Priority control for channel state information reporting

Abstract

There are provided measures for priority control for channel state information reporting. Such measures exemplarily comprise determining a transmission priority for a channel state information report based at least in part on whether channel state information to be reported in said channel state information report is associated with one or more measured quantities and / or one or more predicted quantities.

Description

[0001] Title

[0002] Priority control for channel state information reporting

[0003] Field

[0004] Various example embodiments relate to priority control for channel state information reporting. More specifically, various example embodiments exemplarily relate to measures (including methods, apparatuses and computer program products) for realizing priority control for channel state information reporting of artificial intelligent (Al) or machine learning (ML) enabled beam prediction.

[0005] Background

[0006] The present specification generally relates to beam management utilizing artificial intelligence / machine learning (AI / ML) techniques (AI / ML based beam management) and the related reporting.

[0007] AI / ML based beam management (BM) includes, among others, beam prediction. Beam prediction may comprise spatial domain beam prediction (BM-Casel) and time domain beam prediction (BM-Case2). The scope of spatial beam prediction (BM-Casel) is to predict the best Tx / Rx beams (Tx: transmission; Rx: reception) in different spatial locations. Time-domain beam predictions (BM-Case2) aim to predict the most likely beam to use for next time instants.

[0008] To enable the above-mentioned AI / ML based beam management, it is foreseen that signalling and protocol aspects of (AI / ML related) life cycle management (LCM) enabling functionality and model selection, activation, deactivation, switching, fallback may be needed. In particular, necessary signalling / mechanism(s) for LCM to facilitate model training, inference, performance monitoring, data collection for both UE-sided and NW-sided models may be required.

[0009] The above-mentioned AI / ML-enabled beam prediction in the spatial domain (BM-Casel) or AI / ML-enabled beam prediction in the spatial domain (BM- Casel) and time domain (BM-Case2) may use CSI-reporting framework when supporting the model inference-related beam reports. Namely, the functionality identification and functionality-based LCM framework may be built based on the CSI-reporting framework. In such case, conflicting or colliding CSI reports under participation of CSI-reporting related to the above-mentioned AI / ML-enabled beam prediction can be expected and a solution is needed to solve it if conflicting or colliding happens.

[0010] Summary

[0011] Various example embodiments aim at addressing at least part of the above issues and / or problems and drawbacks.

[0012] Various aspects of example embodiments are set out in the appended claims.

[0013] According to an exemplary aspect, there is provided an apparatus comprising means for determining a transmission priority for a channel state information report based at least in part on whether channel state information to be reported in said channel state information report is associated with one or more measured quantities and / or one or more predicted quantities.

[0014] According to an exemplary aspect, there is provided an apparatus comprising determining circuitry configured to determine a transmission priority for a channel state information report based at least in part on whether channel state information to be reported in said channel state information report is associated with one or more measured quantities and / or one or more predicted quantities. According to an exemplary aspect, there is provided an apparatus comprising at least one processor, and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to perform determining a transmission priority for a channel state information report based at least in part on whether channel state information to be reported in said channel state information report is associated with one or more measured quantities and / or one or more predicted quantities.

[0015] According to an exemplary aspect, there is provided a method comprising determining a transmission priority for a channel state information report based at least in part on whether channel state information to be reported in said channel state information report is associated with one or more measured quantities and / or one or more predicted quantities.

[0016] According to an exemplary aspect, there is provided a computer program product comprising computer-executable computer program code which, when the program is run on a computer, is configured to cause the computer to carry out determining a transmission priority for a channel state information report based at least in part on whether channel state information to be reported in said channel state information report is associated with one or more measured quantities and / or one or more predicted quantities.

[0017] Such computer program product may comprise (or be embodied) a (tangible) computer-readable (storage) medium or the like on which the computerexecutable computer program code is stored, and / or the program may be directly loadable into an internal memory of the computer or a processor thereof.

[0018] Any one of the above aspects enables an efficient handling of conflict or collision situations under participation of CSI-reporting related to the above- mentioned AI / ML-enabled beam prediction to thereby solve at least part of the problems and drawbacks identified in relation to the prior art. By way of example embodiments, there is provided priority control for channel state information reporting. More specifically, by way of example embodiments, there are provided measures and mechanisms for realizing priority control for channel state information reporting.

[0019] Thus, improvement is achieved by methods, apparatuses and computer program products enabling / realizing priority control for channel state information reporting.

[0020] Brief description of the drawings

[0021] In the following, the present disclosure will be described in greater detail by way of non-limiting examples with reference to the accompanying drawings, in which

[0022] FIG. 1 is a block diagram illustrating an apparatus according to example embodiments,

[0023] FIG. 2 is a block diagram illustrating an apparatus according to example embodiments,

[0024] FIG. 3 is a schematic diagram of a procedure according to example embodiments,

[0025] FIG. 4 shows a schematic diagram of signaling sequences according to example embodiments,

[0026] FIG. 5 shows a schematic diagram of signaling sequences according to example embodiments,

[0027] FIG. 6 shows a schematic diagram of signaling sequences according to example embodiments, FIG. 7 is a schematic diagram of a procedure according to example embodiments, and

[0028] FIG. 8 is a block diagram alternatively illustrating apparatuses according to example embodiments.

[0029] Detailed description

[0030] The present disclosure is described herein with reference to particular nonlimiting examples and to what are presently considered to be conceivable embodiments. A person skilled in the art will appreciate that the disclosure is by no means limited to these examples, and may be more broadly applied.

[0031] It is to be noted that the following description of the present disclosure and its embodiments mainly refers to specifications being used as non-limiting examples for certain exemplary network configurations and deployments. Namely, the present disclosure and its embodiments are mainly described in relation to 3GPP specifications being used as non-limiting examples for certain exemplary network configurations and deployments.

[0032] As such, the description of example embodiments given herein specifically refers to terminology which is directly related thereto. Such terminology is only used in the context of the presented non-limiting examples, and does naturally not limit the disclosure in any way. Rather, any other communication or communication related system deployment, etc. may also be utilized as long as compliant with the features described herein.

[0033] Hereinafter, various embodiments and implementations of the present disclosure and its aspects or embodiments are described using several variants and / or alternatives. It is generally noted that, according to certain needs and constraints, all of the described variants and / or alternatives may be provided alone or in any conceivable combination (also including combinations of individual features of the various variants and / or alternatives).

[0034] As used herein, "at least one of the following: " and "at least one of " and similar wording, 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.

[0035] The term "terminal device" or "terminal" in the present disclosure refers to any end device that may be capable of wireless communication. By way of example rather than limitation, 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 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), laptopmounted equipment (LME), USB dongles, smart devices, wireless customerpremises 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. In the following description, the terms "terminal device", "communication device", "terminal", "user equipment" and "UE" may be used interchangeably.

[0036] In relation to AI / ML, the following terminology may be used herein. Data collection: A process of collecting data by the network nodes, management entity, or UE for the purpose of AI / ML model training, data analytics and inference.

[0037] AI / ML Model: A data driven algorithm that applies AI / ML techniques to generate a set of outputs based on a set of inputs.

[0038] AI / ML model training: A process to train an AI / ML Model [by learning the input / output relationship] in a data driven manner and obtain the trained AI / ML Model for inference.

[0039] AI / ML model Inference: A process of using a trained AI / ML model to produce a set of outputs based on a set of inputs.

[0040] AI / ML model validation: A subprocess of training, to evaluate the quality of an AI / ML model using a dataset different from one used for model training, that helps selecting model parameters that generalize beyond the dataset used for model training.

[0041] AI / ML model testing: A subprocess of training, to evaluate the performance of a final AI / ML model using a dataset different from one used for model training and validation. Differently from AI / ML model validation, testing does not assume subsequent tuning of the model.

[0042] UE-side (AI / ML) model : An AI / ML Model whose inference is performed entirely at the UE.

[0043] Network-side (AI / ML) model: An AI / ML Model whose inference is performed entirely at the network.

[0044] One-sided (AI / ML) model : A UE-side (AI / ML) model or a Network-side (AI / ML) model.

[0045] Two-sided (AI / ML) model: A paired AI / ML Model(s) over which joint inference is performed, where joint inference comprises AI / ML Inference whose inference is performed jointly across the UE and the network, i.e, the first part of inference is firstly performed by UE and then the remaining part is performed by gNB, or vice versa.

[0046] AI / ML model transfer: Delivery of an AI / ML model over the air interface, either parameters of a model structure known at the receiving end or a new model with parameters. Delivery may contain a full model or a partial model.

