Beam management

Abstract

Various example embodiments of this disclosure relate to beam management In an aspect, a terminal device determines the CSI report configuration for the AI / ML-based BM, and based on the configuration, transmits at least one report for a first quantity and a second quantity. The first quantity is used for reporting beam prediction, and the second quantity is used for at least reporting a performance metric of a predicted beam. As such, a solution for artificial intelligence / machine learning-based beam management is provided with a channel state information report configuration, thereby improving the communication performance of the terminal device.

Description

BEAM MANAGEMENTCROSS-REFERENCE TO RELATED APPLICATION

[0001] This application claims priority from, and the benefit of, United Kingdom Application No. 2406568.2, filed May 10, 2024, which is hereby incorporated by reference in its entirety.TECHNICAL FIELD

[0002] Various example embodiments described in this disclosure relate to the field of communication, and in particular, but not exclusively, to a terminal device, a network device, methods, apparatuses, and a computer readable storage medium for beam management.BACKGROUND

[0003] A communication network can be seen as a facility that enables communications between two or more communication devices, or provides communication devices access to a data network. A mobile or wireless communication network is one example of a communication network.

[0004] Such communication networks operate in accordance with standards, such as those promulgated by 3GPP (Third Generation Partnership Project) or ETSI (European Telecommunications Standards Institute). Examples of such standards include the so-called 5G (5th Generation) standard or other standards promulgated by 3GPP.SUMMARY

[0005] Various example embodiments described herein provide certain advantages, for example in the form of one or more improvements that are either explicitly described herein or otherwise apparent to a person skilled in the relevant art(s) in view of this disclosure. Hence, at least some of these example embodiments aim to provide (or otherwise contribute to) at least part of these aforementioned advantages and improvements.

[0006] In general, example embodiments of this disclosure provide solution(s) related to beam management, such as for implementing artificial intelligence (Al) / machine learning (ML)-based beam management (BM) with a channel state information (CSI) report configuration. More specifically, some embodiments of the disclosure related to performance metric reporting mechanism for user equipment (UE)- sided model beam prediction.

[0007] Some example embodiments of this disclosure will be described with respect to certain aspects. These aspects are not intended to indicate key or essential features of the various example embodiments of this disclosure, nor are they intended to be used to limit the scope thereof. Other features, aspects, and elements will be apparent to a person skilled in the art in view of this disclosure. For example, it should be appreciated that further aspects may be provided by the combination of any two or more of the various aspects described below.

[0008] In a first aspect, there is provided a terminal device. The terminal device comprises at least one processor and at least one memory storing indications that, when executed by the at least one processor, cause the terminal device at least to: determine a channel state information (CSI) report configuration for artificial intelligence (Al) / machine learning (ML)-based beam management (BM). The CSI report configuration includes a first quantity for reporting beam prediction and a second quantity for at least reporting a performance metric of a predicted beam; and transmit at least one report for the first quantity and the second quantity.

[0009] In a second aspect, there is provided a network device. The network device comprises at least one processor and at least one memory storing indications that, when executed by the at least one processor, cause the network device at least to: transmit, to a terminal device, a channel state information (CSI) report configuration for artificial intelligence (Al) / machine learning (ML)-based beam management (BM). The CSI report configuration includes a first quantity for reporting beam prediction and a second quantity for at least reporting a performance metric of a predicted beam; and receive, from the terminal device, at least one report for the first quantity and the second quantity.

[0010] In a third aspect, there is provided a method. The method comprises determining, at a terminal device, a channel state information (CSI) report configuration for artificial intelligence (Al) / machine learning (ML)-based beam management (BM). The CSI report configuration includes a first quantity for reporting beam prediction and a second quantity for at least reporting a performance metric of a predicted beam; and transmitting at least one report for the first quantity and the second quantity.

[0011] In a fourth aspect, there is provided a method. The method comprises transmitting, at a network device and to a terminal device, a channel state information (CSI) report configuration for artificial intelligence (Al) / machine learning (ML)-based beam management (BM). The CSI report configuration includes a first quantity for reporting beam prediction and a second quantity for at least reporting a performance metric of a predicted beam; and receiving, from the terminal device, at least one report for the first quantity and the second quantity.

[0012] In a fifth aspect, there is provided an apparatus. The apparatus comprises means for determining, at a terminal device, a channel state information (CSI) report configuration for artificial intelligence (Al) / machine learning (ML)-based beam management (BM). The CSI report configuration includes a first quantity for reporting beam prediction and a second quantity for at least reporting a performance metric of a predicted beam; and means for transmitting at least one report for the first quantity and the second quantity.

[0013] In a sixth aspect, there is provided an apparatus. The apparatus comprises means for transmitting, at a network device and to a terminal device, a channel state information (CSI) report configuration for artificial intelligence (Al) / machine learning (ML)-based beam management (BM). The CSI report configuration includes a first quantity for reporting beam prediction and a second quantity for at least reporting a performance metric of a predicted beam; and means for receiving, from the terminal device,at least one report for the first quantity and the second quantity.

[0014] In a seventh aspect, there is provided a non-transitory computer readable medium comprising program instructions for causing an apparatus to perform at least the method according to any of the above third and fourth aspects.

[0015] In an eighth aspect, there is provided a terminal device. The terminal device includes determining circuitry configured to determine a channel state information (CSI) report configuration for artificial intelligence (Al) / machine learning (ML)-based beam management (BM). The CSI report configuration includes a first quantity for reporting beam prediction and a second quantity for at least reporting a performance metric of a predicted beam; and transmitting circuitry configured to transmit at least one report for the first quantity and the second quantity.

[0016] In a ninth aspect, there is provided a network device. The network device includes transmitting circuitry configured to transmit, to a terminal device, a channel state information (CSI) report configuration for artificial intelligence (Al) / machine learning (ML)-based beam management (BM). The CSI report configuration includes a first quantity for reporting beam prediction and a second quantity for at least reporting a performance metric of a predicted beam; and receiving circuitry configured to receive, from the terminal device, at least one report for the first quantity and the second quantity.

[0017] In a tenth aspect, there is provided a computer program including instructions, which, when executed by an apparatus, cause the apparatus at least to perform at least the method according to any of the above third and fourth aspects.

[0018] Various other aspects and further examples are also described in the following detailed description and in the attached claims.

[0019] According to some aspects, there is provided the subject matter of the independent claims. Some further aspects are defined in the dependent claims. Any examples that do not fall under the scope of the claims are to be interpreted as examples useful for understanding this disclosure.

[0020] As previously mentioned, it is to be understood that the summary section is not intended to identify key or essential features of embodiments of this disclosure, nor is it intended to be used to limit the scope thereof. Other features, aspects, and elements of the disclosure will become apparent in view of the following.BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Some example embodiments will now be described, by way of illustrative and non-limiting example only, with reference to the accompanying drawings, in which:

[0022] FIG. 1 illustrates an example communication network in which some example embodiments of this disclosure may be implemented;

[0023] FIG. 2 shows a signaling chart illustrating a process for AI / ML based beam management according to some example embodiments of this disclosure;

[0024] FIG. 3 shows a signaling chart illustrating another process for AI / ML based beam management according to some example embodiments of this disclosure;

[0025] FIG. 4 illustrates a flowchart of a method implemented at a terminal device according to some example embodiments of this disclosure;

[0026] FIG. 5 illustrates a flowchart of a method implemented at a network device according to some example embodiments of this disclosure;

[0027] FIG. 6 illustrates a simplified block diagram of a device that is suitable for implementing example embodiments of this disclosure; and

[0028] FIG. 7 illustrates a block diagram of an example computer readable medium in accordance with some example embodiments of this disclosure.

