service Management and Orchestration (SMO) system, or any combination thereof.
[0072] An RU may also be referred to as a radio head, a smart radio head, a remote radio head (RRH) , a remote radio unit (RRU) , or a transmission reception point (TRP) . One or more components of the network entities 102 in a disaggregated RAN architecture may be co-located, or one or more components of the network entities 102 may be located in distributed locations (e.g., separate physical locations) . In some implementations, one or more network entities 102 of a disaggregated RAN architecture may be implemented as virtual units (e.g., a virtual CU (VCU) , a virtual DU (VDU) , a virtual RU (VRU) ) .
[0073] Split of functionality between a CU, a DU, and an RU may be flexible and may support different functionalities depending upon which functions (e.g., network layer functions, protocol layer functions, baseband functions, radio frequency functions, and any combinations thereof) are performed at a CU, a DU, or an RU. For example, a functional split of a protocol stack may be employed between a CU and a DU such that the CU may support one or more layers of the protocol stack and the DU may support one or more different layers of the protocol stack. In some implementations, the CU may host upper protocol layer (e.g., a layer 3 (L3) , a layer 2 (L2) ) functionality and signaling (e.g., Radio Resource Control (RRC) , service data adaption protocol (SDAP) , Packet Data Convergence Protocol (PDCP) ) . The CU may be connected to one or more DUs or RUs, and the one or more DUs or RUs may host lower protocol layers, such as a layer 1 (L1) (e.g., physical (PHY) layer) or an L2 (e.g., radio link control (RLC) layer, medium access control (MAC) layer) functionality and signaling, and may each be at least partially controlled by the CU 160.
[0074] Additionally, or alternatively, a functional split of the protocol stack may be employed between a DU and an RU such that the DU may support one or more layers of the protocol stack and the RU may support one or more different layers of the protocol stack. The DU may support one or multiple different cells (e.g., via one or more RUs) . In some implementations, a functional split between a CU and a DU, or between a DU and an RU may be within a protocol layer (e.g., some functions for a protocol layer may be performed by one of a CU, a DU, or an RU, while other functions of the protocol layer are performed by a different one of the CU, the DU, or the RU) .
[0075] A CU may be functionally split further into CU control plane (CU-CP) and CU user plane (CU-UP) functions. A CU may be connected to one or more DUs via a midhaul communication link (e.g., F1, F1-c, F1-u) , and a DU may be connected to one or more RUs via a fronthaul communication link (e.g., open fronthaul (FH) interface) . In some implementations, a midhaul communication link or a fronthaul communication link may be implemented in accordance with an interface (e.g., a channel) between layers of a protocol stack supported by respective network entities 102 that are in communication via such communication links.
[0076] The core network 106 may support user authentication, access authorization, tracking, connectivity, and other access, routing, or mobility functions. The core network 106 may be an evolved packet core (EPC) , or a 5G core (5GC) , which may include a control plane entity that manages access and mobility (e.g., a mobility management entity (MME) , an access and mobility management functions (AMF) ) and a user plane entity that routes packets or interconnects to external networks (e.g., a serving gateway (S-GW) , a Packet Data Network (PDN) gateway (P-GW) , or a user plane function (UPF) ) . In some implementations, the control plane entity may manage non-access stratum (NAS) functions, such as mobility, authentication, and bearer management (e.g., data bearers, signal bearers, etc. ) for the one or more UEs 104 served by the one or more network entities 102 associated with the core network 106.
[0077] The core network 106 may communicate with the packet data network 108 over one or more backhaul links 116 (e.g., via an S1, N2, N2, or another network interface) . The packet data network 108 may include an application server 118. In some implementations, one or more UEs 104 may communicate with the application server 118. A UE 104 may establish a session (e.g., a protocol data unit (PDU) session, or the like) with the core network 106 via a network entity 102. The core network 106 may route traffic (e.g., control information, data, and the like) between the UE 104 and the application server 118 using the established session (e.g., the established PDU session) . The PDU session may be an example of a logical connection between the UE 104 and the core network 106 (e.g., one or more network functions of the core network 106) .
[0078] In the wireless communications system 100, the network entities 102 and the UEs 104 may use resources of the wireless communications system 100 (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers) ) to perform various operations (e.g., wireless communications) . In some implementations, the network entities 102 and the UEs 104 may support different resource structures. For example, the network entities 102 and the UEs 104 may support different frame structures. In some implementations, such as in 4G, the network entities 102 and the UEs 104 may support a single frame structure. In some other implementations, such as in 5G and among other suitable radio access technologies, the network entities 102 and the UEs 104 may support various frame structures (i.e., multiple frame structures) . The network entities 102 and the UEs 104 may support various frame structures based on one or more numerologies.
[0079] One or more numerologies may be supported in the wireless communications system 100, and a numerology may include a subcarrier spacing and a cyclic prefix. A first numerology (e.g., μ=0) may be associated with a first subcarrier spacing (e.g., 15 kHz) and a normal cyclic prefix. In some implementations, the first numerology (e.g., μ=0) associated with the first subcarrier spacing (e.g., 15 kHz) may utilize one slot per subframe. A second numerology (e.g., μ=1) may be associated with a second subcarrier spacing (e.g., 30 kHz) and a normal cyclic prefix. A third numerology (e.g., μ=2) may be associated with a third subcarrier spacing (e.g., 60 kHz) and a normal cyclic prefix or an extended cyclic prefix. A fourth numerology (e.g., μ=3) may be associated with a fourth subcarrier spacing (e.g., 120 kHz) and a normal cyclic prefix. A fifth numerology (e.g., μ=4) may be associated with a fifth subcarrier spacing (e.g., 240 kHz) and a normal cyclic prefix.
[0080] A time interval of a resource (e.g., a communication resource) may be organized according to frames (also referred to as radio frames) . Each frame may have a duration, for example, a 10 millisecond (ms) duration. In some implementations, each frame may include multiple subframes. For example, each frame may include 10 subframes, and each subframe may have a duration, for example, a 1 ms duration. In some implementations, each frame may have the same duration. In some implementations, each subframe of a frame may have the same duration.
[0081] Additionally or alternatively, a time interval of a resource (e.g., a communication resource) may be organized according to slots. For example, a subframe may include a number (e.g., quantity) of slots. The number of slots in each subframe may also depend on the one or more numerologies supported in the wireless communications system 100. For instance, the first, second, third, fourth, and fifth numerologies (i.e., μ=0, μ=1, μ=2, μ=3, μ=4) associated with respective subcarrier spacings of 15 kHz, 30 kHz, 60 kHz, 120 kHz, and 240 kHz may utilize a single slot per subframe, two slots per subframe, four slots per subframe, eight slots per subframe, and 16 slots per subframe, respectively. Each slot may include a number (e.g., quantity) of symbols (e.g., OFDM symbols) . In some implementations, the number (e.g., quantity) of slots for a subframe may depend on a numerology. For a normal cyclic prefix, a slot may include 14 symbols. For an extended cyclic prefix (e.g., applicable for 60 kHz subcarrier spacing) , a slot may include 12 symbols. The relationship between the number of symbols per slot, the number of slots per subframe, and the number of slots per frame for a normal cyclic prefix and an extended cyclic prefix may depend on a numerology. It should be understood that reference to a first numerology (e.g., μ=0) associated with a first subcarrier spacing (e.g., 15 kHz) may be used interchangeably between subframes and slots.
[0082] In the wireless communications system 100, an electromagnetic (EM) spectrum may be split, based on frequency or wavelength, into various classes, frequency bands, frequency channels, etc. By way of example, the wireless communications system 100 may support one or multiple operating frequency bands, such as frequency range designations FR1 (410 MHz –7.125 GHz) , FR2 (24.25 GHz –52.6 GHz) , FR3 (7.125 GHz –24.25 GHz) , FR4 (52.6 GHz –114.25 GHz) , FR4a or FR4-1 (52.6 GHz –71 GHz) , and FR5 (114.25 GHz –300 GHz) .