[0047] Model download: Model transfer from the network to UE.

[0048] Model upload: Model transfer from UE to the network.

[0049] Federated learning / federated training: A machine learning technique that trains an AI / ML model across multiple decentralized edge nodes (e.g., UEs, gNBs) each performing local model training using local data samples. The technique requires multiple interactions of the model, but no exchange of local data samples.

[0050] Offline field data: The data collected from field and used for offline training of the AI / ML model.

[0051] Online field data: The data collected from field and used for online training of the AI / ML model.

[0052] Model monitoring: A procedure that monitors the inference performance of the AI / ML model.

[0053] Supervised learning: A process of training a model from input and its corresponding labels.

[0054] Unsupervised learning: A process of training a model without labelled data.

[0055] Semi-supervised learning : A process of training a model with a mix of labelled data and unlabelled data.

[0056] Reinforcement Learning (RL): A process of training an AI / ML model from input (a.k.a. state) and a feedback signal (a.k.a. reward) resulting from the model's output (a.k.a. action) in an environment the model is interacting with.

[0057] Model activation: Enable an AI / ML model for a specific function.

[0058] Model deactivation: Disable an AI / ML model for a specific function.

[0059] Model switching: Deactivating a currently active AI / ML model and activating a different AI / ML model for a specific function.

[0060] Support for downlink (DL) Tx beam prediction for both UE-sided model and NW-sided model may be needed as elaborated above. The prediction may include spatial-domain DL Tx beam prediction for Set A of beams based on measurement results of Set B of beams ("BM-Casel") and temporal DL Tx beam prediction for Set A of beams based on the historic measurement results of Set B of beams ("BM-Case2").

[0061] Here, necessary signalling / mechanism(s) to facilitate LCM operations specific to the BM use cases are to be specified, and method(s) to ensure consistency between training and inference regarding NW-side additional conditions for inference at UE are to be enabled.

[0062] As a further aspect, a reduced overhead and lower beam measurements and reporting latency is to be supported.

[0063] In relation thereto, there are discussions related to data collection in the context of beam management with AI / ML as follows:

[0064] For NW-sided model (NW: network), consider the following options for the contents of data collection for training:

[0065] 1) All layer 1 reference signal receiver power (Ll-RSRP) from the resource for Set A of beams, where Set A of beams are for UE measurement and report;

[0066] 2) A subset of Ll-RSRP from the resource for Set A of beams, with information on corresponding beam / RS ID, where Set A of beams are for UE measurement;

[0067] 3) All Ll-RSRP from the resource for Set B of beams, and information for Top 1 DL beam / RS ID among Set A of beams, where both Set A of beams and Set B of beams are for UE measurement and report respectively;

[0068] 4) A subset of Ll-RSRP from the resource for Set B of beams with information on corresponding beam / RS ID, and information for Top 1 DL beam / RS ID among Set A of beams, where both Set A of beams and Set B of beams are for UE measurement and report respectively;

[0069] 5) A subset of Ll-RSRP from the resource for Set B of beams with information on corresponding beam / RS ID, and a subset of Ll-RSRP from the resource for Set A of beams, with information on corresponding beam / RS ID, where both Set A of beams and Set B of beams are for UE measurement and report respectively.

[0070] In these cases, for NW-sided model and / or UE-assisted model, for Ll-RSRP measurement report for the data collection for training, layer 1 (LI) signaling and high layer signaling is to be provided.

[0071] There are further discussions related to data collection in the context of beam management with AI / ML as follows:

[0072] For NW-sided model for example, the "beam related information" in a beam report in LI signalling, at last for BM-Case 1 and for one time instance of BM- Case 2, supports the following options:

[0073] - With omission: Ll-RSRPs and corresponding beam information of Top M beam(s) of a resource set, e.g. for o Top M beam(s) is the beams with largest M measured values of Ll-RSRPs, where M is configured by gNB, or o M beams within X dB gap to the largest measured value of Ll- RSRP;

[0074] - Without omission: All Ll-RSRPs of a resource set, e.g. for o Without beam information or with best beam index (for differential Ll-RSRP reporting, if supported));

[0075] - Beam information only of Top M beam(s) of a resource set;

[0076] - The last option for one resource set, and the first or second option for another resource set.

[0077] Channel status information (CSI) reporting is a measure for informing how good or bad a channel is at a specific time. CSI is a kind of indicator how good or bad the channel is at a specific time. CSI parameters are quantities related to the state of a channel. A terminal such as a user equipment (UE) reports CSI parameters to an access network node as feedback. The CSI feedback may include several parameters. The UE may use a reference signal to measure the CSI feedback.

[0078] Upon receiving the CSI parameters, the access network may schedule downlink data transmissions (such as modulation scheme, code rate, number of transmission layers, and MIMO precoding) accordingly.

[0079] For any CSI report that comes from the UE, some priority rules may be defined for the UE to follow, especially when dealing with multiple CSI reports.

[0080] A CSI priority rule definition may be as follows (e.g. TS 38.214):

[0081] For two overlapping physical uplink shared channels (PUSCH), the priority rules in this clause are applied for physical channels with same priority index if a UE is not configured with enableSTx2PofmDCI or a UE is configured by higher layer parameter PDCCH-Config that contains two different values of coresetPoolIndex in ControlResourceSet and the UE is configured with enableSTx2PofmDCI and the two overlapping PUSCHs are associated with same value of coresetPoolIndex’.

[0082] CSI reports are associated with a priority value Priicsi(y,k,c,s) =2- Nceiis- Ms-y+ Nceiis- Ms- k+Ms-c+s, where

[0083] - y=0 for aperiodic CSI reports to be carried on PUSCH, y=l for semi-persistent CSI reports to be carried on PUSCH, y=2 for semi-persistent CSI reports to be carried on PUCCH, and y=3 for periodic CSI reports to be carried on PUCCH;

[0084] - k=0 for CSI reports carrying Ll-RSRP or Ll-SINR, and k=l for CSI reports not carrying Ll-RSRP or Ll-SINR;

[0085] - c is the serving cell index, and Nceiis is the value of the higher layer parameter maxNrofServingCells;

[0086] - s is the reportConfigID, and Ms is the value of the higher layer pa ra m ete r maxNrofCSI-ReportConfigura tions . A first CSI report is said to have priority over second CSI report if the associated Priicsi(y,k,c,s) value is lower for the first report than for the second report.

[0087] Two CSI reports may be said to collide if the time occupancy of the physical channels scheduled to carry the CSI reports overlap in at least one orthogonal frequency-division multiplexing (OFDM) symbol and are transmitted on the same carrier. When a UE is configured to transmit two colliding CSI reports,

[0088] - if y values are different between the two CSI reports, the following rules apply except for the case when one of the y value is 2 and the other y value is 3 (for CSI reports transmitted on PUSCH; for CSI reports transmitted on PUCCH): o the CSI report with higher Priicsi(y,k,c,s) value shall not be sent by the UE.

[0089] - otherwise, the two CSI reports are multiplexed or either is dropped based on the priority values.

[0090] However, priority rules such as depicted above do not consider the scenarios where the CSI reports could be one or more beam prediction.

[0091] Hence, the problem arises that priority rules do not provide any policies how to handle such conflict or collision situations under participation of CSI- reporting related to the above-mentioned AI / ML-enabled beam prediction.

[0092] Hence, there is a need to provide for priority control for channel state information reporting, in particular related to the above-mentioned AI / ML- enabled beam prediction.

[0093] According to example embodiments, in general terms, there are provided measures and mechanisms for (enabling / realizing) priority control for channel state information reporting. As mentioned above, conflicting or colliding CSI reports under participation of CSI-reporting related to the above-mentioned AI / ML-enabled beam prediction can be expected, while priority rules such as depicted above do not consider such scenarios, such that approaches to handle AI / ML-enabled beam prediction-related CSI reporting-related priority rules are desired.

[0094] According to priority rules for CSI reporting such as depicted above, which are applicable when there are two CSI reports collide, where colliding means that the time occupancy of the physical channels scheduled to carry the CSI reports overlap in at least one OFDM symbol and are transmitted on the same carrier, each CSI report is associated with a defined priority value Priicsi(y,k,c,s). A lower value for the priority value Priicsi(y,k,c,s) may be considered with higher priority whenever UE behaviors are defined on dropping or multiplexing of CSI reports.