[0029] Throughout the drawings, the same or similar reference numerals represent the same or similar element.DETAILED DESCRIPTION

[0030] Various example embodiments of this disclosure will now be further described. It is to be understood that these example embodiments are described only for the purpose of illustration and intended to aid those skilled in the art to understand and implement the various example embodiments of this disclosure, without suggesting any specific limitation as to the scope thereof. Example embodiments described herein can be implemented in various manners other than the ones described below.

[0031] The terminology used herein is generally provided the purpose of describing certain example embodiments only and is not intended to be limiting. In the following description and claims, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs, unless otherwise defined.

[0032] References in this disclosure to “one embodiment,” “an embodiment,” “an example embodiment,” “some example embodiments,” “certain example embodiments,” “various example embodiments,” and the like indicate that the referenced embodiment(s) described may include particular feature(s), structure(s), or characteristic(s), but it is not necessary that every embodiment or example embodiment includes the particular feature(s), structure(s), or c h aracteristic (s) . Moreover, such phrases are not necessarily referring to the same embodiment or example embodiment. Further, when particular feature(s), structure(s), or characteristic(s) are described in connection with an embodiment or example embodiment, it is submitted that it is within the knowledge of one skilled in the art to combine such feature(s), structure(s), or characteristic(s) in connection with other embodiments or example embodiments described herein whether or not such combination(s) are explicitly described.

[0033] It shall be understood that although the terms “first” and “second” etc. 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. For example, a first element could be termed a secondelement, and similarly, a second element could be termed a first element, without departing from the scope of the various example embodiments.

[0034] 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 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.

[0035] As used herein, “at least one of the following: ” and “at least one of ” and similar expressions, where the list of two or more elements are joined by “and” or “or”, mean at least any one of the elements, or at least any two or more of the elements, or at least all the elements. As used herein, the expression “and / or” includes any and all combinations of the listed terms, including at least one of the elements, or at least two or more of the elements, or at least all of the elements. As used herein, the term “or” refers to a non-exclusive “or” unless otherwise indicated (e.g., use of “or else” or “or in the alternative”).

[0036] As used herein, unless stated explicitly, performing a respective feature, step, or functionality “in response to A” does not indicate that the respective feature, step, or functionality is performed immediately after “A” occurs as one or more intervening features, steps, or functionalities may be included (at least in part) between an occurrence of the respective feature, step or functionality and “A”. Analogously, performing a respective feature, step, or functionality “based on A” does not indicate that the respective feature, step, or functionality is performed solely based on “A” as the respective feature, step, or functionality may be further based at least in part on one or more other features, steps, or functionalities in addition to “A”.

[0037] As used herein, the term “circuitry” may refer to one or more or all of the following example embodiments:(a) hardware-only circuit implementations (such as implementations in only analog and / or digital circuitry) and(b) combinations of hardware circuits and software, such as (as applicable):(i) a combination of analog and / or digital hardware circuit(s) with software / firmware and(ii) any portions of hardware processor(s) with software (including digital signal processor(s)), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions) and(c) hardware circuit(s) and or processor(s), such as a microprocessor(s) or a portion of a microprocessor(s), that requires software (e.g., firmware) for operation, but the software may not be present when it is not utilized for operation.

[0038] This definition of circuitry applies to all uses of this term herein, including in any claims. As afurther example, as used herein, the term circuitry also covers an implementation of merely a hardware circuit or processor (or multiple processors) or portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example and if applicable to the particular claim element, a baseband integrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in server, a cellular network device, or other computing or network device.

[0039] As used herein, the term “communication network” refers to a network following any suitable communication standards, such as 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-loT) and so on. Furthermore, 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 (1 G), the second generation (2G), 2.5G, 2.75G, the third generation (3G), the fourth generation (4G), 4.5G, the fifth generation (5G), sixth generation (6G) communication protocols, and / or any other protocols either currently known or to be developed in the future. The various example embodiments of this disclosure may be applied in various communication systems. Given the rapid development in communications, there will of course also be future type communication technologies and systems with which this disclosure may be embodied. It should not be seen as limiting the scope of this disclosure to only the aforementioned communication technologies and systems.

[0040] As used herein, the term “network device” or “network element” refers to a node in a communication network via which a terminal device accesses the network and receives services therefrom. The communication network may include a core network (CN). The communication network may include a radio access network (RAN). The network device in RAN may refer to a base station (BS) or an access point (AP), for example, a node B (NodeB or NB), an evolved NodeB (eNodeB or eNB), a new radio (NR) next generation NodeB (e.g., a gNB), a Remote Radio Unit (RRU), a radio header (RH), a remote radio head (RRH), a relay, a low power node such as a femto, a pico, and so forth, depending on the applied terminology and technology.

[0041] The term “terminal device” refers to any end device that may be configured to perform wireless communication. By way of example embodiment, a terminal device may also be referred to as a communication device, user equipment (UE), a Subscriber Station (SS), 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, voice over IP (VoIP) phones, wireless local loop phones, a tablet, a wearable terminal device, a personal digital assistant (PDA), portable computers, desktop computer, image capture terminal devices such as digital cameras, gaming terminal devices, music storage and playback appliances, vehicle-mounted wireless terminal devices, wireless endpoints, mobile stations, laptop- embedded equipment (LEE), laptop-mounted equipment (LME), USB dongles, smart devices, 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 and applications (e.g., remote surgery), an industrial device and applications (e.g., 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. As used herein, the terms “terminal device”, “communication device”, “terminal”, “user equipment” and “UE” may be used interchangeably.

[0042] In the communications area, there is a constant evolution ongoing with the aim to provide enhanced (e.g., efficient and reliable) solutions for utilizing wireless communication networks. Each new generation has it owns technical challenges for handling the different situations and processes that are utilized to connect and serve devices connected to the wireless network. To meet the demand for wireless data traffic having increased since deployment of 4th generation (4G) communication systems, efforts have been made to develop an improved 5th generation (5G) or pre-6G communication system. The new communication systems can support various types of service applications for terminal devices.

[0043] The AI / ML based beam management may involve both spatial domain beam prediction (BM-Case1 ) and time domain beam prediction (BM-Case2). The spatial domain beam prediction (BM-Case1) is to predict the best Tx / Rx beams in different spatial locations. The time domain beam prediction (BM-Case2) aims to predict the most likely beam to be used for next time instants. In this way, a reduced overhead and lower beam measurements and reporting latency cane be supported.

[0044] For the AI / ML based beam management, some embodiments of the disclosure may focus on UE- assisted network (NW)-sided performance monitoring, i.e. the solution(s) of reporting a performance metric for UE-side model and NW-side monitoring. When the UE performs beam prediction, the NW can do performance monitoring such that it can configure the UE to switch to other functionality / model or configure the UE to switch back to beam management without AI / ML. In such cases, the NW may configure the UE to derive performance metric(s) that represent ML model performance and ask the UE to report the performance metric(s) to the NW, and then the NW makes a decision. For example, beam prediction accuracy for UE- assisted performance monitoring at the NW-side is reported while the prediction is performed at the UE.