[0083] In some implementations, the network entities 102 and the UEs 104 may perform wireless communications over one or more of the operating frequency bands. In some implementations, FR1 may be used by the network entities 102 and the UEs 104, among other equipment or devices for cellular communications traffic (e.g., control information, data) . In some implementations, FR2 may be used by the network entities 102 and the UEs 104, among other equipment or devices for short-range, high data rate capabilities.
[0084] FR1 may be associated with one or multiple numerologies (e.g., at least three numerologies) . For example, FR1 may be associated with a first numerology (e.g., μ=0) , which includes 15 kHz subcarrier spacing; a second numerology (e.g., μ=1) , which includes 30 kHz subcarrier spacing; and a third numerology (e.g., μ=2) , which includes 60 kHz subcarrier spacing. FR2 may be associated with one or multiple numerologies (e.g., at least 2 numerologies) . For example, FR2 may be associated with a third numerology (e.g., μ=2) , which includes 60 kHz subcarrier spacing; and a fourth numerology (e.g., μ=3) , which includes 120 kHz subcarrier spacing.
[0085] FIG. 2 illustrates an example of signaling flow that supports AI / ML inference for communication in accordance with aspects of the present disclosure. As shown in FIG. 2, the UE 104 receives 203 configuration on a resource setting 202 from base station 102. The configuration on a resource setting contains one or more NZP CSI-RS resource sets for an operation of the UE 104 associated with an AI / ML model or an AI / ML functionality deployed at the UE 104. In addition, if UE 104 determines a failure event based on differential RSRP based performance monitoring for the AI / ML model or the AI / ML functionality, the UE 104 transmits 204 the indication of the failure event to the base station 102. In this way, based on the obtained differential RSRP, the UE 104 can determine whether to report an AI / ML Model / Functionality failure event to the base station 102.
[0086] In some embodiments, UE 104 obtains the average differential RSRP for a set of predicted beams. Based on the obtained average differential RSRP, the UE 104 can further determine whether to report an AI / ML Model / Functionality failure event to the NW.
[0087] FIG. 3 illustrates an example of a procedure that supports AI / ML inference for communication in accordance with aspects of the present disclosure. As shown in FIG. 3, for UE-side AI / ML model inference, the UE 104 performs beam measurement on beams in Set B to obtain the model input for AI / ML inference. Then the AI / ML model can predict the L1-RSRP for all the beam pairs for beam in Set A and report the Top-K Tx beams and corresponding predicted L1-RSRP to the base station 102 according to the base station 102 configuration. In some embodiments of the present application, the UE 104 calculates the differential RSRP between predicted RSRP and the actual / measured RSRP of the same beam pair, and determine whether to report an event report to the base station 102 to tell the base station 102 that the current AI / ML Model / Functionality are inapplicable for the current situation.
[0088] The UE 104 may receive a CSI reporting configuration with the operation of AI / ML associated with the NZP CSI-RS resource configuration. And UE 104 transmits to the base station a beam report corresponding to the CSI reporting configuration. And the beam report indicates a number of Tx beams and corresponding predicted L1-RSRP. Then UE 104 receives from the base station transmission on NZP CSI-RS resource corresponding to the number of Tx beams by receive beams corresponding to each of the Tx beams.
[0089] As shown in FIG. 3, first, the base station 102 provides Set B beam transmission for the UE 104 at 302, and UE 104 obtains the model input for AI / ML inference at 304. In addition, UE 104 performs AI / ML inference to predict top-K beams from Set A and report them to the base station 102. Then the base station 102 prepare Tx beams for performance monitoring at 306, and transmits a set of beams with the same Tx beams reported by the UE 104 to the UE 104 at 308. The UE 104 measure the beams transmitted by the base station 102 with the RX beam corresponding to the predicted RSRP and further calculate the differential RSRP for a same predicted beam pair at 310. The differential RSRP for a same beam pair is defined as the absolute value of the predicted RSRP –the measured RSRP. When multiple beams are predicted and reported, the UE shall calculate the average differential RSRP of those beam pairs. Based on the average differential RSRP to determine whether to report an AI / ML Model / Functionality failure event to the base station 102 at 312. With the received event, the base station 102 decides to do AI / ML model switching or fallback at 314, and indicates the UE 104 to perform Model / Functionality switch or fallback to non-AI operation at 316. Then the UE 104 switch AL / ML model / functionality or fallback to non-AI operation at 318.
[0090] FIG. 4 illustrates an example of transmission for performance monitoring for AI / ML inference in accordance with aspects of the present disclosure. In some embodiments, the resource setting configuration indicates one set of NZP CSI-RS resource, a first NZP CSI-RS at first position of the set of NZP CSI-RS is assumed to be transmitted by a first transmit beam at a first position of the set of Tx beams indicated in the associated beam report, and a second NZP CSI-RS at second position of the set of NZP CSI-RS resource is assumed to be transmitted by a second Tx beam at a second position of the set of Tx beams indicated in the associated beam report, and so on.
[0091] In order to obtain the actual L1-RSRP of the same TX-RX beam pair predicted by UE-side AI / ML models, the base station 102 can perform the transmission with a set of beams with the same Tx beams reported by the UE 104, i.e., transmit a set of CSI-RS resources with the Tx beam determined by the reported CRI or SSBRI in the beam report. The Tx beam determined by a CRI or a SSBRI means that the base station 102 transmit a DL signal with the same DL spatial transmit filter that is used for the transmission of the CSI-RS resource corresponding to the CRI or the transmission of the SSB resource corresponding to the SSBRI. The base station 102 configures a NZP CSI-RS resource set transmission associated with a beam report configuration with AI / ML inference. And the UE 104 assumes the beams, i.e., the NZP CSI-RS resources, in the beam set are transmitted with the same Tx beam as the latest beams reported by the UE 104 in the associated beam report.
[0092] As shown in FIG. 4, a UE 104 is configured with a periodic beam report#n (402, 408, 410, 416, 418, 424, 426, 432) corresponding to a CSI-ReportConfig#n associated with a AI / ML model / functionality for spatial domain beam prediction, and the UE 104 will reports the predicted Tx beams in T1, T2, …, T8, …Further, the UE 104 is configured with a periodic beam transmission corresponding to a CSI-ResourceConfig#m (m=406, 414, 422, or 430) and CSI-ResourceConfig#m is associated with CSI-ReportConfig#n. The UE 104 will receive the beams in S1, S2, S3, S4, …The CSI-RS resources does not expect to be configured with qcl-Info or TCI state, which is used to indicate a DL Rx beam for the CSI-RS resource, or the UE 104 may ignore the qcl-Info or TCI state configured for each of the CSI-RS resource.
[0093] With the association, the UE 104 can assume that the NZP CSI-RS resources corresponding to CSI-ResourceConfig#m are transmitted with the same Tx beams reported by the UE 104 in the latest beam report corresponding to CSI-ReportConfig#n before each of the NZP CSI-RS resource set transmission. For example, the CSI-ResourceConfig#m configures a NZP CSI-RS resource set containing 4 NZP CSI-RS resources, e.g., NZP CSI-RS resources#0, NZP CSI-RS resources#1, NZP CSI-RS resources#2, NZP CSI-RS resources#3. The UE 104 is configured to report 4 beams, i.e., CRI#0, CRI#1, CRI#2 and CRI#3, in each beam report corresponding to CSI-ReportConfig#n. The UE 104 assumes NZP CSI-RS resources#0, NZP CSI-RS resources#1, NZP CSI-RS resources#2, NZP CSI-RS resources#3 transmitted in S1 are transmitted with the same Tx beam as the beams corresponding to CRI#0, CRI#1, CRI#2 and CRI#3 report in T1. And the UE 104 assumes NZP CSI-RS resources#0, NZP CSI-RS resources#1, NZP CSI-RS resources#2, NZP CSI-RS resources#3 transmitted in S2 are transmitted with the same Tx beam as the beams corresponding to CRI#0, CRI#1, CRI#2 and CRI#3 report in T3; and so on.