[0095] For the above-mentioned AI / ML based beam management and in particular the above-mentioned AI / ML-enabled beam prediction, a predicted CSI report may be introduced, and it is to be determined whether and / or when this introduced CSI report is to be reported. A predicted CSI report may involve inference (I), performance monitoring (M) and data collection for training (D).

[0096] While priority rules such as depicted above do not provide any policies how to handle such conflict or collision situations under participation of CSI- reporting related to the above-mentioned AI / ML-enabled beam prediction, much less do these provide any policies how to differentiate between such different CSI report contents and / or CSI categories and the handling thereof.

[0097] Hence, in brief, according to example embodiments, when considering priority value calculation for a CSI report, the predicted CSI report needs to be considered. Furthermore, the category of the predicted CSI report may be considered. The predicted CSI report could be for example as below (categories (A) to (F)): (A) UE-sided AI / ML model related inference (prediction quantity) reporting,

[0098] (B) UE-sided AI / ML model related monitoring (measurements or monitoring metrics) reporting,

[0099] (C) UE-sided AI / ML model related training data collection (measurement reporting),

[0100] (D) NW-sided AI / ML model related measurement reporting (for inference),

[0101] (E) NW-sided AI / ML model related measurement reporting (for monitoring), and

[0102] (F) NW-sided AI / ML model related measurement reporting (for training data collection).

[0103] For the priority value calculation, Priicsi(y,k,c,s), at least three ways to redefine the priority value for predicted CSI report are provided as examples in the present disclosure:

[0104] 1) According to example embodiments, a definition of parameter k (k values) in a formula for priorities (Priicsi(y,k,c,s)) for predicted CSI reports is re-defined.

[0105] 2) Further, according to example embodiments, a new parameter (zl parameter) is introduced into the formula for priorities (Priicsi(y,k,c,s)) to differentiate legacy CSI report and predicted CSI report (the newly introduced parameter (zl parameter) is dedicated for predicted CSI report).

[0106] 3) Still further, according to example embodiments, a new coefficient parameter (z2 parameter) is introduced into the formula for priorities (Priicsi(y,k,c,s)) (the newly introduced parameter (z2 parameter) is dedicated for predicted CSI report).

[0107] Example embodiments are specified below in more detail.

[0108] FIG. 1 is a block diagram illustrating an apparatus according to example embodiments. The apparatus may be terminal 10 such as user equipment (UE) comprising means for determining 11. The means for determining 11 determines a transmission priority for a channel state information report based at least in part on whether channel state information to be reported in said channel state information report is associated with one or more measured quantities and / or one or more predicted quantities.

[0109] Said means for determining said transmission priority for channel state information associated with one or more predicted quantities may be further for determining said transmission priority based at least in part on a reporting category associated with a machine learning model of the one or more predicted quantities.

[0110] FIG. 3 is a schematic diagram of a procedure according to example embodiments. The apparatus according to FIG. 1 may perform the method of FIG. 3 but is not limited to this method. The method of FIG. 3 may be performed by the apparatus of FIG. 1 but is not limited to being performed by this apparatus.

[0111] As shown in FIG. 7, a procedure according to example embodiments may comprise an operation of determining (S31) a transmission priority for a channel state information report based at least in part on whether channel state information to be reported in said channel state information report is associated with one or more measured quantities and / or one or more predicted quantities.

[0112] FIG. 2 is a block diagram illustrating an apparatus according to example embodiments. In particular, FIG. 2 illustrates a variation of the apparatus shown in FIG. 1. The apparatus according to FIG. 2 may thus further comprise means for receiving 21, means for comparing 22, and / or means for controlling 23.

[0113] In an embodiment at least some of the functionalities of the apparatus shown in FIG. 1 (or 2) may be shared between two physically separate devices forming one operational entity. Therefore, the apparatus may be seen to depict the operational entity comprising one or more physically separate devices for executing at least some of the described processes.

[0114] According to a variation of the procedure shown in FIG. 3, exemplary details of the determining operation (S31) are given, which are inherently independent from each other as such. Such exemplary determining operation (S31) according to example embodiments may comprise an operation of determining said transmission priority based at least in part on a reporting category associated with a machine learning model of the one or more predicted quantities.

[0115] A reporting category associated with a machine learning model of the one or more predicted quantities may correspond to a purpose of the channel state information report. The purpose here may mean type or usage of the channel state information report, for example inference, monitoring or training data collection.

[0116] According to further example embodiments, said reporting category comprises at least one of the following: inference, or monitoring, or training data collection.

[0117] According to a variation of the procedure shown in FIG. 3, exemplary additional operations are given, which are inherently independent from each other as such. According to such variation, an exemplary method according to example embodiments may comprise an operation of receiving a configuration for said channel state information report. Here, said configuration may be indicative of at least one of the following: whether the channel state information report is associated with measured or predicted quantities; and / or the reporting category of the one or more predicted quantities. According to a variation of the procedure shown in FIG. 3, exemplary details of the determining operation (S31) are given, which are inherently independent from each other as such. Such exemplary determining operation (S31) according to example embodiments may comprise an operation of determining said transmission priority based at least in part on an equation comprising a multiplier or a term. Here, said multiplier or term is determined to take a value from a set comprising: a first value for a reporting category associated with a machine learning model of the one or more predicted quantities selected as inference; a second value different than the first value for a reporting category associated with a machine learning model of the one or more predicted quantities selected as monitoring; and a third value different than the second value for a reporting category associated with a machine learning model of the one or more predicted quantities selected as training data collection.

[0118] The one or more predicted quantities may comprise Ll-RSRP or Ll-SINR quantities.

[0119] According to further example embodiments, said first value may be 0, the second value may be 1, and the third value may be 3. The first value, the second value, and the third value may reflect the different values for k and zl, respectively, as specified further below.

[0120] According to further example embodiments, said first value may be 0.2, the second value may be 0.4, and the third value may be 0.8. The first value, the second value, and the third value may reflect the different values for z2 as specified further below.

[0121] According to further example embodiments, at least one of the first value, the second value and the third value may be comprised in the configuration or may be pre-configured in the apparatus. According to a variation of the procedure shown in FIG. 3, exemplary details of the determining operation (S31) are given, which are inherently independent from each other as such. Such exemplary determining operation (S31) according to example embodiments may comprise an operation of determining said transmission priority based at least in part on an equation comprising a multiplier or term. Here, said multiplier or term is determined to at least one of the following: take a first value when a number of quantities in the channel state information report is lower or lower-or-equal to a first threshold and take a second value when the number of quantities in the channel state information report is greater or greater-or-equal to the first threshold; take a third value when the number of quantities in the channel state information report is lower or lower-or-equal to a second threshold and take a fourth value when the number of quantities in the channel state information report is greater or greater-or-equal to the second threshold but lower or lower-or-equal to a third threshold and take a fifth value when the number of quantities in the channel state information report is greater or greater-or-equal to the third threshold; take a sixth value when a number of sets associated with the channel state information report is lower or lower-or-equal to a fourth threshold and the apparatus is configured to measure said number of sets, and take a seventh value otherwise; take an eight value when a number of bits associated the quantities encoded into the channel state information report is lower or lower-or-equal to a fifth threshold and take a ninth value when the number of bits is greater or greater-or- equal to the fifth threshold.

[0122] According to further example embodiments, said number of quantities in the channel state information report may be a number of Ll-R.SR.Ps reported in the channel state information report. According to further example embodiments, said number of quantities in the channel state information report may be a number of beam IDs reported in the channel state information report.

[0123] According to further example embodiments, said number of sets may be a number of reference signal sets.

[0124] According to further example embodiments, said second value may be associated with a reporting category of monitoring or training data collection.

[0125] According to further example embodiments, said fifth value may be associated with a reporting category of monitoring or training data collection.

[0126] According to further example embodiments, said seventh value may be associated with a reporting category of training data collection.

[0127] According to further example embodiments, said ninth value may be associated with a reporting category of monitoring or training data collection.

[0128] According to further example embodiments, said number of quantities in the channel state information report may be a number of Ll-R.SR.Ps or Ll_SINRs in the channel state information report.

[0129] According to further example embodiments, said third value may be 0, the fourth value may be 1, and the fifth value may be 3.

[0130] According to further example embodiments, said third value may be 0.2, the fourth value may be 0.4, and the fifth value may be 0.6.

[0131] According to further example embodiments, at least one of the values and / or at least one of the thresholds may be received in a configuration or may be pre-configured in the apparatus. According to a variation of the procedure shown in FIG. 3, exemplary additional operations are given, which are inherently independent from each other as such.