[0045] Since normal periodic beam reporting generally has only one CSI reporting configuration, the NW may need to use the same periodic CSI report configuration for both inference and monitoring in order to avoid duplications of configurations. In addition, it is not fully clear what are the reporting contents and reporting mechanism to report the performance metric, e.g., beam prediction accuracy for BM-Case1 and BM-Case2, when the NW uses one CSI reporting configuration for both inference and monitoring output.

[0046] Currently, there is no method to indicate the UE to report performance metrics using a CSI-report configuration. In addition, the reporting timelines and reporting quantities of beam prediction accuracy using CSI-ReportConfig are still desired to be addressed.

[0047] In some embodiments of this disclosure, the solution(s) of reporting the performance metric are focused for the BM-Case1 and BM-Case2. When the UE is configured to report beam prediction accuracy,the NW may configure the UE to report beam prediction accuracy using CSI reporting framework based L1- signalling. A reporting mechanism and new timeline of reporting for UE-assisted NW-sided performance monitoring is provided in some embodiments of the present disclosure.

[0048] According to embodiments of the present disclosure, there is providing a solution to implement AI / ML-based BM with a CSI report configuration. A terminal device can determine the CSI report configuration for the AI / ML-based BM, and based on the configuration, transmit at least one report for a first quantity and a second quantity. The first quantity is used for reporting beam prediction, and the second quantity is used for at least reporting a performance metric of a predicted beam. As such, a solution for AI / ML-based BM, e.g. a performance metric of a predicted beam, is provided with a CSI report configuration, thereby improving the communication performance of the terminal device. Principles and embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0049] FIG. 1 illustrates a schematic diagram of an example communication environment 100 in which some embodiments of the present disclosure can be implemented. The environment 100, which may be a part of a communication network, includes devices such as a terminal device 110 and a network device 120. The communication between the terminal device 110 and the network device 120 may be direct or indirect. As an example, the terminal device 110 and the network device 120 may communicate with one or more further devices not shown in FIG. 1 .

[0050] In an example, throughout the description, to transmit data and / or control information, the terminal device 110 may perform communications with the network device 120. A link from the network device 120 to the terminal device 110 is referred to as a downlink (DL), while a link from the terminal device 110 to the network device 120 is referred to as an uplink (UL).

[0051] Although the terminal device 110 and the network device 120 are described in the communication environment 100 of FIG. 1 , embodiments of the present disclosure may equally apply to any other suitable communication devices in communication with one another. That is, embodiments of the present disclosure are not limited to the exemplary scenarios of FIG. 1 .

[0052] It is to be understood that the particular number of various communication devices and the particular number of various communication links as shown in FIG. 1 is for illustration purpose only without suggesting any limitations. The communication environment 100 may include any suitable number of communication devices and any suitable number of communication links for implementing embodiments of the present disclosure. In addition, it should be appreciated that there may be various wireless as well as wireline communications (if needed) among all of the communication devices.

[0053] The communications in the environment 100 may follow any suitable communication standards or protocols, which are already in existence or to be developed in the future, such as Universal Mobile Telecommunications System (UMTS), long term evolution (LTE), LTE-Advanced (LTE-A), the fifth generation (5G) New Radio (NR), Wireless Fidelity (Wi-Fi) and Worldwide Interoperability for Microwave Access (WiMAX)standards, and employs any suitable communication technologies, including, for example, Multiple-Input Multiple-Output (MIMO), Orthogonal Frequency Division Multiplexing (OFDM), time division multiplexing (TDM), frequency division multiplexing (FDM), code division multiplexing (CDM), Bluetooth, ZigBee, and machine type communication (MTC), enhanced mobile broadband (eMBB), massive machine type communication (mMTC), ultra-reliable low latency communication (URLLC), Carrier Aggregation (CA), Dual Connectivity (DC), and New Radio Unlicensed (NR-U) technologies.

[0054] More details of some example embodiments of this disclosure will be described with reference to FIGS. 2-3. FIG. 2 shows a signaling chart illustrating an example process for AI / ML-based beam management according to some example embodiments of this disclosure. Only for the purpose of discussion, the process 200 will be described with reference to FIG. 1 . The process 200 may involve the terminal device 110 and the network device 120 in FIG. 1 . It is to be appreciated that any graphic elements, numerical values, and descriptive text in these figures are only for the purpose of illustration without suggesting any specific limitations.

[0055] In the process 200, the terminal device 110 determines (210) a CSI report configuration for AI / ML- based BM. The CSI report configuration includes a first quantity for reporting beam prediction and a second quantity for at least reporting a performance metric of a predicted beam. In an example embodiment, the terminal device 110 may determine the CSI report configuration for the AI / ML BM by receiving (220) the CSI report configuration transmitted from a network device 120, as shown in FIG. 2. In another example embodiment which is not shown, the terminal device 110 may determine the CSI report configuration for the AI / ML BM by determining a predefined CSI report configuration as the CSI report configuration.

[0056] With the CSI report configuration, the terminal device 110 may determine, based on a first CSI processing time for the first quantity, the first quantity for reporting the beam prediction. Additionally or alternatively, the terminal device 110 may determine, based on a second CSI processing time for the second quantity, the second quantity by calculating the performance metric. The second CSI processing time may have a larger value than the first CSI processing time.

[0057] Then, the terminal device 110 transmits (230) one or more reports for the first quantity and the second quantity. In an example embodiment, the one or more reports may comprise a single report for both the first quantity and the second quantity. In another example embodiment, the one or more reports may comprise a first report for the first quantity and a second report for the second quantity. The first report for the first quantity and the second report for the second quantity may be applied for one or more future time instances respectively. It should be understood that the first and second reports may be a common report, or different reports.

[0058] For example, the first report for the first quantity, e.g. the above determined first quantity, is transmitted based on one or both of a first reporting periodicity and a first offset. On the other side of communication, the network device 120 receives (230) the first report from the terminal device 110, forexample, based on one or both of the first reporting periodicity and the first offset. In an example embodiment, the first report for the first quantity may comprise one or more predicted CSI-reference signal (RS) resource indicators (CRIs). Alternatively, the first report for the first quantity may comprise one or more predicted reference signal received power (RSRP). Alternatively, the first report for the first quantity may comprise both the one or more predicted CRIs and the one or more RSRP.

[0059] For example, the second report for the second quantity, e.g. the above determined second quantity, is transmitted based on one or both of a second reporting periodicity and a second offset. On the other side of communication, the network device 120 receives (240) the second report from the terminal device 110, for example, based on one or both of the second reporting periodicity and the second offset. The second reporting periodicity for the second quantity may be longer than the first reporting periodicity for the first quantity. It is to be understood that the first and second reporting periodicities and the first and second offsets can be set according to the actual requirements, which is not limiting herein.

