Enhanced processing timeline for ai use cases

Abstract

Systems and method related to a processing timeline for Artificial Intelligence (AI) or inference-based uses cases such as Channel State Information (CSI) prediction and reporting are disclosed. Embodiments of a method performed by a User Equipment (UE) are disclosed. In one embodiment, a method performed by a UE comprises performing one or more actions related to an inference procedure for CSI prediction functionality or feature at one or more certain time instances, respectively, wherein the one or more certain time instances take into consideration an additional processing time related to use of an inference procedure for CSI prediction functionality or feature at the UE. In this manner, uncertainties in processing timeline for AI-based for inference-based CSI reporting can be removed.

Description

ENHANCED PROCESSING TIMELINE FOR Al USE CASES RELATED APPLICATIONS

[0001] This application claims the benefit of U.S. Provisional Patent Application No.63 / 779,767, filed March 28, 2025, the disclosure of which is hereby incorporated herein by reference in its entirety.TECHNICAL FIELD

[0002] The present disclosure relates to a wireless communications network and, more specifically, to enabling additional processing time for actions (e.g., Channel State Information (CSI) computation) for Artificial Intelligence (Al) use cases.BACKGROUND1 LCM operations of AI / ML model and functionality

[0003] An important part in Artificial Intelligence (Al) development and operation is the Lifecycle Management (LCM) of the AI / Machine Learning (ML) model (e.g., model training, model deployment, model inference, model monitoring, model updating) and AI / ML functionality.1.1 Functionality based LCM and Model ID based LCM

[0004] In the 3rdGeneration Partnership Project (3GPP) AI / ML for New Radio (NR) air interface study item, the LCM procedure is studied for the case that an AI / ML model has a model ID with associated information and / or for the case that a given functionality is provided by some AI / ML operations. Two types of LCM operations were studied in 3GPP, functionality-based LCM and model-ID based LCM.

[0005] Functionality refers to an AI / ML-enabled Feature / Feature Group (FG) enabled by configuration(s), where configuration(s) is(are) supported based on conditions indicated by UE capability. Correspondingly, functionality-based LCM operates based on, at least, one configuration of an AI / ML-enabled Feature / FG or specific configurations of an AI / ML-enabled Feature / FG. In functionality -based LCM, the network indicates activation / deactivation / fallback / switching of AI / ML functionality via 3GPP signalling (e.g., Radio Resource Control (RRC), Medium Access Control (MAC)-Control Element (CE), Downlink Control Information (DCI)). Models may not be identified at the network (NW), and the User Equipment (UE) may perform model-level LCM. NW may or may not have the awareness / aboutmodel-level LCM at the UE. For functionality identification, there may be either one or more than one functionalities defined within an AI / ML-enabled feature, whereby AI / ML-enabled feature refers to a feature where AI / ML may be used.

[0006] In model-ID-based LCM, models are identified at the NW, and the NW7UE may activate / deactivate / select / s witch individual AI / ML models via model ID. A model may be associated with specific configurations / conditions associated with UE capability of an AI / ML-enabled Feature / FG and additional conditions (e.g., scenarios, sites, and datasets) as determined / identified between the UE-side and NW-side. An AI / ML model identified by a model ID may be logical, and how it maps to physical AI / ML model(s) may be up to implementation.1.2 Terms

[0007] Model Activation: Model activation refers to enabling an AI / ML model for a specific AI / ML-enabled feature.

[0008] Model Deactivation: Model deactivation refers to disabling an AI / ML model for a specific AI / ML-enabled feature.

[0009] Model Download: Model download refers to model transfer from the network to UE.

[0010] Model Parameter Update: Model parameter update refers to the process of updating the model parameters of a model.

[0011] Model Selection: Model selection refers to the process of selecting an AI / ML model for activation among multiple models for the same AI / ML enabled feature. Note that model selection may or may not be carried out simultaneously with model activation.

[0012] Model Switching: Model switching refers to deactivating a currently active AI / ML model and activating a different AI / ML model for a specific AI / ML-enabled feature.

[0013] Model Update: Model update refers to the process of updating the model parameters and / or model structure of a model.

[0014] Model Upload: Model upload refers to model transfer from UE to the network.

[0015] Two-Sided (AI / ML) Model: A two-sided AI / LM model refers to 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 the UE and then the remaining part is performed by the next generation NodeB (gNB), or vice versa.