[0094] With the received NZP CSI-RS resources corresponding to CSI-ResourceConfig#m, the UE 104 calculates the different RSRP between the actual RSRP and the predicted RSRP of each of the same Tx-Rx beam pair to determine whether to report an AI / ML failure event based on the average differential RSRP of the for beams.
[0095] In some embodiments, the beam report is transmitted in a first set of symbol (s) , the transmission on the NZP CSI-RS resource (s) is received in a second set of symbol (s) , and the duration between the last symbol of the first set of symbol (s) and the first symbol of the second set of symbol (s) is larger than a first threshold for the NW to prepare the Tx beams for the transmission on the NZP CSI-RS resource (s) . A minimal time gap (404, 412, 420, 428) may be required for the base station 102 to determine the Tx beam for each of the NZP CSI-RS resources as shown in FIG. 4.
[0096] In some example implementations, the UE 104 transmits to the base station an aperiodic beam transmission request for performance monitoring in a beam report associated with AI / ML operation. Semi-persistent and aperiodic CSI-RS transmission can also be supported for performance monitoring by associated with a CSI report for beam report associated with a AI / ML model / functionality. Considering that the UE 104 performs the AI / ML inference and the UE may know the AI / ML model / functionality may not be suitable in advance, e.g., based on the predicted RSRP and the measured SINR based on CSI-RS resources for CSI acquisition for CQI report. It is better to support UE 104 initials a beam measurement procedure to obtain the actual RSRP of certain Tx beams. This feature can be implemented by introduce additional field in each beam report associated with AI / ML models / functionality. The NZP CSI-RS resources corresponding to the CSI resource configuration associated with this CSI report configuration are only transmitted when the UE 104 sends a request in the beam report. For example, an aperiodic CSI resource transmission can be triggered when the UE 104 reports a request for beam measurement in a beam report.
[0097] The NZP CSI-RS resource (s) in the resource setting configuration is periodic in the case that the CSI report is a periodic CSI report. Moreover, the NZP CSI-RS resource (s) in the resource setting configuration can be a semi-persistent in the case that the CSI report is one of a semi-persistent CSI report, or a periodic CSI report. In addition, the NZP CSI-RS resource (s) in the resource setting configuration can be aperiodic in the case that the CSI report is a semi-persistent CSI report, a periodic CSI report, or an aperiodic CSI report. The supported combination of CSI-RS Resource configuration and CSI Reporting configuration is shown in Table 1.
[0098] Table 1
[0099] FIG. 5 illustrates an example of transmission for performance monitoring for AI / ML inference in accordance with aspects of the present disclosure. For the case that aperiodic CSI-RS transmission associated with an aperiodic CSI reporting for performance, multiple time requirement may need to be satisfied. An illustration the time requirement for the target case is provided in FIG. 5.
[0100] The triggering DCI 502 triggers set B beam transmission 504 and beam report 506 with AI / ML inference and aperiodic NZP CSI-RS transmission 508 for performance monitoring. The following time requirement may need to be satisfied.
[0101] Tproc, CSI, AI 510 is the minimal time requirement for the UE 104 to report an aperiodic beam report with AI / ML inference after receiving a triggering DCI, which is defined as the next UL symbol with its CP starting Tproc, CSI, AI after the end of the last symbol of the PDCCH triggering the CSI report containing beam report with AI inference.
[0102] T’proc, CSI, AI 512 is the minimal time requirement for the UE 104 to obtain the required beam report after received a set of beams for AI / ML model input, which is defined as the next UL symbol with its CP starting Tproc, CSI, AI after the end of the last symbol in time of aperiodic CSI-RS for channel measurement when aperiodic CSI-RS is used for channel measurement for the triggered CSI report.
[0103] Tproc, AI_Monitor 514 is the minimal time requirement for the base station 102 to prepare the Tx beams for each of the aperiodic CSI-RS resources after receiving the beam report, which is defined as the next DL symbol with its CP starting Tproc, AI_Monitor after the end of the last symbol of the PUSCH carry the beam report.
[0104] For temporal domain prediction, the UE 104 may predict the Top-K Tx beams for F future time instance and report the prediction results to the base station 102 in a beam report. For this case, the base station 102 can transmit NZP CSI-RS resources in each of the F future time instance for the UE 104 to obtain the actual RSRP. The mechanism for spatial domain beam prediction can be reused.
[0105] In some scenarios, an AI / ML model failure instance or an AI / ML functionality failure instance is determined in the case that average differential RSRP of all beams in the set of Tx beams is worse than a second threshold. Based on the obtained difference RSRP for a set of beam pairs, the UE 104 may determine whether the current AI / ML model / functionalities are applicable. Beam Failure Recovery-like procedure can be designed for this purpose. AI / ML Model / functionality failure (AMFF) is detected by counting AI / ML model / functionality failure instance indication from the lower layers to the MAC entity.
[0106] The base station 102 can configure the following parameters for AMFF report: differential-RSRP threshold, a differential RSRP threshold for AMFF indication, aiFunctionalityFailureTimer for AI / ML model / functionality failure detection, aiFunctionalityFailureInstanceMaxCount for the AI / ML model / functionality failure detection, AMFFI_COUNTER which is counter for AI / ML Model / Functionality failure instance indication which is initially set to 0.
[0107] The physical layer in the UE 104 assesses the average differential RSRP for some pairs of Tx-Rx beam pairs against the threshold differential-RSRP threshold. If the average differential RSRP of all beams in a NZP CSI-RS resource set associated with a CSI reporting configuration associated with AI / ML Model / Functionality are worse than the differential-RSRP threshold, the physical layer informs the higher layer an AI / ML Model / Functionality failure instance.
[0108] In some situations, UE 104 determines the failure event of the AI / ML model or the AI / ML functionality in the case that a number of the AI / ML model failure instances or the AI / ML functionality failure instances during a period is greater than a third threshold. The MAC entity of UE 104 may perform following procedures. If AI / ML Model / Functionality failure indication has been received from lower layers, start or restart aiFunctionalityFailureTimer, increment AMFFI_COUNTER by 1. If AMFFI_COUNTER>=aiFunctionalityFailureInstanceMaxCount, trigger an AI / ML model / functionality failure report. If the aiFunctionalityFailureTimer expires, set AMFFI_COUNTER =0.
[0109] In some embodiments, the failure event of the AI / ML model or the AI / ML functionality comprises at least a measured L1-RSRP of each of the beams in the latest set of NZP CSI-RS resource for performance monitoring, or whether there is another AI / ML model or functionality applicable to a current scenario or condition, or a recommended AI / ML model or functionality. MAC CE based AMFF report comprises: a dedicated Scheduling Request resource is configured for the UE for AMFF MAC CE report when there is no available UL-SCH resource for the AMFF MAC CE transmission. In the AMFF MAC CE, the UE may report the following information, the actual L1-RSRP of the beams in the latest NZP CSI-RS resource set for performance monitoring, whether there is another AI / ML Model or Functionality applicable to the current scenario / conditions, a recommended AI / ML Model for Functionality, if possible. Based on the received AMFF MAC CE, the base station 102 can indicate the UE 104 to switch to another AI / ML Model or Functionality or fall back to non-AI / ML operation.