[0060] In an example embodiment, with the same periodic CSI report configuration for both inference and monitoring, this is possible for the configured / indicated monitoring RS resource set when the same RS resource set for inference and monitoring is configured or when different RS resource sets are configured for inference and monitoring. In other words, the first report for the first quantity and the second report for the second quantity may be configured with a same RS resource set or separate RS resource sets. As an example, the terminal device 110 may report the first quantity based on a configured RS resource set, and may report the second quantity based on another configured RS resource set. As another example, the terminal device 110 may report the first and the second quantities based on one common RS resource set.

[0061] In an example embodiment, the second report for the second quantity may comprise beam prediction accuracy. The beam prediction accuracy may comprise one of the following: a percentage of a Top-1 genie-aided beam being a Top-1 predicted beam; a percentage of a Top-1 genie-aided beam being one of Top-K predicted beams; a percentage of a RSRP of the Top-1 predicted beam being within a margin of a RSRP of the Top-1 genie-aided beam; a percentage of Top-K genie-aided beams being the Top-K predicted beams; or a difference between the RSRP of the Top-1 predicted beam and the RSRP of the Top- 1 genie-aided beam.

[0062] Additionally or alternatively, the second report for the second quantity may comprise RSRP prediction accuracy. The RSRP prediction accuracy may comprise accuracy of RSRP prediction corresponding to Top-K genie-aided beams. Additionally or alternatively, the second report for the second quantity may comprise RSRP and beam prediction accuracy. The RSRP and beam prediction accuracy may comprise accuracy of Top-K beams prediction and corresponding RSRP prediction. Additionally or alternatively, the second report for the second quantity may comprise an RSRP difference, e.g. L1-RSRP difference, which will be further described below.

[0063] In another example embodiment, the second quantity may be further used for reporting beamprediction. Accordingly, the second report for the second quantity may further comprise a predicted CRI, a predicted RSRP, or both. More details will be further described with reference to FIG. 3.

[0064] FIG. 3 shows a signaling chart illustrating another example process for AI / ML-based beam management according to some example embodiments of this disclosure. FIG. 3 also shows a reporting framework for UE-assisted NW-side monitoring when a UE is configured to report beam prediction accuracy for BM-Case1 . Only for the purpose of discussion, the process 300 will be described with reference to FIG. 1 . The process 300 may involve a UE 301 and a NW 302. The UE 301 may be an example of the terminal device 110 in FIG. 1 , and the NW 302 may be an example of the network device 120 in FIG. 1. It is to be appreciated that any graphic elements, numerical values, and descriptive text in these figures are only for the purpose of illustration without suggesting any specific limitations.

[0065] In the process 300, the UE 110 receives (310) a configuration to support beam prediction in CSI- ReportConfig_x. The configuration includes reportquantity 1 / reportquantity 2 and CSI- ReportPeriodicityAndOffset 1 / CSI-ReportPeriodicityAndOffset 2. The configuration may be an RRC configuration that contains CSI-MeasConfig and CSI-ReportConfig, where at least one CSI-ReportConfig (e.g., CSI-ReportConfig_x) is enabling ML beam prediction at the UE side for BM-Case1 or BM-Case2.

[0066] In other words, the NW 120 configures the UE 110 with the CSI-RS report configuration (CSI- ReportConfig_x) which enables two reporting quantities, i.e. the first quantity and the second quantity. The first quantity is used for inference reporting, and the second quantity is used for both inference and monitoring metric (or only monitoring metric) reporting. For example, the first quantity (reportquantityl) for inference reporting can be predicted CRI (Peri) (or other variants mentioned below) with CSI- ReportPeriodicityAndOffsetl . The NW 120 also configures the second quantity (reportq uantity2) for reporting inference and performance metric which can be predicted CRI and beam prediction accuracy (Pcri- BPaccuracy) (or other variants mentioned below) with CSI-ReportPeriodicityAndOffset2.

[0067] Then, the NW 120 enables (320) reporting regarding CSLReportCo nfi g_x for the UE 110 to report (i) an inference output and (ii) a performance metric based UE-assisted NW-sided performance monitoring output. Accordingly, the UE 110 performs (330) inference for AI / ML enabled beam prediction. Further, the UE 110 determines (340) reportq u an ity 1 for reporting inference, for example, with considering a first CSI processing timeline associated to reportquanity 1 . The UE 110 can be defined (in the spec) to consider the first CSI processing time for the first quantity. Next, the UE 110 reports (350) reportquanityl for inference output, for example, with considering CSI ReportPeriodicityAndOffsetl .

[0068] Additionally or alternatively, The UE 110 determines (360) reportingquantity2 by calculating performance metrics, for example, with considering a second CSI processing timeline associated to reportingquantity2. The UE 110 can be defined (in the spec) to consider the second CSI processing time for the second quantity. In this case, the second CSI processing time can have a larger value than the first CSI processing time.

[0069] As an option 1 , the UE 110 may calculate Top-K beam prediction accuracy. As an option 2, the UE 110 may calculate RSRP prediction accuracy. It is to be noted that the option 2 also covers the reporting of both Top-K prediction accuracy and RSRP prediction accuracy in the same report. As an option 3, the UE 110 may calculate RSRP prediction accuracy. It should be understood that other options for possible performance metrics can be considered, which will be further described below.

[0070] In some embodiments of the present disclosure, one or more of the following performance metrics may be used. The performance metric may be beam prediction accuracy (%), for example, Top-1 (%) or Top-K / 1 (%). The Top-1 (%) indicates a percentage of "a Top-1 genie-aided beam is a Top-1 predicted beam". The Top-K / 1 (%) indicates a percentage of "a Top-1 genie-aided beam is one of Top-K predicted beams", where K >1 and values can be reported.

[0071] The performance metric may be beam prediction accuracy (%) with a 1 dB margin for Top-1 beam. The beam prediction accuracy (%) with a 1 dB margin is a percentage of the Top-1 predicted beam “whose ideal L1-RSRP is within 1 dB of the ideal L1-RSRP of the Top-1 genie-aided beam.”

[0072] The performance metric may be RSRP and Top-K beams prediction accuracy. It is also possible to report the accuracy of RSRP and Top-K beams prediction. In this case, the ML model used at the UE can predict RSRP corresponding predicted Top-K beams. It is to be noted that the inference reporting of this option can be predicted RSRP values and predicted Top-K beam IDs. While the reporting for performance monitoring (UE-assisted NW-side performance monitoring) can be the accuracy of predicted RSRP and the accuracy of predicted Top-K beam IDs.

[0073] The performance metric may be RSRP prediction accuracy. It is also possible to report the accuracy of RSRP prediction. In this case, the ML model used at the UE can predict RSRP values of Top- K genie-aided beams. It is to be noted that the inference reporting of this option can be predicted RSRP. While the reporting for performance monitoring (UE-assisted NW-side performance monitoring) can be RSRP prediction accuracy.

[0074] The performance metric may be an L1-RSRP difference. When the output of AI / ML model is Top- K beam IDs and RSRP. The L1-RSRP difference can be calculated by the difference between the ideal L1- RSRP of a Top-1 predicted beam and the ideal L1-RSRP of a Top-1 genie-aided beam.