[0016] UE-Side (AI / ML) Model: A UE-side AI / ML model is an AI / ML model whose inference is performed entirely at the UE.2 Scenario / Configuration / Site Specific AI / ML Models

[0017] In some use cases, like beam prediction, a single model may not generalize well to multiple scenarios / configurations / sites. In such cases, scenario / configuration specific models may provide performance benefits comparing to a global model.

[0018] Various approaches for achieving good performance across different scenarios / configurations / sites were studied in the 3GPP study item on AI / ML for NR air interface (see 3GPP Technical Report (TR) 38.843 v2.0.1), including- Model generalization, i.e., using a global model that is generalizable to different scenarios / configurations / sites- Model switching, i.e., switching among a group of models where each model is for a parti cul ar scenari o / configurati on / siteo Models in a group of models may have varying model structures, share a common model structure, or partially share a common sub-structure. Models in a group of models may have different input / output format and / or different pre- / post- processing.- Model update, i.e., using one model whose parameters are flexibly updated as the scenario / configuration / site that the device experiences changes over time. Fine-tuning is one example.

[0019] Overhead of Model Switching• Model unloading: The system may need to clear memory and free up resources.• Model loading: The new model is fetched from storage (Random Access Memory (RAM), flash storage) or a cloud / server and loaded into the Al engine.• Re-initialization: Some models require reconfiguring execution pipelines, loading new weights, and setting up inference parameters.3 NR CSI processing unit (CPU) for computing CSI report

[0020] In NR, the concept of NR Channel State Information (CSI) Processing Unit (CPU) was introduced, where the number of CPUs, denoted as NCPU, is equal to the number of simultaneous CSI calculations supported by the UE. The UE indicates NCPUto the NW as part of the UE capability. When the UE is triggered for a CSI report, a certain number of CPUs, denoted as OCPU, will be allocated to the UE from the available CPU pool, which will be occupied for a period of time (measured in symbols). If there are not enough CPUs for a given time instance, the newly triggered CSI report does not need to be calculated by the UE.

[0021] The number of occupied CPUs for a given CSI report depends on the content (configured by higher layer parameter ‘ reportQuantity ’), actually the complexity, for calculating it. The followings options are based on the current 3GPP NR TS 38.214 vl8.5.0,- When "reportQuantity’ is set to ‘none’ and aperiodic Tracking Reference Signal (TRS) is configured, then the TRS is mainly used for time and / or frequency synchronization at the UE, and nothing needs to be reported. In addition, the UE is assumed to have dedicated resources for TRS processing. Therefore, for this case, OCPU= 0.- When "reportQuantity’ is set to beam related parameters, such as ‘cri-RSRP’, ‘ssb-Index- RSRP’, etc., OCPU= 1, since beam related processing is usually not complex.- When "reportQuantity’ is set to non-beam related parameters, such as ‘cri-RI-PMI-CQI’, ‘cri-RI-il’, etc., the CSI report typically occupies as many CPUs as the number of Channel State Information Reference Signal (CSI-RS) resources in the CSI-RS resource set for channel measurement.- When ‘reportQuantity’ is set to 'cri-RI-PMI-CQI' and with codebookType set to 'typell- Doppler-rl8' or 'typeII-Doppler-PortSelection-rl8',o if the corresponding CSI-RS Resource Set for channel measurement is aperiodic and configured with K CSI-RS resources, OCPU= 8 for K = 12 and OCPU= Y4• K for K < 12, where Y4E {1, 2, 3} is reported by UE capability indication, o if the corresponding CSI-RS Resource Set for channel measurement is periodic or semi-persistent and configured with a single CSI-RS resource, OCPU= 4 for N4= 1 and OCPU= max( Y2• N4, 4) for N4> 1, where the value of N4is configured by the higher layer parameter N4, and Y2E {1,2, 3} is reported by UE capability indication,