[0110] FIG. 6 illustrates an example of a procedure that supports AI / ML inference for communication in accordance with aspects of the present disclosure. In some embodiments, UE 104 receives from the base station 102 a CSI reporting configuration associated with the resource setting configuration, the NZP CSI-RS resources in the NZP CSI-RS resource set for the resource setting is configured with a parameter of repetition. The UE 104 transmits to the base station a beam report corresponding to the CSI reporting configuration. And the beam report comprises a set of beams and a corresponding measured L1-RSRP.
[0111] As shown in FIG. 6, for NW-side AI / ML models inference, the UE 104 can perform beam measurement and beam report on beam set B according to base station 102 configuration / indication to provide the model input for AI / ML inference deployed at the base station 102 side at 602. With the model input, the AI / ML models can predict the L1-RSRP for each of the beams in beam Set A with a certain Rx beam, and then output the top-K Tx beam IDs and the corresponding predicted L1-RSRP from beam Set A. To support the performance monitoring on the NW-side AI / ML models, the base station 102 needs to obtain the actual or the measured L1-RSRP of the same Tx obtained by the AI / ML models. The base station 102 can configure or trigger a beam measurement and beam report procedure on the predicted Tx beams. Then UE 104 performs beam measurement and report on the transmitted beams for performance monitoring at 604.
[0112] In order to obtain the L1-RSRP corresponding to a TX beam, the following two options are considered on the Rx beam assumption. The option 1 is that the predicted L1-RSRP is obtained with a specific Rx beam. The option 2 is that the predicted L1-RSRP is obtained among all the Rx beams of the UE 104.
[0113] For option 1, the base station 102 can configure a beam report, i.e., by configure a CSI-ReportConfig, associated with a beam set, where the beam set K beams and the beams are transmitted with the top-K Tx beams obtained by the AI / ML inference and each beam is configured a same qcl-info or a same TCI state for the UE 104 to determine the specific RX beam to obtain the measured RSRP for each Tx beam. This procedure can be supported based on Rel-17 beam management procedure.
[0114] For option 2, the base station 102 may repeat the same Tx beams for the UE 104 to sweep its Rx beams to obtain the best L1-RSRP among all its Rx beams. For example, if the UE 104 has 4 Rx beams, then the beams associated with the beam report configuration may be repeated 4 times. The CSI-RS repetition mechanism where an NZP-CSI-RS resource set is configured with higher layer parameter repetition set as ‘on’ and the UE 104 assumes the NZP CSI-RS resources within the set are transmitted by a same Tx beam, can be enhanced to support this feature.
[0115] In some embodiments, the CSI-RS resources does not expect to be configured with qcl-Info or TCI state, or the UE 104 can ignore the qcl-Info or TCI state configured for each of the CSI-RS resource.
[0116] In some cases, the beams may be repeated per resource. For example, introduce a RRC parameters repetitionNumber for each NZP CSI-RS resource configured in a CSI resource set. Each NZP CSI-RS resource will be transmitted repetitionNumber times with the same Tx beams in repetitionNumber continuous or available symbols. The UE 104 can report the best L1-RSRP for each CSI-RS resource among all the repetitionNumber receptions.
[0117] In some embodiments, a UE 104 is configured with a CSI-ReportConfig for beam report for performance monitoring and the CSI-ReportConfig is associated with a CSI Resource Setting as the channel measurement resource (CMR) for beam measurement.
[0118] In some other embodiments, the CMR contains a NZP CSI-RS resource set containing K NZP CSI-RS resources, e.g., NZP CSI-RS resource set#0= {NZP CSI-RS resource #0, NZP CSI-RS resource#1, …, NZP CSI-RS resource#K-1} . The NZP CSI-RS resource set or each of the NZP CSI-RS resource is configured with a new RRC parameter repetitionNumber to indicate the repetition number of each NZP CSI-RS resource. The UE 104 assumes that all the repetition of each NZP CSI-RS resource are transmitted by a same Tx beam. If the repetitionNumber is set as 4, the resulted CSI-RS transmission pattern is as follows: NZP CSI-RS resource #0, NZP CSI-RS resource #0, NZP CSI-RS resource #0, NZP CSI-RS resource #0, NZP CSI-RS resource #1, NZP CSI-RS resource #1, NZP CSI-RS resource #1, NZP CSI-RS resource #1, …, NZP CSI-RS resource #K-1, NZP CSI-RS resource #K-1, NZP CSI-RS resource #K-1, NZP CSI-RS resource #K-1.
[0119] In some further embodiments, the resource setting containing a NZP CSI-RS resource set, and a transmission on an NZP CSI-RS resource in the NZP CSI-RS resource set is transmitted with a configured repetition times in a same number of the valid symbols. All repetitions of a same CSI-RS resource are transmitted in the repetitionNumber continuous OFDM symbols, if all the repetitions of all the CSI-RS resources cannot be transmitted in a same slot, e.g., K=4, repetitionNumber=4. They are expected to be transmitted in continuous slots. For the above example, NZP CSI-RS resource #0 and NZP CSI-RS resource #1 are transmitted in a first slot, and NZP CSI-RS resource #2 and NZP CSI-RS resource #3 are transmitted in the next slot, and so on.
[0120] In some examples, the base station 102 further indicate the UE 104 to report K beams with corresponding L1-RSRP of each beam, by configure reportQuantity=cri-RSRP and nrofReportedRS=K. The UE 104 may report the best RSRP of each CSI-RS resource among all the repetitions. An example report format is as follows:
[0121] Table 2
[0122] The NZP CSI-RS resource configuration may be an NZP CSI-RS resource groups configuration, transmissions on NZP CSI-RS resources in the same NZP CSI-RS resource group are transmitted by a same Tx beam, and transmissions on NZP CSI-RS resources in different NZP CSI-RS resource groups are transmitted by different Tx beams.
[0123] In some other examples, the beams can be repeated per resource set. For example, a beam report can be associated with multiple beam sets or a beam set with multiple beam groups. Each beam set or a beam group in a beam set is configured with a RRC parameter repetition set as ‘on’ to tell the UE 104 that all beams in the beam set or beam group are transmitted by a same Tx beam.
[0124] In some implementations, the CMR contains a NZP CSI-RS resource set containing K NZP CSI-RS resource group. Each NZP CSI-RS resource group contains N NZP CSI-RS resources, and each NZP CSI-RS resource group or the NZP CSI-RS resource set is configured with repetition set to ‘on’ . The UE 104 may assume that all NZP CSI-RS resources in a same NZP CSI-RS resource group are transmitted by a same Tx beam and the UE 104 may sweep its RX beams to obtain L1-RSRP corresponding to each RX beams. For example, the CMR can be configured as: NZP CSI-RS resource set#0= {resource group#0= [NZP CSI-RS resource#0, NZP CSI-RS resource#1, NZP CSI-RS resource#2, NZP CSI-RS resource#3] , resource group#1= [NZP CSI-RS resource#4, NZP CSI-RS resource#5, NZP CSI-RS resource#6, NZP CSI-RS resource#7] , …, resource group #K= [NZP CSI-RS resource#NK-4, NZP CSI-RS resource#NK-3, NZP CSI-RS resource#NK-2, NZP CSI-RS resource#NK-1] } .
[0125] A first beam at a first position of the set of beams may correspond to Tx beams used for a first NZP CSI resource group of the NZP CSI-RS resource groups configuration, the corresponding L1-RSRP is the highest L1-RSRP corresponding to the first beam among the receive beams of the UE, a second beam at a second position of the set of beams corresponds to Tx beams used for a second NZP CSI resource group of the NZP CSI-RS resource groups configuration, and the corresponding L1-RSRP is the highest L1-RSRP corresponding to the second beam among the receive beams of the UE. The UE 104 can assume that the NZP CSI-RS resources in each resource group are transmitted by a same TX beam and the UE 104 can receive each of the NZP CSI-RS resource in a group with different RX beam to obtain corresponding L1-RSRP and take the best one for L1-RSRP report for the beam in a resource group.