[0075] Next, the UE 110 reports (370) reportquanity2 with considering CSI-ReportPeriodicityAndOffset2. For example, the UE 110 can be configured to report beam prediction accuracy, e.g. Top-1 (%) or Top-K / 1 (%) beam prediction accuracy, using L1 -signalling and via a same CSI report for beam prediction inference.

[0076] One or more of the above variants of performance metrics for BM-Case1 / 2 also can be applied in this disclosure. As an implementation, when the ML model at the UE side can predict Top-K beams, the first quantity for inference reporting can be Peri (predicted CRI), and the second quantity for both inference and monitoring reporting can be Pcri-BPaccuracy (predicted CRI and beam prediction accuracy) or BPaccuracy (Top-K beam prediction accuracy). For BM-Case2, the reporting can be applied for N futuretime instances.

[0077] As another implementation, when the ML model at the UE side can predict the corresponding RSRP of predicted beams, the first quantity for inference reporting can be Pcri-PRSRP (predicted CRI and predicted RSRP), and the second quantity of reporting for both inference and monitoring reporting can be Pcri-PRSRP -BPaccuracy (Peri, PRSRP, and Top-K beams prediction accuracy) or BP-accuracy (Top-K beam prediction accuracy). For BM-Case2, the reporting can be applied for N future time instances.

[0078] In addition, the UE 110 can be defined (in the specifications) or configured (via RRC) to report a first reporting periodicity / period value for the first quantity (for inference reporting) and a second reporting periodicity / period value for the second quantity. As an example, in such a case, the second reporting periodicity / period can have a longer periodicity than the first reporting periodicity / period.

[0079] It is to be noted that in a UE-side AI / ML model, the NW 120 can configure the UE 110 to report the performance monitoring metric(s) based on the configured / indicated monitoring RS resource set (e.g. a full Set A or a subset of Set A beams can be considered as the monitoring RS resource set). The monitoring RS resource set can be used by the UE 110 to calculate performance metrics (such as Top-1 (%) or Top- K / 1 (%) beam prediction accuracy). The monitoring RS resource set can be configured corresponding to the full Set A or subset of Set A. It is to be noted that the CSI-ResourceConfig can be extended to separate two resource sets, one for an inference resource set and another one for a monitoring resource set.

[0080] An embodiment on the CSI processing time for BM-Case1 is shown in Table 1 .Table 1 (extended based on Table 5.4-2 in 38.214), the new formats of CSI computation delay requirement for reporting beam prediction accuracy are given in bold, and p denotes the subcarrier spacing.

[0081] An embodiment on the CSI processing time for BM-Case2 is shown in Table 2. For BM-Case2, the beampredictionReportTiming and beamPredictionMonitoringReportTime can be considered in multiple future time instances. Table 2 shows the beampredictionReportTiming and beamPredictionMonitoringReportTimefor four future time instances.Table 2 (extended based on Table 5.4-2 in 38.214), the new formats of CSI computation delay requirement for reporting beam prediction accuracy for BM-Case 2 are given in bold, and denotes the subcarrier spacing.

[0082] As an alternative, when the UE 110 reports the first reporting quantity which are Peri or Pcri- predicted RSRP (PRSRP) (or other variants of inference report), the UE 110 can use a new CSI processing time according to, for example, [Z4, Z ) of the table 1 or 2. As for the 1Z4,Z ), the X is according to UE reported capability beamPredictionReportTiming, and the KBI is according to UE reported capability beamSwitchTiming as defined in 3GPP specifications, for example, TS 38.306. The X will be changed according to UE reported capability beamPredictionReportTiming, where it may indicate the number of OFDM symbols between the end of the last symbol of CSI-RS and the start of the first symbol of the transmission channel containing Peri or Pcri-PRSRP. The UE 110 provides the capability for the band number for which the report is provided (where the measurement is performed). The UE 110 includes this field for each supported sub-carrier spacing. Also, the KBI will be changed according to UE reported capability beamSwitchTiming as in a normal scheme, such as, a legacy scheme.

[0083] As another alternative, when the UE 110 reports the second quantity which are Pcri-BPaccuracy or ‘Pcri-PRSRP-BPaccuracy’ (or other variants of monitoring metrics), the UE 110 uses a CSI processing time according to, for example, (Z5, Zs) of the table 1 or 2. As for the (Z5, Zs), the Xp is according to UE reported capability beamPredictionMonitoringReportTiming, and the KBI is according to UE reported capability beamSwitchTiming as defined in 3GPP specifications, such as, TS 38.306. The Xp will be changed according to UE reported capability beamPredictionMonitoringReportTiming, where it may indicate the number of OFDM symbols between the end of the last symbol of CSI-RS and the start of the first symbol of the transmission channel containing Peri or Pcri-PRSRP. The UE 110 provides the capability for the band number for which the report is provided (where the measurement is performed). The UE 110 includes this field for each supported sub-carrier spacing. Also, the KBI will be changed according to UE reported capability beamSwitchTiming as in a normal scheme, for example, a legacy scheme.

[0084] FIG. 4 shows a flowchart of an example method 400 implemented at a terminal device in accordance with some example embodiments of this disclosure. For the purpose of discussion, the method 400 will be described from the perspective of the terminal device 110 with reference to FIG. 1.

[0085] At block 410, the terminal device 110 determines a channel state information (CSI) report configuration for artificial intelligence (Al) / machine learning (ML)-based beam management (BM). The CSI report configuration includes a first quantity for reporting beam prediction and a second quantity for at least reporting a performance metric of a predicted beam. At block 420, the terminal device 110 transmits at least one report for the first quantity and the second quantity.

[0086] In some example embodiments, the at least one report comprises a single report for both the firstquantity and the second quantity.

[0087] In some example embodiments, the at least one report comprises a first report for the first quantity and a second report for the second quantity.

[0088] In some example embodiments, the first report for the first quantity comprises at least one of the following: at least one predicted CSI-reference signal (RS) resource indicator (CRI); or at least one predicted reference signal received power (RSRP).

[0089] In some example embodiments, the second report for the second quantity comprises at least one of the following: beam prediction accuracy; RSRP prediction accuracy; RSRP and beam prediction accuracy; or an RSRP difference.

[0090] In some example embodiments, the beam prediction accuracy comprises one of the following: a percentage of a Top-1 genie-aided beam being a Top-1 predicted beam; a percentage of a Top-1 genie-aided beam being one of Top-K predicted beams; a percentage of a RSRP of the Top-1 predicted beam being within a margin of a RSRP of the Top-1 genie-aided beam; a percentage of Top-K genie-aided beams being the Top-K predicted beams; or a difference between the RSRP of the Top-1 predicted beam and the RSRP of the Top-1 genie-aided beam.

[0091] In some example embodiments, the RSRP prediction accuracy comprises accuracy of RSRP prediction corresponding to Top-K genie-aided beams.

[0092] In some example embodiments, the RSRP and beam prediction accuracy comprises accuracy of Top-K beams prediction and corresponding RSRP prediction.

[0093] In some example embodiments, the first report for the first quantity and the second report for the second quantity are applied for at least one future time instance.

[0094] In some example embodiments, the terminal device 110 determines the CSI report configuration for the AI / ML BM by: receiving the CSI report configuration from a network device; or determining a predefined CSI report configuration as the CSI report configuration.

[0095] In some example embodiments, the second quantity is further used for reporting beam prediction.