[0132] According to such variation, an exemplary method according to example embodiments may comprise an operation of comparing said transmission priority of said channel state information report with a further transmission priority of a further channel state report, and an operation of controlling to transmit either of said channel state information report and said further channel state information report, and to drop the other of said channel state information report and said further channel state information report, or to transmit both of said channel state information report and said further channel state information report in a multiplexed manner based on a result of said means for comparing said transmission priority of said channel state information report with said further transmission priority of the further channel state information report.

[0133] According to a variation of the procedure shown in FIG. 3, exemplary details of the controlling operation (controlling to drop the other of said channel state information report and said further channel state information report based on said result of said means for comparing said transmission priority of said channel state information report with said further transmission priority of the further channel state information report) are given, which are inherently independent from each other as such.

[0134] Such exemplary controlling operation according to example embodiments may comprise an operation of, when said channel state information report is associated with one or more measured quantities and said further channel state information report is associated with one or more predicted quantities, controlling to drop said further channel state information report.

[0135] Example embodiments outlined and specified above are explained below in more specific terms. In detail, modifications of the priority rules as depicted above, and corresponding behaviors of involved entities, are provided and specified according to example embodiments.

[0136] As mentioned above, according to example embodiments, a definition of parameter k (k values) in a formula for priorities (Priicsi(y,k,c,s)) for predicted CSI reports is re-defined.

[0137] Heretofore, k values for different purposes of predicted CSI reporting may be introduced.

[0138] According to example embodiments, these k values may be explicitly categorized by the network to the UE via RRC (explicit definition of k values). In particular, for example, different k values for monitoring (M), data collection (D), and inference (I) for predicted CSI reporting may be introduced.

[0139] As an example, k=0 for I, k=l for M, k=3 for D, and k=2 (more general, k is lower than for M and higher than for D) for other than Ll-RSRP legacy reports.

[0140] According to example embodiments, these k values may be implicitly categorized, following implicit rules (implicit definition of k values).

[0141] According to example embodiments related to implicit categorization of k values, when the number of Ll-RSRPs reported in the one CSI report exceed N1 value (N1 may be defined or configured to the UE), the UE may determine that Ll-RSRP reporting is for a purpose other than (A) or (D) (e.g., purpose can be data collection for training or monitoring).

[0142] According to further example embodiments, when the number of Ll-RSRPs reported in the one CSI report exceed a N2 value and is also larger than N1 (N2 > N1 may be defined or configured to the UE), the UE may determine that Ll-RSRP reporting is for monitoring purpose (i.e., (B), (E)). According to further example embodiments, a larger k value may be assumed for data collection purposes ((C) or (F)) than for purposes (B) or (E).

[0143] According to example embodiments related to implicit categorization of k values, when the number of beam IDs reported in one CSI report exceed N1 value (N1 may be defined or configured to the UE), the UE may determine that beam ID reporting is for a purpose other than (A) or (D) (e.g., purpose can be data collection for training or monitoring).

[0144] According to further example embodiments, when the number of beam IDs reported in one CSI report exceed N2 value and is also larger than N1 (N2 > N1 may be defined or configured to the UE), the UE may determine that beam ID reporting is for monitoring purpose (i.e., (B), (E)). According to further example embodiments, a larger k value may be assumed for data collection purposes ((C) or (F)) than for purposes (B) or (E).

[0145] According to example embodiments related to implicit categorization of k values, when the number of reference signal (RS) sets the CSI report is 2 and the UE is expected to measure both RS sets, the UE may determine that CSI reporting is for data collection purposes ((C) or (F)). According to further example embodiments, a larger k value may be assumed for data collection purposes ((C) or (F)) than for purposes (B) or (E).

[0146] According to example embodiments related to implicit categorization of k values, when the number of bits reported in the CSI report exceed N Ibits value (Nlbits represent N1 quantity refers to number of RS measurements which may be defined or configured to the UE), the UE may determine that CSI reporting is for data collection purposes ((C) or (F)) and / or for monitoring purpose ((B) or (E)).

[0147] In the light of the above, according to example embodiments, the priority rules as depicted above may be modified as follows. For two overlapping physical uplink shared channels (PUSCH), the priority rules in this clause are applied for physical channels with same priority index if a UE is not configured with enableSTx2PofmDCI or a UE is configured by higher layer parameter PDCCH-Config that contains two different values of coresetPoolIndex in ControlResourceSet and the UE is configured with enableSTx2PofmDCI and the two overlapping PUSCHs are associated with same value of coresetPoolIndex’.

[0148] CSI reports are associated with a priority value Priicsi(y,k,c,s) =2- Nceiis- Ms-y+ Nceiis- Ms- k+Ms-c+s, where

[0149] - y=0 for aperiodic CSI reports to be carried on PUSCH, y=l for semi-persistent CSI reports to be carried on PUSCH, y=2 for semi-persistent CSI reports to be carried on PUCCH, and y=3 for periodic CSI reports to be carried on PUCCH;

[0150] - explicit categorization of k values:

[0151] ■ k=0 when CSI report carrying predicted CSI, k=l for CSI report carrying measurements or performance metric / KPIs for monitoring, k=3 for CSI report carrying measurements for data collection, k=2 for CSI report carrying other quantities than Ll-RSRP or Ll-SINR legacy reports; or

[0152] ■ k=offset value between (0, 1), e.g., k=0.2 when CSI report carrying predicted CSI, k=offset value between (0, 1), e.g., k=0.4 when CSI report carrying measurements or performance metric / KPIs for monitoring, where this k value is higher than k value in CSI carrying predicted CSI, k=offset value between (0, 1), e.g., k=0.8 for CSI report carrying measurements for data collection, where this k value is higher than k value in CSI carrying measurements or performance metric / KPIs for monitoring, k=offset value between (0, 1), e.g., k=0.6 for CSI report carrying other quantities than Ll-RSRP or Ll- SINR legacy reports; - implicit categorization of k values:

[0153] ■ k=0 when a CSI report carrying less than N1 Ll-RSRP or Ll-SINR in one report, k=l when a CSI report carrying less than N2 but larger than N1 L1RSRP, k=3 when a CSI report carrying larger than N2 Ll-RSRP, k=2 when a CSI report carrying other quantities than Ll-RSRP or Ll-SINR legacy reports; or

[0154] ■ k=0.2 when a CSI report carrying less than N1 Ll-RSRP or Ll-SINR in one report, k=0.4 when a CSI report carrying less than N2 but larger than N1 Ll-RSRP, k=0.8 when a CSI report carrying larger than N2 Ll-RSRP, k=0.6 when a CSI report carrying other quantities than Ll-RSRP or Ll-SINR legacy reports;

[0155] - c is the serving cell index, and Nceiis is the value of the higher layer parameter maxNrofServingCells;

[0156] - s is the reportConfigID, and Ms is the value of the higher layer pa ra m ete r maxNrofCSI-ReportConfigura tions .

[0157] A first CSI report is said to have priority over second CSI report if the associated Pr csi(y,k,c,s) value is lower for the first report than for the second report.

[0158] It should be understood that using k for determining the transmission priority for channel state information associated with one or more predicted quantities is an example, similar solution may also be considered for y instead of k, and present disclosure only shows how to calculate priority value for predicted CSI reports and determine whether channel state information report associated with measured quantities or one or more predicted quantities should be reported based on the calculation.

[0159] FIG. 4 shows a schematic diagram of signaling sequences according to example embodiments, and in particular illustrates a case where a definition of parameter k (k values) in a formula for priorities (Priicsi(y,k,c,s)) for predicted CSI reports is re-defined. In a step 1 of FIG. 4, according to example embodiments, a configuration to support beam prediction may be exchanged in CSI-ReportConfig_x. Step 1 of FIG. 4 is associated with the AI / ML-enabled beam prediction, where gNB may provide an RRC configuration to enable the CSI reporting based on the beam prediction at the UE side.

[0160] In steps 2 and 3 of FIG. 4, according to example embodiments, a configuration to support monitoring and data collection may be exchanged in CSI-ReportConfig_y and CSI-ReportConfig_m.

[0161] In other words, steps 1, 2 and 3 of FIG. 4 show CSI reporting configurations which priority rules will be compared with when collision between their reports occurs and also when collision between their reports and CSI reports of any further (not-depicted) configurations occurs.