[0126] The base station 102 can indicate the UE 104 to report K beams with corresponding L1-RSRP of each beam, by configure reportQuantity=cri-RSRP and nrofReportedRS=K. The UE 104 may report the best RSRP of a CSI-RS resource among all the NZP CSI-RS resources in a resource group. An example report format is as follows:
[0127] Table 3
[0128] The differential RSRP is defined as the difference between the best RSRP of each resource group and the largest RSRP corresponding to the indicated CRI. With the received L1-RSRPs for the certain Tx beams (i.e., NZP CSI-RS resources) , the base station 102 may calculate the differential RSRP between the reported L1-RSRP and the predicted L1-RSRP for a same Tx beam to determine whether the current AI / ML Model / Functionality are applicable for the current situation.
[0129] FIG. 7 illustrates an example of a device that supports AI / ML inference for communication in accordance with aspects of the present disclosure. The device 700 may be an example of the UE 104 as described herein. The device 700 may support wireless communication with one or more network entities 102, UEs 104, or any combination thereof. The device 700 may include components for bi-directional communications including components for transmitting and receiving communications, such as a processor 702, a memory 704, a transceiver 706, and, optionally, an I / O controller 708. These components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g., buses) .
[0130] The processor 702, the memory 704, the transceiver 706, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as described herein. For example, the processor 702, the memory 704, the transceiver 706, or various combinations or components thereof may support a method for performing one or more of the operations described herein.
[0131] In some implementations, the processor 702, the memory 704, the transceiver 706, or various combinations or components thereof may be implemented in hardware (e.g., in communications management circuitry) . The hardware may include a processor, a digital signal processor (DSP) , an application-specific integrated circuit (ASIC) , a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic, discrete hardware components, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure. In some implementations, the processor 702 and the memory 704 coupled with the processor 702 may be configured to perform one or more of the functions described herein (e.g., executing, by the processor 702, instructions stored in the memory 704) .
[0132] For example, the processor 702 may support wireless communication at the device 700 in accordance with examples as disclosed herein. The processor 702 may be configured to operable to support a means for receiving, from a base station via the transceiver, a configuration on a resource setting containing one or more non-zero power channel state information reference signal (NZP CSI-RS) resource sets for an operation of the UE associated with an artificial intelligence (AI) / machine learning (ML) model or an AI / ML functionality; and transmitting, to the base station via the transceiver, an indication for a failure event of the AI / ML model or the AI / ML functionality in the case that the UE determines the failure event based on differential reference signal receiving power (RSRP) based performance monitoring for the AI / ML model or the AI / ML functionality.
[0133] The processor 702 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, a microcontroller, an ASIC, an FPGA, a programmable logic device, a discrete gate or transistor logic component, a discrete hardware component, or any combination thereof) . In some implementations, the processor 702 may be configured to operate a memory array using a memory controller. In some other implementations, a memory controller may be integrated into the processor 702. The processor 702 may be configured to execute computer-readable instructions stored in a memory (e.g., the memory 704) to cause the device 700 to perform various functions of the present disclosure.
[0134] The memory 704 may include random access memory (RAM) and read-only memory (ROM) . The memory 704 may store computer-readable, computer-executable code including instructions that, when executed by the processor 702 cause the device 700 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. In some implementations, the code may not be directly executable by the processor 702 but may cause a computer (e.g., when compiled and executed) to perform functions described herein. In some implementations, the memory 704 may include, among other things, a basic I / O system (BIOS) which may control basic hardware or software operation such as the interaction with peripheral components or devices.
[0135] The I / O controller 708 may manage input and output signals for the device 700. The I / O controller 708 may also manage peripherals not integrated into the device M02. In some implementations, the I / O controller 708 may represent a physical connection or port to an external peripheral. In some implementations, the I / O controller 708 may utilize an operating system such as or another known operating system. In some implementations, the I / O controller 708 may be implemented as part of a processor, such as the processor 706. In some implementations, a user may interact with the device 700 via the I / O controller 708 or via hardware components controlled by the I / O controller 708.
[0136] In some implementations, the device 700 may include a single antenna 710. However, in some other implementations, the device 700 may have more than one antenna 710 (i.e., multiple antennas) , including multiple antenna panels or antenna arrays, which may be capable of concurrently transmitting or receiving multiple wireless transmissions. The transceiver 706 may communicate bi-directionally, via the one or more antennas 710, wired, or wireless links as described herein. For example, the transceiver 706 may represent a wireless transceiver and may communicate bi-directionally with another wireless transceiver. The transceiver 706 may also include a modem to modulate the packets, to provide the modulated packets to one or more antennas 710 for transmission, and to demodulate packets received from the one or more antennas 710. The transceiver 706 may include one or more transmit chains, one or more receive chains, or a combination thereof.
[0137] A transmit chain may be configured to generate and transmit signals (e.g., control information, data, packets) . The transmit chain may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM) , frequency modulation (FM) , or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM) . The transmit chain may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmit chain may also include one or more antennas 710 for transmitting the amplified signal into the air or wireless medium.
[0138] A receive chain may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receive chain may include one or more antennas 710 for receive the signal over the air or wireless medium. The receive chain may include at least one amplifier (e.g., a low-noise amplifier (LNA) ) configured to amplify the received signal. The receive chain may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receive chain may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.
[0139] FIG. 8 illustrates an example of a device that supports AI / ML inference for communication in accordance with aspects of the present disclosure. The device 800 may be an example of the base station 102 as described herein. The device 800 may support wireless communication with one or more network entities 102, UEs 104, or any combination thereof. The device 800 may include components for bi-directional communications including components for transmitting and receiving communications, such as a processor 802, a memory 804, a transceiver 806, and, optionally, an I / O controller 808. These components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g., buses) .
[0140] The processor 802, the memory 804, the transceiver 806, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as described herein. For example, the processor 802, the memory 804, the transceiver 806, or various combinations or components thereof may support a method for performing one or more of the operations described herein.
[0141] In some implementations, the processor 802, the memory 804, the transceiver 806, or various combinations or components thereof may be implemented in hardware (e.g., in communications management circuitry) . The hardware may include a processor, a digital signal processor (DSP) , an application-specific integrated circuit (ASIC) , a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic, discrete hardware components, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure. In some implementations, the processor 802 and the memory 804 coupled with the processor 802 may be configured to perform one or more of the functions described herein (e.g., executing, by the processor 802, instructions stored in the memory 804) .
[0142] For example, the processor 802 may support wireless communication at the device 800 in accordance with examples as disclosed herein. The processor 802 may be configured to operable to support a means for transmitting, to a user equipment (UE) via the transceiver, a configuration on a resource setting containing one or more non-zero power channel state information reference signal (NZP CSI-RS) resource sets for an operation of the UE associated with an artificial intelligence (AI) / machine learning (ML) model or an AI / ML functionality; and receiving, from the UE via the transceiver, an indication for a failure event of the AI / ML model or the AI / ML functionality in the case that the UE determines the failure event based on differential reference signal receiving power (RSRP) based performance monitoring for the AI / ML model or the AI / ML functionality.
[0143] The processor 802 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, a microcontroller, an ASIC, an FPGA, a programmable logic device, a discrete gate or transistor logic component, a discrete hardware component, or any combination thereof) . In some implementations, the processor 802 may be configured to operate a memory array using a memory controller. In some other implementations, a memory controller may be integrated into the processor 802. The processor 802 may be configured to execute computer-readable instructions stored in a memory (e.g., the memory 804) to cause the device 800 to perform various functions of the present disclosure.