[0096] In some example embodiments, the second report for the second quantity further comprises at least one of the following: a predicted CRI; or a predicted RSRP.

[0097] In some example embodiments, the first report for the first quantity and the second report for the second quantity are configured with a same RS resource set or separate RS resource sets.

[0098] In some example embodiments, the terminal device 110 may further determine, based on a first CSI processing time for the first quantity, the first quantity for reporting the beam prediction, and determine, based on a second CSI processing time for the second quantity, the second quantity by calculating the performance metric.

[0099] In some example embodiments, the second CSI processing time has a larger value than the first CSI processing time.

[0100] In some example embodiments, the first report for the first quantity is transmitted based on at least one of a first reporting periodicity and a first offset; and the second report for the second quantity is transmitted based on at least one of a second reporting periodicity and a second offset.

[0101] In some example embodiments, the second reporting periodicity for the second quantity is longer than the first reporting periodicity for the first quantity.

[0102] FIG. 5 shows a flowchart of an example method 500 implemented at a network device in accordance with some example embodiments of this disclosure. For the purpose of discussion, the method 500 will be described from the perspective of the network device 120 with reference to FIG. 1.

[0103] At block 510, the network device 120 transmits, to a terminal device 110, a channel state information (CSI) report configuration for artificial intelligence (Al) / machine learning (ML)-based beam management (BM). The CSI report configuration includes a first quantity for reporting beam prediction and a second quantity for at least reporting a performance metric of a predicted beam. At block 520, the network device 120 receives, from the terminal device 110, at least one report for the first quantity and the second quantity.

[0104] In some example embodiments, the at least one report comprises a single report for both the first quantity and the second quantity.

[0105] In some example embodiments, the at least one report comprises a first report for the first quantity and a second report for the second quantity.

[0106] In some example embodiments, the first report for the first quantity comprises at least one of the following: at least one predicted CSI-reference signal (RS) resource indicator (CRI); or at least one predicted reference signal received power (RSRP).

[0107] In some example embodiments, the second report for the second quantity comprises at least one of the following: beam prediction accuracy; RSRP prediction accuracy; RSRP and beam prediction accuracy; or an RSRP difference.

[0108] In some example embodiments, the beam prediction accuracy comprises one of the following: a percentage of a Top-1 genie-aided beam being a Top-1 predicted beam; a percentage of a Top-1 genie-aided beam being one of Top-K predicted beams; or a percentage of a RSRP of the Top-1 predicted beam being within a margin of a RSRP of the Top-1 genie-aided beam.

[0109] In some example embodiments, the RSRP prediction accuracy comprises accuracy of RSRP prediction corresponding to Top-K genie-aided beams.

[0110] In some example embodiments, the RSRP and beam prediction accuracy comprises accuracy of Top-K beams prediction and corresponding RSRP prediction.

[0111] In some example embodiments, the first report for the first quantity and the second report for the second quantity are applied for at least one future time instance.

[0112] In some example embodiments, the second quantity is further used for reporting beam prediction.

[0113] In some example embodiments, the second report for the second quantity further comprises atleast one of the following: a predicted CRI; or a predicted RSRP.

[0114] In some example embodiments, the first report for the first quantity and the second report for the second quantity are configured with separate RS resource sets.

[0115] In some example embodiments, the first report for the first quantity is received based on at least one of a first reporting periodicity and a first offset; and the second report for the second quantity is received based on at least one of a second reporting periodicity and a second offset.

[0116] In some example embodiments, the second reporting periodicity for the second quantity is longer than the first reporting periodicity for the first quantity.

[0117] In some example embodiments, an apparatus configured to perform the method 400 (for example, the terminal device 110) may include means for performing respective steps of the method 400. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.

[0118] In some example embodiments, the apparatus includes means for determining, at a terminal device, a channel state information (CSI) report configuration for artificial intelligence (Al) / machine learning (ML)- based beam management (BM), wherein the CSI report configuration includes a first quantity for reporting beam prediction and a second quantity for at least reporting a performance metric of a predicted beam; and means for transmitting at least one report for the first quantity and the second quantity.

[0119] In some example embodiments, the at least one report comprises a single report for both the first quantity and the second quantity.

[0120] In some example embodiments, the at least one report comprises a first report for the first quantity and a second report for the second quantity.

[0121] In some example embodiments, the first report for the first quantity comprises at least one of the following: at least one predicted CSI-reference signal (RS) resource indicator (CRI); or at least one predicted reference signal received power (RSRP).

[0122] In some example embodiments, the second report for the second quantity comprises at least one of the following: beam prediction accuracy; RSRP prediction accuracy; RSRP and beam prediction accuracy; or an RSRP difference.

[0123] In some example embodiments, the beam prediction accuracy comprises one of the following: a percentage of a Top-1 genie-aided beam being a Top-1 predicted beam; a percentage of a Top-1 genie-aided beam being one of Top-K predicted beams; a percentage of a RSRP of the Top-1 predicted beam being within a margin of a RSRP of the Top-1 genie-aided beam; a percentage of Top-K genie-aided beams being the Top-K predicted beams; or a difference between the RSRP of the Top-1 predicted beam and the RSRP of the Top-1 genie-aided beam.

[0124] In some example embodiments, the RSRP prediction accuracy comprises accuracy of RSRP prediction corresponding to Top-K genie-aided beams.

[0125] In some example embodiments, the RSRP and beam prediction accuracy comprises accuracy of Top-K beams prediction and corresponding RSRP prediction.

[0126] In some example embodiments, the first report for the first quantity and the second report for the second quantity are applied for at least one future time instance.

[0127] In some example embodiments, the means for determining the CSI report configuration for the AI / ML BM includes means for determining the CSI report configuration for the AI / ML BM by receiving the CSI report configuration from a network device; or means for determining the CSI report configuration for the AI / ML BM by determining a predefined CSI report configuration as the CSI report configuration.

[0128] In some example embodiments, the second quantity is further used for reporting beam prediction.

[0129] In some example embodiments, the second report for the second quantity further comprises at least one of the following: a predicted CRI; or a predicted RSRP.

[0130] In some example embodiments, the first report for the first quantity and the second report for the second quantity are configured with a same RS resource set or separate RS resource sets.

[0131] In some example embodiments, the apparatus further includes means for determining, based on a first CSI processing time for the first quantity, the first quantity for reporting the beam prediction, and means for determining, based on a second CSI processing time for the second quantity, the second quantity by calculating the performance metric.

[0132] In some example embodiments, the second CSI processing time has a larger value than the first CSI processing time.

[0133] In some example embodiments, the first report for the first quantity is transmitted based on at least one of a first reporting periodicity and a first offset; and the second report for the second quantity is transmitted based on at least one of a second reporting periodicity and a second offset.

[0134] In some example embodiments, the second reporting periodicity for the second quantity is longer than the first reporting periodicity for the first quantity.

[0135] In some example embodiments, the apparatus further includes means for performing other steps in some example embodiments of the method 400. In some example embodiments, the means includes at least one processor and at least one memory including computer program code, the at least one memory and computer program code configured to, with the at least one processor, cause the performance of the apparatus.

[0136] In some example embodiments, an apparatus configured to perform the method 500 (for example, the network device 120) may include means for performing respective steps of the method 500. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.