[0022] The period of time (measured by the number of symbols) for which the CPU is occupied for a given CSI report depends on the time domain behavior of the said CSI report, in general:- For periodic or semi-persistent CSI report (excluding an initial semi-persistent CSI report on Physical Uplink Shared Channel (PUSCH) after the Physical Downlink Control Channel (PDCCH) triggering the report and a semi-persistent CSI report on PUSCH configured with the higher layer parameter codebookType set to 'typeII-Doppler-rl8' or 'typeII-Doppler-PortSelection-rl8'), the CPU is occupied from the first symbol of the earliest CSI-RS / CSI for Interference Measurement (CSI-IM) / Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) Block (SSB) resource for channel or interference measurement, no later than the CSI-RS reference resource, until the lastsymbol of the configured PUSCH / Physical Uplink Control Channel (PUCCH) carrying the report. For the example of CPU occupancy period shown in Figure 1, one CSI-RS resource is configured to the UE for channel measurement (denoted by the first bar), then T' is the CPU occupancy period for periodic or semi-persistent CSI report.- For aperiodic CSI report, the CPU is occupied from the first symbol after the PDCCH triggering the CSI report, until the last symbol of the scheduled PUSCH carrying the report. For the example in Figure 1, T" is the CPU occupancy period for aperiodic CSI report. - An initial semi-persistent CSI report on PUSCH after the PDCCH trigger occupies CPU(s) from the first symbol after the PDCCH until the last symbol of the scheduled PUSCH carrying the report. For the example in Figure 1, T" is the CPU occupancy period for an initial semi-persistent CSI report.- A semi-persistent CSI report on PUSCH configured with the higher layer parameter codebookType set to 'typeII-Doppler-rl8' or 'typeII-Doppler-PortSelection-rl8' occupies CPU(s) from the first symbol of T-th latest consecutive periodic / semi-persistent CSI-RS occasions no later than CSI reference resource, until the last symbol of the PUSCH carrying the report, where the value of KPE {1,2,4} is indicated by UE capability.

[0023] If a CSI-RS resource is referenced N times by one or more CSI Reporting Settings not configured with higher layer parameter csi-ReportSubConfigToAddModList, the CSI-RS resource and the CSI-RS ports within the CSI-RS resource are counted N times.

[0024] For a periodic or semi-persistent CSI-RS resource in a CSI-RS resource set for channel measurement linked to a CSI-ReportConfig configured with the higher layer parameter codebookType set to 'typeII-Doppler-rl8' or 'typeII-Doppler-PortSelection-rl8', the CSI-RS resource and the CSI-RS ports within the CSI-RS resource are counted KPtimes, where the value of KPE {1,2,4} is indicated by UE capability.4 Examples of AI / ML based CSI reporting use cases4.1 AI / ML based time domain CSI prediction using UE-sided models

[0025] One or more AI / ML models can be trained and deployed at a UE for the Al-based CSL prediction feature. Figure 2 provides an example for the inference procedure for CSI prediction using a UE-sided AI / ML model (see 3GPP Technical Report (TR) 38.843 v2.0.1). For generating the input of CSI prediction model, it may need some further pre-processing on the measured channel; for the output of the CSI prediction model, some further post-processing may also be applied.

[0026] During model inference, a UE is configured by the gNB to measure a set of historical CSI-RSs (e.g., the K CSI-RS measurements in the observation window shown in Figure 3) and then report a predicted CSI in the scheduled UL slot for one or multiple future time instances (e.g., the N4future time instances separation in Figure 3) using its AI / ML model. Alternatively, NW may also configure a legacy periodic (P) or semi-persistent (SP) CSI-RS resource for measuring historical CSI and creating model input.4.2 AI / ML based CSI compression using two-sided models

[0027] Figure 4 provides an example for the inference procedure for CSI compression using a two-sided model (see 3GPP TR 38.843 v2.0.1). The two-sided model consists of two parts, i.e., an AI / ML-based CSI generation part to generate the CSI feedback information and an AI / ML-based CSI reconstruction part which is used to reconstruct the CSI from the received CSI feedback information. At least for inference, the CSI generation part is located at the UE side, and the CSI reconstruction part is located at the gNB side.

[0028] Figure 5 illustrates how an autoencoder (AE) might be used for AI / ML-enhanced CSI reporting in NR. The UE measures the channel in the downlink using CSI-RS. The UE estimates the channel for each subcarrier (SC) from each base station transmit (TX) antenna to each UE receive (RX) antenna. The estimate can be viewed as a three-dimensional channel matrix. The 3D channel matrix represents the Multiple Input Multiple Output (MIMO) channel estimated over several SCs and is input to the encoder. However, there are different architectures where a processed version of the 3D MIMO channel, or a processed subset of the information, e.g., singular vectors of the MIMO channel, is input to the encoder.