[0144] The memory 804 may include random access memory (RAM) and read-only memory (ROM) . The memory 804 may store computer-readable, computer-executable code including instructions that, when executed by the processor 802 cause the device 800 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. In some implementations, the code may not be directly executable by the processor 802 but may cause a computer (e.g., when compiled and executed) to perform functions described herein. In some implementations, the memory 804 may include, among other things, a basic I / O system (BIOS) which may control basic hardware or software operation such as the interaction with peripheral components or devices.
[0145] The I / O controller 808 may manage input and output signals for the device 800. The I / O controller 808 may also manage peripherals not integrated into the device M02. In some implementations, the I / O controller 808 may represent a physical connection or port to an external peripheral. In some implementations, the I / O controller 808 may utilize an operating system such as or another known operating system. In some implementations, the I / O controller 808 may be implemented as part of a processor, such as the processor 806. In some implementations, a user may interact with the device 800 via the I / O controller 808 or via hardware components controlled by the I / O controller 808.
[0146] In some implementations, the device 800 may include a single antenna 810. However, in some other implementations, the device 800 may have more than one antenna 810 (i.e., multiple antennas) , including multiple antenna panels or antenna arrays, which may be capable of concurrently transmitting or receiving multiple wireless transmissions. The transceiver 806 may communicate bi-directionally, via the one or more antennas 810, wired, or wireless links as described herein. For example, the transceiver 806 may represent a wireless transceiver and may communicate bi-directionally with another wireless transceiver. The transceiver 806 may also include a modem to modulate the packets, to provide the modulated packets to one or more antennas 810 for transmission, and to demodulate packets received from the one or more antennas 810. The transceiver 806 may include one or more transmit chains, one or more receive chains, or a combination thereof.
[0147] A transmit chain may be configured to generate and transmit signals (e.g., control information, data, packets) . The transmit chain may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM) , frequency modulation (FM) , or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM) . The transmit chain may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmit chain may also include one or more antennas 810 for transmitting the amplified signal into the air or wireless medium.
[0148] A receive chain may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receive chain may include one or more antennas 810 for receive the signal over the air or wireless medium. The receive chain may include at least one amplifier (e.g., a low-noise amplifier (LNA) ) configured to amplify the received signal. The receive chain may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receive chain may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.
[0149] FIG. 9 illustrates an example of a processor that supports AI / ML inference for communication in accordance with aspects of the present disclosure. The processor 900 may be an example of a processor configured to perform various operations in accordance with examples as described herein. The processor 900 may include a controller 902 configured to perform various operations in accordance with examples as described herein. The processor 900 may optionally include at least one memory 904. Additionally, or alternatively, the processor 900 may optionally include one or more arithmetic-logic units (ALUs) 900. One or more of these components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g., buses) .
[0150] The processor 900 may be a processor chipset and include a protocol stack (e.g., a software stack) executed by the processor chipset to perform various operations (e.g., receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) in accordance with examples as described herein. The processor chipset may include one or more cores, one or more caches (e.g., memory local to or included in the processor chipset (e.g., the processor 900) or other memory (e.g., random access memory (RAM) , read-only memory (ROM) , dynamic RAM (DRAM) , synchronous dynamic RAM (SDRAM) , static RAM (SRAM) , ferroelectric RAM (FeRAM) , magnetic RAM (MRAM) , resistive RAM (RRAM) , flash memory, phase change memory (PCM) , and others) .
[0151] The controller 902 may be configured to manage and coordinate various operations (e.g., signaling, receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) of the processor 900 to cause the processor 900 to support various operations in accordance with examples as described herein. For example, the controller 902 may operate as a control unit of the processor 900, generating control signals that manage the operation of various components of the processor 900. These control signals include enabling or disabling functional units, selecting data paths, initiating memory access, and coordinating timing of operations.
[0152] The controller 902 may be configured to fetch (e.g., obtain, retrieve, receive) instructions from the memory 904 and determine subsequent instruction (s) to be executed to cause the processor 900 to support various operations in accordance with examples as described herein. The controller 902 may be configured to track memory address of instructions associated with the memory 904. The controller 902 may be configured to decode instructions to determine the operation to be performed and the operands involved. For example, the controller 902 may be configured to interpret the instruction and determine control signals to be output to other components of the processor 900 to cause the processor 900 to support various operations in accordance with examples as described herein. Additionally, or alternatively, the controller 902 may be configured to manage flow of data within the processor 900. The controller 902 may be configured to control transfer of data between registers, arithmetic logic units (ALUs) , and other functional units of the processor 900.
[0153] The memory 904 may include one or more caches (e.g., memory local to or included in the processor 900 or other memory, such RAM, ROM, DRAM, SDRAM, SRAM, MRAM, flash memory, etc. In some implementation, the memory 904 may reside within or on a processor chipset (e.g., local to the processor 900) . In some other implementations, the memory 904 may reside external to the processor chipset (e.g., remote to the processor 900) .
[0154] The memory 904 may store computer-readable, computer-executable code including instructions that, when executed by the processor 900, cause the processor 900 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. The controller 902 and / or the processor 900 may be configured to execute computer-readable instructions stored in the memory 904 to cause the processor 900 to perform various functions (e.g., functions or tasks supporting transmit power prioritization) . For example, the processor 900 and / or the controller 902 may be coupled with or to the memory 904, the processor 900, the controller 902, and the memory 904 may be configured to perform various functions described herein. In some examples, the processor 900 may include multiple processors and the memory 904 may include multiple memories. One or more of the multiple processors may be coupled with one or more of the multiple memories, which may, individually or collectively, be configured to perform various functions herein.
[0155] The one or more ALUs 900 may be configured to support various operations in accordance with examples as described herein. In some implementation, the one or more ALUs 900 may reside within or on a processor chipset (e.g., the processor 900) . In some other implementations, the one or more ALUs 900 may reside external to the processor chipset (e.g., the processor 900) . One or more ALUs 900 may perform one or more computations such as addition, subtraction, multiplication, and division on data. For example, one or more ALUs 900 may receive input operands and an operation code, which determines an operation to be executed. One or more ALUs 900 be configured with a variety of logical and arithmetic circuits, including adders, subtractors, shifters, and logic gates, to process and manipulate the data according to the operation. Additionally, or alternatively, the one or more ALUs 900 may support logical operations such as AND, OR, exclusive-OR (XOR) , not-OR (NOR) , and not-AND (NAND) , enabling the one or more ALUs 900 to handle conditional operations, comparisons, and bitwise operations.
[0156] The processor 900 may support wireless communication in accordance with examples as disclosed herein. The processor 902 may be configured to or operable to support a means for receiving, from a base station via the transceiver, a configuration on a resource setting containing one or more non-zero power channel state information reference signal (NZP CSI-RS) resource sets for an operation of the UE associated with an artificial intelligence (AI) / machine learning (ML) model or an AI / ML functionality; and transmitting, to the base station via the transceiver, an indication for a failure event of the AI / ML model or the AI / ML functionality in the case that the UE determines the failure event based on differential reference signal receiving power (RSRP) based performance monitoring for the AI / ML model or the AI / ML functionality.
[0157] FIG. 10 illustrates an example of a processor that supports AI / ML inference for communication in accordance with aspects of the present disclosure. The processor 1000 may be an example of a processor configured to perform various operations in accordance with examples as described herein. The processor 1000 may include a controller 1002 configured to perform various operations in accordance with examples as described herein. The processor 1000 may optionally include at least one memory 1004. Additionally, or alternatively, the processor 1000 may optionally include one or more arithmetic-logic units (ALUs) 1000. One or more of these components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g., buses) .
[0158] The processor 1000 may be a processor chipset and include a protocol stack (e.g., a software stack) executed by the processor chipset to perform various operations (e.g., receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) in accordance with examples as described herein. The processor chipset may include one or more cores, one or more caches (e.g., memory local to or included in the processor chipset (e.g., the processor 1000) or other memory (e.g., random access memory (RAM) , read-only memory (ROM) , dynamic RAM (DRAM) , synchronous dynamic RAM (SDRAM) , static RAM (SRAM) , ferroelectric RAM (FeRAM) , magnetic RAM (MRAM) , resistive RAM (RRAM) , flash memory, phase change memory (PCM) , and others) .