[0137] In some example embodiments, the apparatus includes means for transmitting, at a network device and to a terminal device, a channel state information (CSI) report configuration for artificial intelligence (Al) / machine learning (ML)-based beam management (BM), wherein the CSI report configuration includes a first quantity for reporting beam prediction and a second quantity for at least reporting a performance metric of a predicted beam; and means for receiving, from the terminal device, at least one report for the first quantity and the second quantity.

[0138] In some example embodiments, the at least one report comprises a single report for both the first quantity and the second quantity.

[0139] In some example embodiments, the at least one report comprises a first report for the first quantity and a second report for the second quantity.

[0140] In some example embodiments, the first report for the first quantity comprises at least one of the following: at least one predicted CSI-reference signal (RS) resource indicator (CRI); or at least one predicted reference signal received power (RSRP).

[0141] In some example embodiments, the second report for the second quantity comprises at least one of the following: beam prediction accuracy; RSRP prediction accuracy; RSRP and beam prediction accuracy; or an RSRP difference.

[0142] In some example embodiments, the beam prediction accuracy comprises one of the following: a percentage of a Top-1 genie-aided beam being a Top-1 predicted beam; a percentage of a Top-1 genie-aided beam being one of Top-K predicted beams; or a percentage of a RSRP of the Top-1 predicted beam being within a margin of a RSRP of the Top-1 genie-aided beam.

[0143] In some example embodiments, the RSRP prediction accuracy comprises accuracy of RSRP prediction corresponding to Top-K genie-aided beams.

[0144] In some example embodiments, the RSRP and beam prediction accuracy comprises accuracy of Top-K beams prediction and corresponding RSRP prediction.

[0145] In some example embodiments, the first report for the first quantity and the second report for the second quantity are applied for at least one future time instance.

[0146] In some example embodiments, the second quantity is further used for reporting beam prediction.

[0147] In some example embodiments, the second report for the second quantity further comprises at least one of the following: a predicted CRI; or a predicted RSRP.

[0148] In some example embodiments, the first report for the first quantity and the second report for the second quantity are configured with separate RS resource sets.

[0149] In some example embodiments, the first report for the first quantity is received based on at least one of a first reporting periodicity and a first offset; and the second report for the second quantity is received based on at least one of a second reporting periodicity and a second offset.

[0150] In some example embodiments, the second reporting periodicity for the second quantity is longer than the first reporting periodicity for the first quantity.

[0151] In some example embodiments, the apparatus further includes means for performing other stepsin some example embodiments of the method 500. In some example embodiments, the means includes at least one processor and at least one memory including computer program code, the at least one memory and computer program code configured to, with the at least one processor, cause the performance of the apparatus.

[0152] FIG. 6 is a simplified block diagram of a device 600 that is suitable for implementing example embodiments of this disclosure. The device 600 may be provided to implement the communication device, for example the terminal device 110 or the network device 120 as shown in FIG. 1 . As shown, the device 600 includes one or more processors 610, one or more memories 620 coupled to the processor 610, and one or more communication modules 640 coupled to the processor 610.

[0153] The communication module 640 is for bidirectional communications. The communication modules 640 have at least one antenna to facilitate communication. The communication interface may represent any interface that is necessary for communication with other network elements.

[0154] The processor 610 may be of any type suitable to the local technical network and may include one or more of the following: general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) and processors based on multicore processor architecture, as non-limiting and illustrative examples. The device 600 may have multiple processors, such as an application specific integrated circuit chip that is slaved in time to a clock which synchronizes the main processor.

[0155] The memory 620 may include one or more non-volatile memories and one or more volatile memories. Examples of the non-volatile memories include, but are not limited to, a Read Only Memory (ROM) 624, an electrically programmable read only memory (EPROM), a flash memory, a hard disk, a compact disc (CD), a digital video disk (DVD), and other magnetic storage and / or optical storage. Examples of the volatile memories include, but are not limited to, a random access memory (RAM) 622 and other volatile memories that will not last in the power-down duration.

[0156] A computer program 630 includes computer executable instructions that are executed by the associated processor 610. The program 630 may be stored in the ROM 624. The processor 610 may perform any suitable actions and processing by loading the program 630 into the RAM 622.

[0157] The example embodiments of this disclosure may be implemented by means of the program 630 so that the device 600 may perform any process of this disclosure as discussed with reference to FIGS. 2 to 5. The example embodiments of this disclosure may also be implemented by hardware or by a combination of software and hardware.

[0158] In some example embodiments, the program 630 may be tangibly contained in a computer readable medium which may be included in the device 600 (such as in the memory 620) or other storage devices that are accessible by the device 600. The device 600 may load the program 630 from the computer readable medium to the RAM 622 for execution. The computer readable medium may include any types of tangible non-volatile storage, such as ROM, EPROM, a flash memory, a hard disk, CD, DVD, and the like. FIG. 7shows an example of the computer readable medium 700 in form of CD or DVD. The computer readable medium has the program 630 stored thereon.

[0159] Generally, various example embodiments of this disclosure may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. While various aspects of example embodiments of this disclosure are illustrated and described as block diagrams, flowcharts, or using some other pictorial representations, it is to be understood that the block, apparatus, system, technique or method described herein may be implemented in, as non-limiting and illustrative examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.

[0160] Some embodiments of this disclosure also provide at least one computer program product tangibly stored on a non-transitory computer readable storage medium. The computer program product includes computer-executable instructions, such as those included in program modules, being executed in a device on a target real or virtual processor, to carry out the methods as described above with reference to FIGS. 2- 5. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, or the like that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or split between program modules as desired in various example embodiments. Machine-executable instructions for program modules may be executed within a local or distributed device. In a distributed device, program modules may be located in both local and remote storage media.

[0161] Program code for carrying out methods of this disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0162] In the context of this disclosure, the computer program code or related data may be carried by any suitable carrier to enable the device, apparatus or processor to perform various processes and operations as described above. Examples of the carrier include a signal, computer readable medium, and the like.

[0163] The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable medium may include, but not be limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the computer readable storage medium wouldinclude an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. The term “non- transitory,” as used herein, is a limitation of the medium itself (e.g., tangible, not a signal) as opposed to a limitation on data storage persistency (e.g., RAM vs. ROM).

[0164] Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are contained in the above discussions, these should not be construed as limitations on the scope of this disclosure, but rather as descriptions of features that may be specific to particular example embodiments. Certain features that are described in the context of separate embodiments may also be implemented in combination in a single example embodiment. Conversely, various features that are described in the context of a single example embodiment may also be implemented in multiple example embodiments separately or in any suitable sub-combination.

[0165] Although this disclosure has been described in language specific to structural features and / or methodological acts, it is to be understood that the various example embodiments of this disclosure are not limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the various example embodiments of this disclosure.

Claims

WHAT IS CLAIMED IS:1 . A terminal device comprising: at least one processor; and at least one memory storing indications that, when executed by the at least one processor, cause the terminal device at least to: determine a channel state information (CSI) report configuration for artificial intelligence (Al) / machine learning (ML)-based beam management (BM), wherein the CSI report configuration includes a first quantity for reporting beam prediction and a second quantity for at least reporting a performance metric of a predicted beam; and transmit at least one report for the first quantity and the second quantity.