[0162] In a step 4 of FIG. 4, according to example embodiments, CSI-RS and / or SSB transmission is associated to CSI-ReportConfig(s). Step 4 of FIG. 4 may be needed to support any beam measurements and CSI calculations, and the UE may expect to receive the DL RSs prior to any beam or CSI reporting.

[0163] It should be noted that present disclosure does not restrict the sequence or order of step 1 to step 4 in FIG. 4. Configuring or not of step 1 to step 4 depends on gNB, and gNB may configure only part of them which may depend on AI / ML model configuration.

[0164] In a step 5 of FIG. 4, according to example embodiments, the UE performs AI / ML beam prediction.

[0165] In a step 6 of FIG. 4, according to example embodiments, the UE calculates CSI quantities for active CSI report configuration. Step 6 of FIG. 4 may be performed before steps 7 to 9 of FIG. 4 depending on CSI report becoming applicable for the reporting or not. In a step 7 of FIG. 4, according to example embodiments, the UE determines the k parameter at least for each CSI report subject to a collision as discussed above. Step 7 of FIG. 4 may impact other steps, where AI / ML-enabled beam prediction-related CSI reporting determines a parameter k value (as discussed above). Which k shall be determined for the CSI report depends on the configuration in step 1 to step 4 as described before.

[0166] In a step 8 of FIG. 4, according to example embodiments, the UE determines the priority value Priicsi(y,k,c,s) for each CSI report subject to a collision as discussed above based on y and other parameters. That is, the k values are further used to determine the priority values in step 8 of FIG. 4 for each CSI report, where the priority values can be determined as discussed above.

[0167] The priority values may be subsequently considered in the multiplexing and dropping rules when transmitting the CSI reports in the allocated UL resources. According to example embodiments, any instance that the multiplexing rule or dropping rule considers the priority value of a CSI report shall consider the determination of parameter k (as discussed above) of step 7 of FIG. 4.

[0168] In a step 9 of FIG. 4, according to example embodiments, UL resources scheduled for CSI reports are determined under consideration of multiplexing and dropping rules fed with the results of step 8 of FIG. 4.

[0169] As mentioned above, according to example embodiments, a new parameter (zl parameter) may be introduced into the formula for priorities (Priicsi(y,k,c,s)) to differentiate legacy CSI report and predicted CSI report (the newly introduced parameter (zl parameter) is dedicated for predicted CSI report).

[0170] Heretofore, a zl parameter with different values for different purposes of predicted CSI reporting may be introduced. According to example embodiments, the zl parameter may be considered in the formula for priorities (Priicsi(y,k,c,s)) as follows:

[0171] Priicsi(y,k,c,s,zl) = 2- Nceiis- Ms-y+ Nceiis- Ms- k+Ms-c+s+zl

[0172] According to example embodiments, these zl values may be explicitly categorized by the network to the UE via RRC (explicit definition of zl values). In particular, different zl values for monitoring (M), data collection (D), and inference (I) for predicted CSI reporting may be introduced.

[0173] As an example, zl=0 for I, zl = l for M, zl=3 for D, and zl=2 (more general, zl is lower than for M and higher than for D) for other than Ll-RSRP legacy reports.

[0174] According to example embodiments, these zl values may be implicitly categorized, following implicit rules (implicit definition of zl values).

[0175] According to example embodiments related to implicit categorization of zl values, when the number of Ll-RSRPs reported in the one CSI report exceed N1 value (N1 may be defined or configured to the UE), the UE may determine that Ll-RSRP reporting is for a purpose other than (A) or (D) (e.g., purpose can be data collection for training or monitoring).

[0176] According to further example embodiments, when the number of Ll-RSRPs reported in the one CSI report exceed a N2 value and is also larger than N1 (N2 > N1 may be defined or configured to the UE), the UE may determine that Ll-RSRP reporting is for monitoring purpose (i.e., (B), (E)). According to further example embodiments, a larger zl value may be assumed for data collection purposes ((C) or (F)) than for purposes (B) or (E).

[0177] According to example embodiments related to implicit categorization of zl values, when the number of beam IDs reported in one CSI report exceed N1 value (N 1 may be defined or configured to the UE), the UE may determine that beam ID reporting is for a purpose other than (A) or (D) (e.g., purpose can be data collection for training or monitoring).

[0178] According to further example embodiments, when the number of beam IDs reported in one CSI report exceed N2 value and is also larger than N1 (N2 > N1 may be defined or configured to the UE), the UE may determine that beam ID reporting is for monitoring purpose (i.e., (B), (E)). According to further example embodiments, a larger zl value may be assumed for data collection purposes ((C) or (F)) than for purposes (B) or (E).

[0179] According to example embodiments related to implicit categorization of zl values, when the number of reference signal (RS) sets the CSI report is 2 and the UE is expected to measure both RS sets, the UE may determine that CSI reporting is for data collection purposes ((C) or (F)). According to further example embodiments, a larger zl value may be assumed for data collection purposes ((C) or (F)) than for purposes (B) or (E).

[0180] According to example embodiments related to implicit categorization of zl values, when the number of bits reported in the CSI report exceed N Ibits value (Nlbits represent N1 quantity refers to number of RS measurements which may be defined or configured to the UE), the UE may determine that CSI reporting is for data collection purposes ((C) or (F)) and / or for monitoring purpose ((B) or (E)).

[0181] In the light of the above, according to example embodiments, the priority rules as depicted above may be modified as follows.

[0182] For two overlapping physical uplink shared channels (PUSCH), the priority rules in this clause are applied for physical channels with same priority index if a UE is not configured with enableSTx2PofmDCI or a UE is configured by higher layer parameter PDCCH-Config that contains two different values of coresetPoolIndex in ControlResourceSet and the UE is configured with enableSTx2PofmDCI and the two overlapping PUSCHs are associated with same value of coresetPoolIndex

[0183] CSI reports are associated with a priority value Priicsi(y,k,c,s,zl) = 2- Nceiis- Ms-y+ Nceiis- Ms- k+Ms-c+s+zl, where

[0184] - y=0 for aperiodic CSI reports to be carried on PUSCH, y=l for semi-persistent CSI reports to be carried on PUSCH, y=2 for semi-persistent CSI reports to be carried on PUCCH, and y=3 for periodic CSI reports to be carried on PUCCH;

[0185] - k=0 for CSI reports carrying Ll-RSRP or Ll-SINR and k=l for CSI reports not carrying Ll-RSRP or Ll-SINR;

[0186] - c is the serving cell index, and Nceiis is the value of the higher layer parameter maxNrofServingCells;

[0187] - s is the reportConfigID, and Ms is the value of the higher layer pa ra m ete r maxNrofCSI-ReportConfigura tions ;

[0188] - explicit categorization of zl values:

[0189] ■ zl=0 when CSI report carrying predicted CSI, zl = l for CSI report carrying measurements or performance metric / KPIs for monitoring, zl = 3 for CSI report carrying measurements for data collection, zl = 2 for CSI report carrying other quantities than Ll-RSRP or Ll-SINR legacy reports;

[0190] - implicit categorization of zl values:

[0191] ■ zl=0 when a CSI report carrying less than N1 Ll-RSRP or Ll-SINR in one report, zl = l when a CSI report carrying less than N2 but larger than N1 L1RSRP, zl=3 when a CSI report carrying larger than N2 Ll-RSRP, zl=2 when a CSI report carrying other quantities than Ll-RSRP or Ll-SINR legacy reports.

[0192] A first CSI report is said to have priority over second CSI report if the associated Priicsi(y,k,c,s,zl) value is lower for the first report than for the second report. FIG. 5 shows a schematic diagram of signaling sequences according to example embodiments, and in particular illustrates a case where a new parameter (zl parameter) is introduced into the formula for priorities (Priicsi(y,k,c,s)) to differentiate legacy CSI report and predicted CSI report (the newly introduced parameter (zl parameter) is dedicated for predicted CSI report).

[0193] In a step 1 of FIG. 5, according to example embodiments, a configuration to support beam prediction may be exchanged in CSI-ReportConfig_x. Step 1 of FIG. 5 is associated with the AI / ML-enabled beam prediction, where gNB may provide an RRC configuration to enable the CSI reporting based on the beam prediction at the UE side.

[0194] In steps 2 and 3 of FIG. 5, according to example embodiments, a configuration to support monitoring and data collection may be exchanged in CSI-ReportConfig_y and CSI-ReportConfig_m.

[0195] In other words, steps 1, 2 and 3 of FIG. 5 show CSI reporting configurations which priority rules will be compared with when collision between their reports occurs and also when collision between their reports and CSI reports of any further (not-depicted) configurations occurs.