[0159] The controller 1002 may be configured to manage and coordinate various operations (e.g., signaling, receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) of the processor 1000 to cause the processor 1000 to support various operations in accordance with examples as described herein. For example, the controller 1002 may operate as a control unit of the processor 1000, generating control signals that manage the operation of various components of the processor 1000. These control signals include enabling or disabling functional units, selecting data paths, initiating memory access, and coordinating timing of operations.
[0160] The controller 1002 may be configured to fetch (e.g., obtain, retrieve, receive) instructions from the memory 1004 and determine subsequent instruction (s) to be executed to cause the processor 1000 to support various operations in accordance with examples as described herein. The controller 1002 may be configured to track memory address of instructions associated with the memory 1004. The controller 1002 may be configured to decode instructions to determine the operation to be performed and the operands involved. For example, the controller 1002 may be configured to interpret the instruction and determine control signals to be output to other components of the processor 1000 to cause the processor 1000 to support various operations in accordance with examples as described herein. Additionally, or alternatively, the controller 1002 may be configured to manage flow of data within the processor 1000. The controller 1002 may be configured to control transfer of data between registers, arithmetic logic units (ALUs) , and other functional units of the processor 1000.
[0161] The memory 1004 may include one or more caches (e.g., memory local to or included in the processor 1000 or other memory, such RAM, ROM, DRAM, SDRAM, SRAM, MRAM, flash memory, etc. In some implementation, the memory 1004 may reside within or on a processor chipset (e.g., local to the processor 1000) . In some other implementations, the memory 1004 may reside external to the processor chipset (e.g., remote to the processor 1000) .
[0162] The memory 1004 may store computer-readable, computer-executable code including instructions that, when executed by the processor 1000, cause the processor 1000 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. The controller 1002 and / or the processor 1000 may be configured to execute computer-readable instructions stored in the memory 1004 to cause the processor 1000 to perform various functions (e.g., functions or tasks supporting transmit power prioritization) . For example, the processor 1000 and / or the controller 1002 may be coupled with or to the memory 1004, the processor 1000, the controller 1002, and the memory 1004 may be configured to perform various functions described herein. In some examples, the processor 1000 may include multiple processors and the memory 1004 may include multiple memories. One or more of the multiple processors may be coupled with one or more of the multiple memories, which may, individually or collectively, be configured to perform various functions herein.
[0163] The one or more ALUs 1000 may be configured to support various operations in accordance with examples as described herein. In some implementation, the one or more ALUs 1000 may reside within or on a processor chipset (e.g., the processor 1000) . In some other implementations, the one or more ALUs 1000 may reside external to the processor chipset (e.g., the processor 1000) . One or more ALUs 1000 may perform one or more computations such as addition, subtraction, multiplication, and division on data. For example, one or more ALUs 1000 may receive input operands and an operation code, which determines an operation to be executed. One or more ALUs 1000 be configured with a variety of logical and arithmetic circuits, including adders, subtractors, shifters, and logic gates, to process and manipulate the data according to the operation. Additionally, or alternatively, the one or more ALUs 1000 may support logical operations such as AND, OR, exclusive-OR (XOR) , not-OR (NOR) , and not-AND (NAND) , enabling the one or more ALUs 1000 to handle conditional operations, comparisons, and bitwise operations.
[0164] The processor 1000 may support wireless communication in accordance with examples as disclosed herein. The processor 1002 may be configured to or operable to support a means for transmitting, to a user equipment (UE) via the transceiver, a configuration on a resource setting containing one or more non-zero power channel state information reference signal (NZP CSI-RS) resource sets for an operation of the UE associated with an artificial intelligence (AI) / machine learning (ML) model or an AI / ML functionality; and receiving, from the UE via the transceiver, an indication for a failure event of the AI / ML model or the AI / ML functionality in the case that the UE determines the failure event based on differential reference signal receiving power (RSRP) based performance monitoring for the AI / ML model or the AI / ML functionality.
[0165] FIG. 11 illustrates flowchart of method that supports AI / ML inference for communication in accordance with aspects of the present disclosure. The operations of the method 1100 may be implemented by a device or its components as described herein. For example, the operations of the method 1100 may be performed by a UE 104 as described herein. In some implementations, the device may execute a set of instructions to control the function elements of the device to perform the described functions. Additionally, or alternatively, the device may perform aspects of the described functions using special-purpose hardware.
[0166] At 1105, the method may include receiving, from a base station via the transceiver, a configuration on a resource setting containing one or more non-zero power channel state information reference signal (NZP CSI-RS) resource sets for an operation of the UE associated with an artificial intelligence (AI) / machine learning (ML) model or an AI / ML functionality. The operations of 1105 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 1105 may be performed by a device as described with reference to FIG. 1.
[0167] At 1110, the method may include transmitting, to the base station via the transceiver, an indication for a failure event of the AI / ML model or the AI / ML functionality in the case that the UE determines the failure event based on differential reference signal receiving power (RSRP) based performance monitoring for the AI / ML model or the AI / ML functionality. The operations of 1110 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 1110 may be performed by a device as described with reference to FIG. 1.
[0168] FIG. 12 illustrates flowchart of method that supports AI / ML inference for communication in accordance with aspects of the present disclosure. The operations of the method 1200 may be implemented by a device or its components as described herein. For example, the operations of the method 1200 may be performed by a base station 102 as described herein. In some implementations, the device may execute a set of instructions to control the function elements of the device to perform the described functions. Additionally, or alternatively, the device may perform aspects of the described functions using special-purpose hardware.
[0169] At 1205, the method may include transmitting, to a user equipment (UE) via the transceiver, a configuration on a resource setting containing one or more non-zero power channel state information reference signal (NZP CSI-RS) resource sets for an operation of the UE associated with an artificial intelligence (AI) / machine learning (ML) model or an AI / ML functionality. The operations of 1205 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 1205 may be performed by a device as described with reference to FIG. 1.
[0170] At 1210, the method may include receiving, from the UE via the transceiver, an indication for a failure event of the AI / ML model or the AI / ML functionality in the case that the UE determines the failure event based on differential reference signal receiving power (RSRP) based performance monitoring for the AI / ML model or the AI / ML functionality. The operations of 1210 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 1210 may be performed by a device as described with reference to FIG. 1.
[0171] It should be noted that the methods described herein describes possible implementations, and that the operations and the steps may be rearranged or otherwise modified and that other implementations are possible. Further, aspects from two or more of the methods may be combined.
[0172] The various illustrative blocks and components described in connection with the disclosure herein may be implemented or performed with a general-purpose processor, a DSP, an ASIC, a CPU, an FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices (e.g., a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.
[0173] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Other examples and implementations are within the scope of the disclosure and appended claims. For example, due to the nature of software, functions described herein may be implemented using software executed by a processor, hardware, firmware, hardwiring, or combinations of any of these. Features implementing functions may also be physically located at various positions, including being distributed such that portions of functions are implemented at different physical locations.
[0174] Computer-readable media includes both non-transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or special-purpose computer. By way of example, non-transitory computer-readable media may include RAM, ROM, electrically erasable programmable ROM (EEPROM) , flash memory, compact disk (CD) ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that may be used to carry or store desired program code means in the form of instructions or data structures and that may be accessed by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor.