2. The terminal device of claim 1 , wherein the at least one report comprises a single report for both the first quantity and the second quantity.

3. The terminal device of claim 1 , wherein the at least one report comprises a first report for the first quantity and a second report for the second quantity.

4. The terminal device of claim 3, wherein the first report for the first quantity comprises at least one of the following: at least one predicted CSI-reference signal (RS) resource indicator (CRI); or at least one predicted reference signal received power (RSRP).

5. The terminal device of claim 3 or 4, wherein the second report for the second quantity comprises at least one of the following: beam prediction accuracy;RSRP prediction accuracy;RSRP and beam prediction accuracy; or an RSRP difference.

6. The terminal device of claim 5, wherein the beam prediction accuracy comprises one of the following: a percentage of a Top-1 genie-aided beam being a Top-1 predicted beam; a percentage of a Top-1 genie-aided beam being one of Top-K predicted beams; a percentage of a RSRP of the Top-1 predicted beam being within a margin of a RSRP of the Top-1 genie-aided beam;a percentage of Top-K genie-aided beams being the Top-K predicted beams; or a difference between the RSRP of the Top-1 predicted beam and the RSRP of the Top-1 genie-aided beam.

7. The terminal device of claim 5, wherein the RSRP prediction accuracy comprises accuracy of RSRP prediction corresponding to Top-K genie-aided beams.

8. The terminal device of claim 5, wherein the RSRP and beam prediction accuracy comprises accuracy of Top-K beams prediction and corresponding RSRP prediction.

9. The terminal device of any of claims 3-8, wherein the first report for the first quantity and the second report for the second quantity are applied for at least one future time instance.

10. The terminal device of any of claims 1-9, wherein the terminal device is caused to determine the CSI report configuration for the AI / ML BM by: receiving the CSI report configuration from a network device; or determining a predefined CSI report configuration as the CSI report configuration.

11. The terminal device of any of claims 1-10, wherein the second quantity is further used for reporting beam prediction.

12. The terminal device of claim 5, wherein the second report for the second quantity further comprises at least one of the following: a predicted CRI; or a predicted RSRP.

13. The terminal device of any of claims 3-12, wherein the first report for the first quantity and the second report for the second quantity are configured with a same RS resource set or separate RS resource sets.

14. The terminal device of any of claims 1-13, wherein the terminal device is further caused to: determine, based on a first CSI processing time for the first quantity, the first quantity for reporting the beam prediction; and determine, based on a second CSI processing time for the second quantity, the second quantity by calculating the performance metric.

15. The terminal device of claim 14, wherein the second CSI processing time has a larger value than the first CSI processing time.

16. The terminal device of any of claims 3-15, wherein: the first report for the first quantity is transmitted based on at least one of a first reporting periodicity and a first offset; and the second report for the second quantity is transmitted based on at least one of a second reporting periodicity and a second offset.

17. The terminal device of claim 16, wherein the second reporting periodicity for the second quantity is longer than the first reporting periodicity for the first quantity.

18. A network device comprising: at least one processor; and at least one memory storing indications that, when executed by the at least one processor, cause the network device at least to: transmit, to a terminal device, a channel state information (CSI) report configuration for artificial intelligence (Al) / machine learning (ML)-based beam management (BM), wherein the CSI report configuration includes a first quantity for reporting beam prediction and a second quantity for at least reporting a performance metric of a predicted beam; and receive, from the terminal device, at least one report for the first quantity and the second quantity.

19. The network device of claim 18, wherein the at least one report comprises a single report for both the first quantity and the second quantity.

20. The network device of claim 19, wherein the at least one report comprises a first report for the first quantity and a second report for the second quantity.21 . The network device of claim 20, wherein the first report for the first quantity comprises at least one of the following: at least one predicted CSI-reference signal (RS) resource indicator (CRI); or at least one predicted reference signal received power (RSRP).

22. The network device of claim 20 or 21 , wherein the second report for the second quantity comprises at least one of the following: beam prediction accuracy;RSRP prediction accuracy;RSRP and beam prediction accuracy; or an RSRP difference.

23. The network device of claim 22, wherein the beam prediction accuracy comprises one of the following: a percentage of a Top-1 genie-aided beam being a Top-1 predicted beam; a percentage of a Top-1 genie-aided beam being one of Top-K predicted beams; or a percentage of a RSRP of the Top-1 predicted beam being within a margin of a RSRP of the Top-1 genie-aided beam.

24. The network device of claim 22, wherein the RSRP prediction accuracy comprises accuracy of RSRP prediction corresponding to Top-K genie-aided beams.

25. The network device of claim 22, wherein the RSRP and beam prediction accuracy comprises accuracy of Top-K beams prediction and corresponding RSRP prediction.

26. The network device of any of claims 20-25, wherein the first report for the first quantity and the second report for the second quantity are applied for at least one future time instance.

27. The network device of any of claims 18-26, wherein the second quantity is further used for reporting beam prediction.

28. The network device of claim 22, wherein the second report for the second quantity further comprises at least one of the following: a predicted CRI; or a predicted RSRP.

29. The network device of any of claims 20-28, wherein the first report for the first quantity and the second report for the second quantity are configured with separate RS resource sets.

30. The network device of any of claims 20-29, wherein:the first report for the first quantity is received based on at least one of a first reporting periodicity and a first offset; and the second report for the second quantity is received based on at least one of a second reporting periodicity and a second offset.

31. The network device of claim 30, wherein the second reporting periodicity for the second quantity is longer than the first reporting periodicity for the first quantity.

32. A method comprising: determining, at a terminal device, a channel state information (CSI) report configuration for artificial intelligence (Al) / machine learning (ML)-based beam management (BM), wherein the CSI report configuration includes a first quantity for reporting beam prediction and a second quantity for at least reporting a performance metric of a predicted beam; and transmitting at least one report for the first quantity and the second quantity.

33. A method comprising: transmitting, at a network device and to a terminal device, a channel state information (CSI) report configuration for artificial intelligence (Al) / machine learning (ML)-based beam management (BM), wherein the CSI report configuration includes a first quantity for reporting beam prediction and a second quantity for at least reporting a performance metric of a predicted beam; and receiving, from the terminal device, at least one report for the first quantity and the second quantity.

34. An apparatus comprising: means for determining, at a terminal device, a channel state information (CSI) report configuration for artificial intelligence (Al) / machine learning (ML)-based beam management (BM), wherein the CSI report configuration includes a first quantity for reporting beam prediction and a second quantity for at least reporting a performance metric of a predicted beam; and means for transmitting at least one report for the first quantity and the second quantity.

35. An apparatus comprising: means for transmitting, at a network device and to a terminal device, a channel state information (CSI) report configuration for artificial intelligence (Al) / machine learning (ML)-based beam management (BM), wherein the CSI report configuration includes a first quantity for reporting beam prediction and a second quantity for at least reporting a performance metric of a predicted beam; and means for receiving, from the terminal device, at least one report for the first quantity and the secondquantity.

36. A non-transitory computer readable medium comprising program instructions that, when executed by an apparatus, cause the apparatus to perform at least the method of claim 32 or 33.

Images