[0029] The AE encoder is implemented in the UE, and the AE decoder is implemented in the NW, denoted “BS” for base station in the figure. The output of the AE encoder (Al compressed CSI information) is reported from the UE to the NW as a CSI report over the uplink. The Al compressed CSI information can be viewed as a learned latent representation of the channel.4.3 AI / ML based beam management using UE-sided models

[0030] Figure 6 provides an example for the inference procedure for beam management for two Al based beam management cases using UE-sided models:• Beam Management (BM)-Casel: Spatial-domain Downlink beam prediction for Set A of beams based on measurement results of Set B of beams, where Set A and Set B can be different (i.e., Set B is NOT a subset of Set A), or Set B is a subset of Set A. The AI / ML model input may consider: Alt 1): Only Layer 1 (Ll)-Reference Signal Received Power(RSRP) measurement based on Set B; Alt.2): Ll-RSRP measurement based on Set B and assistance information; Alt. 3): Channel Impulse Response (CIR) based on Set B; Alt. 4): Ll-RSRP measurement based on Set B and the corresponding DL Tx and / or Rx beam ID.• BM-Case2: Temporal Downlink beam prediction for Set A of beams based on the historic measurement results of Set B of beams, where Set A and Set B can be different (i.e., Set B is NOT a subset of Set A), or Set B is a subset of Set A, or Set A and Set B are the same. The AI / ML model input is based on measurement results of K (K>1) latest measurement instances with the following alternatives: Alt. 1): Only Ll-RSRP measurement based on Set B; Alt 2): Ll-RSRP measurement based on Set B and assistance information; Alt. 3): Ll-RSRP measurement based on Set B and the corresponding downlink (DL) Tx and / or Rx beam ID. F predictions for F future time instances can be obtained based on the output of AI / ML model, where each prediction is for each time instance, with F>=1.

[0031] For both BM-Casel and BM-Case2, UE can report the prediction result to NW based on the output of a UE-side model (see 3GPP TR 38.843 v2.0.1).4.4 AI / ML based CSLRS overhead reduction using UE-sided models

[0032] Figure 7 shows an example of using a UE-sided model to reduce CSI-RS overhead reduction for CSI acquisition. In this example, it is assumed that the NW deploys Ntantenna ports. For massive MIMO system, the value of Ntis typically very large, hence sounding CSLRS for each of the antenna ports will introduce significant overhead. In light of this, an Al model can be used, whose input is channel measurement based on NRSCSLRS ports, which are transmitted over NRSof the Ntantenna ports. The output of the Al model is then a CSI report associated for all Ntantenna ports. Since NRS< Nt, CSI-RS overhead can be reduced.SUMMARY

[0033] Systems and method related to a processing timeline for Artificial Intelligence (Al) or inference-based uses cases such as Channel State Information (CSI) prediction and reporting are disclosed. Embodiments of a method performed by a User Equipment (UE) are disclosed. In one embodiment, a method performed by a UE comprises performing one or more actions related to an inference procedure for CSI prediction functionality or feature at one or more certain time instances, respectively, wherein the one or more certain time instances take into consideration an additional processing time related to use of an inference procedure for CSI prediction functionalityor feature at the UE. In this manner, uncertainties in processing timeline for Al-based for inference-based CSI reporting can be removed.

[0034] In one embodiment, the additional processing time related to use of an inference procedure for CSI prediction functionality or feature at the UE is in addition to another timing parameter related to the one or more actions.

[0035] In one embodiment, the other timing parameter is a legacy processing time or a processing time defined or configured for a non-inference based functionality or feature corresponding to the inference procedure for CSI prediction functionality or feature.

[0036] In one embodiment, the method further comprises transmitting, to a network node, capability information related to the additional processing time.

[0037] In one embodiment, performing the one or more actions comprises transmitting a CSI report at a certain time that takes into consideration the additional processing time related to use of the inference procedure for CSI prediction at the UE. In one embodiment, the method further comprises receiving, from a network node, information that configures the UE for CSI reporting.

[0038] In one embodiment, the CSI report is a periodic CSI report or a semi-persistent CSI report. In one embodiment, the additional processing time is in addition to a legacy processing time for a periodic or semi-persistent CSI report, wherein the legacy processing time for a periodic or semi-persistent CSI report is a CSI processing unit occupancy time starting from a first symbol of an earliest Channel State Information Reference Signal (CSI-RS), CSI for Interference Measurement (CSI-IM), or Synchronization Signal (SS) / Physical Broadcast Channel (PBCH) Block (SSB) resource for channel or interference measurement, no later than a CSI-RS reference resource, until a last symbol of a configured Physical Uplink Shared Channel (PUSCH) or Physical Uplink Control Channel (PUCCH) carrying an respective CSI report.