[0196] In a step 4 of FIG. 5, according to example embodiments, CSI-RS and / or SSB transmission may be associated to CSI-ReportConfig(s). Step 4 of FIG. 5 may be needed to support any beam measurements and CSI calculations, and the UE may expect to receive the DL RSs prior to any beam or CSI reporting.

[0197] It should be noted that present disclosure does not restrict the sequence or order of step 1 to step 4 in FIG. 5. Configuring or not of step 1 to step 4 depends on gNB, and gNB may configure only part of them which may depend on AI / ML model configuration. In a step 5 of FIG. 5, according to example embodiments, the UE performs AI / ML beam prediction.

[0198] In a step 6 of FIG. 5, according to example embodiments, the UE may calculate CSI quantities for active CSI report configuration. Step 6 of FIG. 5 may be performed before steps 7 to 9 of FIG. 5 depending on CSI report becoming applicable for the reporting or not.

[0199] In a step 7 of FIG. 5, according to example embodiments, the UE determines the zl parameter at least for each CSI report subject to collision as discussed above. Step 7 of FIG. 5 may impact other steps, where AI / ML-enabled beam prediction-related CSI reporting determines a parameter zl (as discussed above). Which zl parameter is determined depends on the configuration of predictions in step 1 to step 4.

[0200] In a step 8 of FIG. 5, according to example embodiments, the UE determines the priority value Priicsi(y,k,c,s,zl) for each CSI report subject to collision as discussed above based on zl and other parameters. That is, the zl values are further used to determine the priority values in step 8 of FIG. 5 for each CSI report (configured by gNB), where the priority values can be determined as discussed above. The priority values may be subsequently considered in the multiplexing and dropping rules when transmitting the CSI reports in the allocated UL resources.

[0201] In a step 9 of FIG. 5, according to example embodiments, UL resources scheduled for CSI reports may be determined under consideration of multiplexing and dropping rules fed with the results of step 8 of FIG. 5.

[0202] As mentioned above, according to example embodiments, a new coefficient parameter (z2 parameter) may be introduced into the formula for priorities (Priicsi(y,k,c,s)) (the newly introduced parameter (z2 parameter) may be dedicated for predicted CSI report). Heretofore, a coefficient z2 parameter with different values for different purposes of predicted CSI reporting may be introduced.

[0203] According to example embodiments, the z2 parameter is considered in the formula for priorities (Priicsi(y,k,c,s)) as follows:

[0204] Priicsi(y,k,c,s,z2) =2- Nceiis- Ms-y+ Nceiis- Ms- k-z2+Ms-c+s

[0205] According to example embodiments, these z2 values are explicitly categorized by the network to the UE via RRC (explicit definition of z2 values). In particular, different z2 values for monitoring (M), data collection (D), and inference (I) for predicted CSI reporting may be introduced.

[0206] As an example, z2=0.2 for I, z2=0.4 for M, z2=0.8 for D, and z2=0.6 (more general, z2 is lower than for M and higher than for D) for other than Ll-RSRP legacy reports.

[0207] According to example embodiments, these z2 values may be implicitly categorized, following implicit rules (implicit definition of z2 values).

[0208] According to example embodiments related to implicit categorization of z2 values, when the number of Ll-RSRPs reported in the one CSI report exceed N1 value (N1 may be defined or configured to the UE), the UE may determine that Ll-RSRP reporting is for a purpose other than (A) or (D) (e.g., purpose can be data collection for training or monitoring).

[0209] According to further example embodiments, when the number of Ll-RSRPs reported in the one CSI report exceed a N2 value and is also larger than N1 (N2 > N1 may be defined or configured to the UE), the UE may determine that Ll-RSRP reporting is for monitoring purpose (i.e., (B), (E)). According to further example embodiments, a larger z2 value may be assumed for data collection purposes ((C) or (F)) than for purposes (B) or (E). According to example embodiments related to implicit categorization of z2 values, when the number of beam IDs reported in one CSI report exceed N1 value (N 1 may be defined or configured to the UE), the UE may determine that beam ID reporting is for a purpose other than (A) or (D) (e.g., purpose can be data collection for training or monitoring).

[0210] According to further example embodiments, when the number of beam IDs reported in one CSI report exceed N2 value and is also larger than N1 (N2 > N1 may be defined or configured to the UE), the UE may determine that beam ID reporting is for monitoring purpose (i.e., (B), (E)). According to further example embodiments, a larger z2 value may be assumed for data collection purposes ((C) or (F)) than for purposes (B) or (E).

[0211] According to example embodiments related to implicit categorization of z2 values, when the number of reference signal (RS) sets the CSI report is 2 for example and the UE is expected to measure both RS sets, the UE may determine that CSI reporting is for data collection purposes ((C) or (F)). According to further example embodiments, a larger z2 value may be assumed for data collection purposes ((C) or (F)) than for purposes (B) or (E).

[0212] According to example embodiments related to implicit categorization of z2 values, when the number of bits reported in the CSI report exceed N Ibits value (Nlbits represent N1 quantity refers to number of RS measurements which may be defined or configured to the UE), the UE may determine that CSI reporting is for data collection purposes ((C) or (F)) and / or for monitoring purpose ((B) or (E)).

[0213] In the light of the above, according to example embodiments, the priority rules as depicted above may be modified as follows.

[0214] For two overlapping physical uplink shared channels (PUSCH), the priority rules in this clause are applied for physical channels with same priority index if a UE is not configured with enableSTx2PofmDCI or a UE is configured by higher layer parameter PDCCH-Config that contains two different values of coresetPoolIndex in ControlResourceSet and the UE is configured with enableSTx2PofmDCI and the two overlapping PUSCHs are associated with same value of coresetPoolIndex’.

[0215] CSI reports are associated with a priority value Priicsi(y,k,c,s,z2) = 2- Nceiis- Ms-y+ Nceiis- Ms- k-z2+Ms-c+s, where

[0216] - y=0 for aperiodic CSI reports to be carried on PUSCH, y=l for semi-persistent CSI reports to be carried on PUSCH, y=2 for semi-persistent CSI reports to be carried on PUCCH, and y=3 for periodic CSI reports to be carried on PUCCH;

[0217] - k=0 for CSI reports carrying Ll-RSRP or Ll-SINR and k=l for CSI reports not carrying Ll-RSRP or Ll-SINR;

[0218] - c is the serving cell index, and Nceiis is the value of the higher layer parameter maxNrofServingCells;

[0219] - s is the reportConfigID, and Ms is the value of the higher layer pa ra m ete r maxNrofCSI-ReportConfigura tions ;

[0220] - explicit categorization of z2 values:

[0221] ■ z2=offset value between (0, 1), e.g., z2=0.2 when CSI report carrying predicted CSI, z2=offset value between (0, 1), e.g., z2=0.4 when CSI report carrying measurements or performance metric / KPIs for monitoring, where this z2 value is higher than z2 value in CSI carrying predicted CSI, z2=offset value between (0, 1), e.g., z2=0.8 for CSI report carrying measurements for data collection, where this z2 value is higher than z2 value in CSI carrying measurements or performance metric / KPIs for monitoring, z2=offset value between (0, 1), e.g., z2=0.6 for CSI report carrying other quantities than Ll-RSRP or Ll-SINR legacy reports;

[0222] - implicit categorization of z2 values:

[0223] ■ z2=0.2 when a CSI report carrying less than N1 Ll-RSRP or Ll-SINR in one report, z2=0.4 when a CSI report carrying less than N2 but larger than N1 Ll-RSRP, z2=0.8 when a CSI report carrying larger than N2 Ll-RSRP, z2=0.6 when a CSI report carrying other quantities than Ll-RSRP or Ll-SINR legacy reports.

[0224] A first CSI report is said to have priority over second CSI report if the associated Priicsi(y,k,c,s,z2) value is lower for the first report than for the second report.

[0225] FIG. 6 shows a schematic diagram of signaling sequences according to example embodiments, and in particular illustrates a case where a new coefficient parameter (z2 parameter) may be introduced into the formula for priorities (Priicsi(y,k,c,s)) (the newly introduced parameter (z2 parameter) is dedicated for predicted CSI report).

[0226] In a step 1 of FIG. 6, according to example embodiments, a configuration to support beam prediction may be exchanged in CSI-ReportConfig_x. Step 1 of FIG. 4 is associated with the AI / ML-enabled beam prediction, where gNB may provide an RRC configuration to enable the CSI reporting based on the beam prediction at the UE side.