[0175] As used herein, including in the claims, an article “a” before an element is unrestricted and understood to refer to “at least one” of those elements or “one or more” of those elements. The terms “a, ” “at least one, ” “one or more, ” and “at least one of one or more” may be interchangeable. As used herein, including in the claims, “or” as used in a list of items (e.g., a list of items prefaced by a phrase such as “at least one of” or “one or more of” or “one or both of” ) indicates an inclusive list such that, for example, a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C) . Also, as used herein, the phrase “based on” shall not be construed as a reference to a closed set of conditions. For example, an example step that is described as “based on condition A” may be based on both a condition A and a condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase “based on” shall be construed in the same manner as the phrase “based at least in part on. Further, as used herein, including in the claims, a “set” may include one or more elements.
[0176] The description herein is provided to enable a person having ordinary skill in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to a person having ordinary skill in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not limited to the examples and designs described herein but is to be accorded the broadest scope consistent with the principles and novel features disclosed herein.
Claims
1.A user equipment (UE) comprising:a processor; anda transceiver coupled to the processor,wherein the processor is configured to:receive, from a base station via the transceiver, a configuration on a resource setting containing one or more non-zero power channel state information reference signal (NZP CSI-RS) resource sets for an operation of the UE associated with an artificial intelligence (AI) / machine learning (ML) model or an AI / ML functionality; andtransmit, to the base station via the transceiver, an indication for a failure event of the AI / ML model or the AI / ML functionality in the case that the UE determines the failure event based on differential reference signal receiving power (RSRP) based performance monitoring for the AI / ML model or the AI / ML functionality.2.The UE of claim 1, wherein the operation comprises one of the following:providing a channel state information (CSI) report,performing a beam prediction, orperforming a CSI prediction.3.The UE of claim 1, wherein the processor is further configured to:receive, from the base station via the transceiver, a CSI reporting configuration with the operation of AI / ML associated with the resource setting configuration;transmit, to the base station via the transceiver, a beam report corresponding to the CSI reporting configuration, wherein the beam report indicates a set of transmit beams and corresponding predicted layer 1 reference signal receiving power (L1-RSRP) ; andreceive, from the base station via the transceiver, transmission on NZP CSI-RS resources corresponding to the resource setting associated with the set of reported transmit beams.4.The UE of claim 3, wherein the beam report is transmitted in a first set of symbol (s) , the transmission on the NZP CSI-RS resource (s) is received in a second set of symbol (s) , and the duration between the last symbol of the first set of symbol (s) and the first symbol of the second set of symbol (s) is larger than a first threshold.5.The UE of claim 3, wherein the resource setting configuration indicates one set of NZP CSI-RS resources, a first NZP CSI-RS resource at first position of the set of NZP CSI-RS is assumed to be transmitted by a first transmit beam at a first position of the set of transmit beams indicated in the associated beam report, and a second NZP CSI-RS resource at second position of the set of NZP CSI-RS resource is assumed to be transmitted by a second transmit beam at a second position of the set of transmit beams indicated in the associated beam report.6.The UE of claim 1, wherein the NZP CSI-RS resource (s) in the resource setting configuration is periodic in the case that the CSI report is a periodic CSI report.7.The UE of claim 1, wherein the NZP CSI-RS resource (s) in the resource setting configuration is a semi-persistent in the case that the CSI report is one of the following:a semi-persistent CSI report, ora periodic CSI report.8.The UE of claim 1, wherein the NZP CSI-RS resource (s) in the resource setting configuration is aperiodic in the case that the CSI report is one of the following:a semi-persistent CSI report,a periodic CSI report, oran aperiodic CSI report.9.The UE of claim 1, wherein the processor is further configured to:transmit, to the base station via the transceiver, an aperiodic beam transmission request for performance monitoring in a beam report associated with AI / ML operation.10.The UE of claim 3, wherein an AI / ML model failure instance or an AI / ML functionality failure instance is determined in the case that average differential RSRP of all beams in the set of transmit beams is worse than a second threshold.11.The UE of claim 10, wherein determining the failure event based on differential RSRP based performance monitoring for the AI / ML model or the AI / ML functionality comprises:determining the failure event of the AI / ML model or the AI / ML functionality in the case that a number of the AI / ML model failure instances or the AI / ML functionality failure instances during a period is greater than a third threshold.12.The UE of claim 11, wherein the failure event of the AI / ML model or the AI / ML functionality comprises at least one of the following:a measured L1-RSRP of each of the beams in the latest set of NZP CSI-RS resource for performance monitoring;whether there is another AI / ML model or functionality applicable to a current scenario or condition; ora recommended AI / ML model or functionality.13.The UE of claim 1, wherein the processor is further configured to:receive, from the base station via the transceiver, a CSI reporting configuration associated with the resource setting configuration, the NZP CSI-RS resources in the NZP CSI-RS resource set for the resource setting is configured with a parameter of repetition;transmit, to the base station via the transceiver, a beam report corresponding to the CSI reporting configuration, wherein the beam report comprises a set of beams and a corresponding L1-RSRP.14.The UE of claim 13, wherein the resource setting configuration comprises one NZP CSI-RS resource set containing one or more NZP CSI-RS resource groups, transmissions on NZP CSI-RS resources in the same NZP CSI-RS resource group are assumed to be transmitted by a same transmit beam, and transmissions on NZP CSI-RS resources in different NZP CSI-RS resource groups are assumed to be transmitted by different transmit beams.15.The UE of claim 14, wherein a first beam at a first position in the beam report corresponds to the transmit beam used for a first NZP CSI resource group of the NZP CSI-RS resource set, the corresponding L1-RSRP is the highest L1-RSRP corresponding to the first beam among the receive beams of the UE, a second beam in the beam report at a second position corresponds to the transmit beam used for a second NZP CSI resource group of the NZP CSI-RS resource set, and the corresponding L1-RSRP is the highest L1-RSRP corresponding to the second beam among the receive beams of the UE.16.The UE of claim 13, wherein the resource setting containing a NZP CSI-RS resource set, and a transmission on an NZP CSI-RS resource in the NZP CSI-RS resource set is transmitted with a configured repetition times in a same number of the valid symbols.17.The UE of claim 16, wherein transmissions on different NZP CSI-RS resources in the NZP CSI-RS resource set are transmitted in different slots.18.A processor for wireless communication, comprising:at least one memory; anda controller coupled with the at least one memory and configured to cause the controller to:receive, from a base station via the transceiver, a configuration on a resource setting containing one or more non-zero power channel state information reference signal (NZP CSI-RS) resource sets for an operation of the UE associated with an artificial intelligence (AI) / machine learning (ML) model or an AI / ML functionality; andtransmit, to the base station via the transceiver, an indication for a failure event of the AI / ML model or the AI / ML functionality in the case that the UE determines the failure event based on differential reference signal receiving power (RSRP) based performance monitoring for the AI / ML model or the AI / ML functionality.19.A method performed by a user equipment (UE) , the method comprising:receiving, from a base station via the transceiver, a configuration on a resource setting containing one or more non-zero power channel state information reference signal (NZP CSI-RS) resource sets for an operation of the UE associated with an artificial intelligence (AI) / machine learning (ML) model or an AI / ML functionality; andtransmitting, to the base station via the transceiver, an indication for a failure event of the AI / ML model or the AI / ML functionality in the case that the UE determines the failure event based on differential reference signal receiving power (RSRP) based performance monitoring for the AI / ML model or the AI / ML functionality.20.A base station comprising:a processor; anda transceiver coupled to the processor,wherein the processor is configured to:transmit, to a user equipment (UE) via the transceiver, a configuration on a resource setting containing one or more non-zero power channel state information reference signal (NZP CSI-RS) resource sets for an operation of the UE associated with an artificial intelligence (AI) / machine learning (ML) model or an AI / ML functionality; andreceive, from the UE via the transceiver, an indication for a failure event of the AI / ML model or the AI / ML functionality in the case that the UE determines the failure event based on differential reference signal receiving power (RSRP) based performance monitoring for the AI / ML model or the AI / ML functionality.