[0227] In steps 2 and 3 of FIG. 6, according to example embodiments, a configuration to support monitoring and data collection may be exchanged in CSI-ReportConfig_y and CSI-ReportConfig_m.

[0228] In other words, steps 1, 2 and 3 of FIG. 6 show CSI reporting configurations which priority rules will be compared with when collision between their reports occurs and also when collision between their reports and CSI reports of any further (not-depicted) configurations occurs.

[0229] In a step 4 of FIG. 6, according to example embodiments, CSI-RS and / or SSB transmission may be associated to CSI-ReportConfig(s). Step 4 of FIG. 6 may be needed to support any beam measurements and CSI calculations, and the UE may expect to receive the DL RSs prior to any beam or CSI reporting. It should be noted that present disclosure does not restrict the sequence or order of step 1 to step 4 in FIG. 6. Configuring or not of step 1 to step 4 depends on gNB, and gNB may configure only part of them which may depend on AI / ML model configuration.

[0230] In a step 5 of FIG. 6, according to example embodiments, the UE may perform AI / ML beam prediction.

[0231] In a step 6 of FIG. 6, according to example embodiments, the UE calculates CSI quantities for active CSI report configuration. Step 6 of FIG. 6 may be performed before steps 7 to 9 of FIG. 6 depending on CSI report becoming applicable for the reporting or not.

[0232] In a step 7 of FIG. 6, according to example embodiments, the UE may determine the z2 parameter at least for each CSI report subject to collision as discussed above. Step 7 of FIG. 6 may impact other steps, where AI / ML- enabled beam prediction-related CSI reporting determines a parameter z2 (as discussed above). Which z2 parameter is determined depends on the configuration of predictions in step 1 to step 4.

[0233] In a step 8 of FIG. 6, according to example embodiments, the UE may determine the priority value Priicsi(y,k,c,s,z2) for each CSI report subject to collision as discussed above based on z2 and other parameters. That is, the z2 values may be further used to determine the priority values in step 8 of FIG. 6 for each CSI report (configured by gNB), where the priority values can be determined as discussed above. The priority values may be subsequently considered in the multiplexing and dropping rules when transmitting the CSI reports in the allocated UL resources.

[0234] In a step 9 of FIG. 6, according to example embodiments, UL resources scheduled for CSI reports are determined under consideration of multiplexing and dropping rules fed with the results of step 8 of FIG. 6. FIG. 7 is a schematic diagram of a procedure according to example embodiments, and in particular illustrates a general processing logic of the UE according to example embodiments.

[0235] In a step S71, according to example embodiments, the UE may receive an RRC message that enables CSI reports corresponding to more than one CSI reporting configurations.

[0236] In a step S72, according to example embodiments, the UE may measure DL RS resources (CSI-RS or SSB) corresponding to one or more CSI reporting configurations.

[0237] In a step S73, according to example embodiments, the UE may calculate CSI for one or more CSI reporting configurations based on the DL RS resource measurements (calculations can be further based on model inference, monitoring, and data collection).

[0238] In a step S74, according to example embodiments, the UE may determine an overlap (at least two CSI reports) in the UL reporting resource.

[0239] In a step S75, according to example embodiments, the UE may, in order to rank different CSI reports, determine the purpose of each CSI report, where the purpose can include at least beam prediction related inference, monitoring, and data collection.

[0240] In a step S76, according to example embodiments, the UE may determine at least parameter "k" in the formula defined for priority value calculation, where "k" is pre-defined (via specification) to the UE and depends on the purpose of each CSI report. Alternatively, the UE may determine at least parameter "zl" in the formula defined for priority value calculation. Still alternatively, the UE may determine at least parameter "z2" in the formula defined for priority value calculation.

[0241] In a step S77, according to example embodiments, the UE calculates priority values for overlapping CSI reports.

[0242] Finally, in a step S78, according to example embodiments, the UE transmits one or more CSI reports in uplink reporting instance based on ranking of the calculated priority values (by multiplexing or dropping CSI reports).

[0243] The above-described procedures and functions may be implemented by respective functional elements, processors, or the like, as described below.

[0244] In the foregoing exemplary description of the network entity, only the units that are relevant for understanding the principles of the disclosure have been described using functional blocks. The network entity may comprise further units that are necessary for its respective operation. However, a description of these units is omitted in this specification. The arrangement of the functional blocks of the devices is not construed to limit the disclosure, and the functions may be performed by one block or further split into sub-blocks.

[0245] When in the foregoing description it is stated that the apparatus, i.e. terminal (or some other means) is configured to perform some function, this is to be construed to be equivalent to a description stating that a (i.e. at least one) processor or corresponding circuitry, potentially in cooperation with computer program code stored in the memory of the respective apparatus, is configured to cause the apparatus to perform at least the thus mentioned function. Also, such function is to be construed to be equivalently implementable by specifically configured circuitry or means for performing the respective function (i.e. the expression "unit configured to" is construed to be equivalent to an expression such as "means for"). In FIG. 8, an alternative illustration of apparatuses according to example embodiments is depicted. As indicated in FIG. 8, according to example embodiments, the apparatus (terminal) 10' (corresponding to the terminal 10) comprises a processor 81, a memory 82 and an interface 83, which are connected by a bus 84 or the like, and the apparatus 10 may be connected via link 85 to another apparatus (e.g. apparatus 800), in particular to an interface of the another apparatus.

[0246] The processor 81 and / or the interface 83 may also include a modem or the like to facilitate communication over a (hardwire or wireless) link, respectively. The interface 83 may include a suitable transceiver coupled to one or more antennas or communication means for (hardwire or wireless) communications with the linked or connected device(s), respectively. The interface 83 is generally configured to communicate with at least one other apparatus, i.e. the interface thereof.

[0247] The memory 82 may store respective programs assumed to include program instructions or computer program code that, when executed by the respective processor, enables the respective electronic device or apparatus to operate in accordance with the example embodiments.

[0248] In general terms, the respective devices / apparatuses (and / or parts thereof) may represent means for performing respective operations and / or exhibiting respective functionalities, and / or the respective devices (and / or parts thereof) may have functions for performing respective operations and / or exhibiting respective functionalities.

[0249] When in the subsequent description it is stated that the processor (or some other means) is configured to perform some function, this is to be construed to be equivalent to a description stating that at least one processor, potentially in cooperation with computer program code stored in the memory of the respective apparatus, is configured to cause the apparatus to perform at least the thus mentioned function. Also, such function is to be construed to be equivalently implementable by specifically configured means for performing the respective function (i.e. the expression "processor configured to [cause the apparatus to] perform xxx-ing" is construed to be equivalent to an expression such as "means for xxx-ing").

[0250] According to example embodiments, an apparatus representing the terminal 10 comprises at least one processor 81, at least one memory 82 including computer program code, and at least one interface 83 configured for communication with at least another apparatus. The processor (i.e. the at least one processor 81, with the at least one memory 82 and the computer program code) is configured to perform determining a transmission priority for a channel state information report based at least in part on whether channel state information to be reported in said channel state information report is associated with one or more measured quantities and / or one or more predicted quantities (thus the apparatus comprising corresponding means for determining or circuitry configured to determine).

[0251] For further details regarding the operability / functionality of the individual apparatuses, reference is made to the above description in connection with any one of FIGs. 1 to 7, respectively.

[0252] For the purpose of the present disclosure as described herein above, it should be noted that

[0253] - method steps likely to be implemented as software code portions and being run using a processor at a network server or network entity (as examples of devices, apparatuses and / or modules thereof, or as examples of entities including apparatuses and / or modules therefore), are software code independent and can be specified using any known or future developed programming language as long as the functionality defined by the method steps is preserved;

[0254] - generally, any method step is suitable to be implemented as software or by hardware without changing the idea of the embodiments and its modification in terms of the functionality implemented; - method steps and / or devices, units or means likely to be implemented as hardware components at the above-defined apparatuses, or any module(s) thereof, (e.g., devices carrying out the functions of the apparatuses according to the embodiments as described above) are hardware independent and can be implemented using any known or future developed hardware technology or any hybrids of these, such as MOS (Metal Oxide Semiconductor), CMOS (Complementary MOS), BiMOS (Bipolar MOS), BiCMOS (Bipolar CMOS), ECL (Emitter Coupled Logic), TTL (Transistor-Transistor Logic), etc., using for example ASIC (Application Specific IC (Integrated Circuit)) components, FPGA (Field-programmable Gate Arrays) components, CPLD (Complex Programmable Logic Device) components or DSP (Digital Signal Processor) components;

[0255] - devices, units or means (e.g. the above-defined network entity or network register, or any one of their respective units / means) can be implemented as individual devices, units or means, but this does not exclude that they are implemented in a distributed fashion throughout the system, as long as the functionality of the device, unit or means is preserved;

[0256] - an apparatus like the user equipment and the network entity / network register may be represented by a semiconductor chip, a chipset, or a (hardware) module comprising such chip or chipset; this, however, does not exclude the possibility that a functionality of an apparatus or module, instead of being hardware implemented, be implemented as software in a (software) module such as a computer program or a computer program product comprising executable software code portions for execution / being run on a processor;

[0257] - a device may be regarded as an apparatus or as an assembly of more than one apparatus, whether functionally in cooperation with each other or functionally independently of each other but in a same device housing, for example.

[0258] In general, it is to be noted that respective functional blocks or elements according to above-described aspects can be implemented by any known means, either in hardware and / or software, respectively, if it is only adapted to perform the described functions of the respective parts. The mentioned method steps can be realized in individual functional blocks or by individual devices, or one or more of the method steps can be realized in a single functional block or by a single device.

[0259] Generally, any method step is suitable to be implemented as software or by hardware without changing the idea of the present disclosure. Devices and means can be implemented as individual devices, but this does not exclude that they are implemented in a distributed fashion throughout the system, as long as the functionality of the device is preserved. Such and similar principles are to be considered as known to a skilled person.

[0260] Software in the sense of the present description comprises software code as such comprising code means or portions or a computer program or a computer program product for performing the respective functions, as well as software (or a computer program or a computer program product) embodied on a tangible medium such as a computer-readable (storage) medium having stored thereon a respective data structure or code means / portions or embodied in a signal or in a chip, potentially during processing thereof.

[0261] The present disclosure also covers any conceivable combination of method steps and operations described above, and any conceivable combination of nodes, apparatuses, modules or elements described above, as long as the above-described concepts of methodology and structural arrangement are applicable.

[0262] In view of the above, there are provided measures for priority control for channel state information reporting. Such measures exemplarily comprise determining a transmission priority for a channel state information report based at least in part on whether channel state information to be reported in said channel state information report is associated with one or more measured quantities and / or one or more predicted quantities. Even though the disclosure is described above with reference to the examples according to the accompanying drawings, it is to be understood that the disclosure is not restricted thereto. Rather, it is apparent to those skilled in the art that the present disclosure can be modified in many ways without departing from the scope of the inventive idea as disclosed herein.

[0263] List of acronyms and abbreviations

[0264] 3GPP Third Generation Partnership Project

[0265] AI / ML artificial intelligence / machine learning

[0266] BM beam management

[0267] CSI channel status information

[0268] DL downlink

[0269] LI layer 1

[0270] Ll-RSRP layer 1 reference signal receiver power

[0271] Ll-SINR layer 1 signal-to-interference plus noise ratio

[0272] LCM life cycle management

[0273] NW network

[0274] OFDM orthogonal frequency-division multiplexing

[0275] PUCCH physical uplink control channel

[0276] PUSCH physical uplink shared channel

[0277] RL reinforcement learning

[0278] RS reference signal

[0279] Rx reception

[0280] Tx transmission

[0281] UE user equipment

Claims

44Claims1. An apparatus comprising: means for determining a transmission priority for a channel state information report based at least in part on whether channel state information to be reported in said channel state information report is associated with one or more measured quantities and / or one or more predicted quantities.

2. The apparatus of claim 1, wherein said means for determining said transmission priority for channel state information associated with one or more predicted quantities is further for determining said transmission priority based at least in part on a reporting category associated with a machine learning model of the one or more predicted quantities.

3. The apparatus of claim 2, wherein the reporting category comprises at least one of the following: inference, or monitoring, or training data collection.

4. The apparatus of any of claims 2-3, further comprising: means for receiving a configuration for said channel state information report, wherein said configuration is indicative of at least one of the following : whether the channel state information report is associated with measured or predicted quantities; or the reporting category of the one or more predicted quantities.

5. The apparatus of claim 1-4, wherein said means for determining the transmission priority for channel state information associated with one or more predicted quantities is further for determining said transmission priority based at least in part on an equation comprising a multiplier or a term,45 wherein said multiplier or term is determined to take a value from a set comprising: a first value for a reporting category associated with a machine learning model of the one or more predicted quantities selected as inference; a second value different than the first value for a reporting category associated with a machine learning model of the one or more predicted quantities selected as monitoring; and a third value different than the second value for a reporting category associated with a machine learning model of the one or more predicted quantities selected as training data collection.

6. The apparatus of claim 5, wherein the first value is 0, the second value is 1, and the third value is 3; or wherein the first value is 0.2, the second value is 0.4, and the third value is 0.8.

7. The apparatus of claim 5, wherein at least one of the first value, the second value and the third value is comprised in the configuration or is preconfigured in the apparatus.

8. The apparatus of claim 1, wherein said means for determining the transmission priority for channel state information associated with one or more predicted quantities is further for determining said transmission priority based at least in part on an equation comprising a multiplier or term, wherein said multiplier or term is determined to at least one of the following: take a first value when a number of quantities in the channel state information report is lower or lower-or-equal to a first threshold and take a second value when the number of quantities in the channel state information report is greater or greater-or-equal to the first threshold; take a third value when the number of quantities in the channel state information report is lower or lower-or-equal to a second threshold and46 take a fourth value when the number of quantities in the channel state information report is greater or greater-or-equal to the second threshold but lower or lower-or-equal to a third threshold and take a fifth value when the number of quantities in the channel state information report is greater or greater-or-equal to the third threshold; take a sixth value when a number of sets associated with the channel state information report is lower or lower-or-equal to a fourth threshold and the apparatus is configured to measure said number of sets, and take a seventh value otherwise; take an eight value when a number of bits associated the quantities encoded into the channel state information report is lower or lower-or-equal to a fifth threshold and take a ninth value when the number of bits is greater or greater-or- equal to the fifth threshold.

9. The apparatus of claim 8, wherein at least one of the following: the number of quantities in the channel state information report is a number of layer 1 reference signal receiver powers reported in the channel state information report; or the number of quantities in the channel state information report is a number of beam IDs reported in the channel state information report; or the number of sets is a number of reference signal sets; or the second value is associated with a reporting category of monitoring or training data collection; or the fifth value is associated with a reporting category of monitoring or training data collection; or the seventh value is associated with a reporting category of training data collection; or the ninth value is associated with a reporting category of monitoring or training data collection.

10. The apparatus of claim 8 or 9, wherein the number of quantities in the channel state information report is a number of layer 1 reference signalreceiver power or layer 1 signal-to-interference plus noise ratio in the channel state information report and one of the following: the third value is 0, the fourth value is 1, and the fifth value is 3; or the third value is 0.2, the fourth value is 0.4, and the fifth value is 0.6.

11. The apparatus of claim 8 or 9, wherein at least one of the values and / or at least one of the thresholds is received in a configuration or is preconfigured in the apparatus.

12. The apparatus according to any of claims 1 to 10, further comprising means for comparing said transmission priority of said channel state information report with a further transmission priority of a further channel state report, and means for controlling to transmit either of said channel state information report and said further channel state information report and to drop the other of said channel state information report and said further channel state information report or to transmit both of said channel state information report and said further channel state information report in a multiplexed manner based on a result of said means for comparing said transmission priority of said channel state information report with said further transmission priority of the further channel state information report.

13. The apparatus according to claim 12, wherein said means for controlling to drop the other of said channel state information report and said further channel state information report based on said result of said means for comparing said transmission priority of said channel state information report with said further transmission priority of the further channel state information report is further for, when said channel state information report is associated with one or more measured quantities and said further channel state information report is associated with one or more predicted quantities, controlling to drop said further channel state information report.

14. A method comprising determining a transmission priority for a channel state information report based at least in part on whether channel state information to be reported in said channel state information report is associated with one or more measured quantities and / or one or more predicted quantities.

15. A computer program product comprising computer-executable computer program code which, when the program is run on a computer, is configured to cause the computer to carry out: determining a transmission priority for a channel state information report based at least in part on whether channel state information to be reported in said channel state information report is associated with one or more measured quantities and / or one or more predicted quantities.

Images