[0039] In one embodiment, the CSI report is aperiodic CSI report. In one embodiment, the additional processing time is in addition to a legacy processing time for an aperiodic CSI report, wherein the legacy processing time for an aperiodic CSI report is a CSI processing unit occupancy time starting from a first symbol after a Physical Downlink Control Channel (PDCCH) triggering the aperiodic CSI report until a last symbol of a scheduled PUSCH carrying the aperiodic CSI report.

[0040] In one embodiment, performing the one or more actions comprises transmitting an initial periodic CSI report at a certain time that takes into consideration the additional processing time related to use of the inference procedure for CSI prediction at the UE, wherein the initial periodic CSI report is a first in time periodic CSI report after the UE has received a corresponding periodic CSI report configuration. In one embodiment, the additional processing time is onlyapplied for the initial periodic CSI report and not for subsequent periodic CSI reports corresponding to the periodic CSI report configuration. In one embodiment, performing the one or more actions further comprises applying, for the initial periodic CSI report, the additional processing time to a configured periodicity of the periodic CSI report configuration, thereby determining the certain time at which the initial CSI report is to be transmitted. In one embodiment, the additional processing time is predefined or configured. In one embodiment, the UE receives a separate configuration of an uplink resource for transmission of the initial periodic CSI report where this separate configuration of the uplink resource takes into consideration the additional processing time, and the uplink resource defines or corresponds to the certain time at which the initial periodic CIS report is to be transmitted.

[0041] In one embodiment, performing the one or more actions comprises transmitting a periodic CSI report at a certain time that takes into consideration the additional processing time related to use of the inference procedure for CSI prediction at the UE, wherein the periodic CSI report is any periodic CSI report after the UE has received a corresponding periodic CSI report configuration. In one embodiment, performing the one or more actions further comprises applying, for the periodic CSI report, the additional processing time to a configured periodicity of the periodic CSI report configuration, thereby determining the certain time at which the CSI report is to be transmitted. In one embodiment, the additional processing time is predefined or configured. In one embodiment, the periodicity configured for periodic CSI reporting takes into consideration the additional processing time.

[0042] In one embodiment, performing the one or more actions comprises transmitting an initial semi-persistent CSI report at a certain time that takes into consideration the additional processing time related to use of the inference procedure for CSI prediction at the UE, wherein the initial semi-persistent CSI report is a first in time semi-persistent CSI report after the UE has received a corresponding trigger for the semi-persistent CSI report configuration. In one embodiment, the additional processing time is only applied for the initial semi-persistent CSI report and not for subsequent semi-persistent CSI reports corresponding to the semi-persistent CSI report configuration. In one embodiment, performing the one or more actions further comprises applying, for the initial semi-persistent CSI report, the additional processing time to a configured periodicity of the semi-persistent CSI report configuration, thereby determining the certain time at which the initial semi-persistent CSI report is to be transmitted. In one embodiment, the additional processing time is predefined or configured.

[0043] In one embodiment, performing the one or more actions comprises transmitting an aperiodic CSI report at a certain time that takes into consideration the additional processing timerelated to use of the inference procedure for CSI prediction at the UE. In one embodiment, the method further comprises determining whether one or more criteria for applying the additional processing time for the aperiodic CSI report are satisfied and applying the additional processing time for the aperiodic CSI report upon determining that the one or more criteria are satisfied. In one embodiment, the additional processing time is predefined or configured. In one embodiment, the one or more criteria comprise any one or more of the following: a criterion that the additional processing time is applied for the aperiodic CSI report if a most recently triggered CSI report including inference procedure for CSI prediction has a different report configuration; a criterion that the additional processing time is applied for the aperiodic CSI report if a most recently triggered CSI report including inference procedure for CSI prediction has a different report configuration and the most recently triggered CSI report including inference procedure for CSI prediction is associated with a same inference based functionality or feature; a criterion that the additional processing time is applied for the aperiodic CSI report if a most recently triggered CSI report including inference procedure for CSI prediction is associated to a different inference based functionality or feature but shares the same hardware resources for inference of CSI; and a criterion that the additional processing time is applied for the aperiodic CSI report if a most recently triggered CSI report includes non-inference based CSI but shares the same hardware resources for inference of CSI.

[0044] In one embodiment, the method further comprises transmitting, to a network node, a request for additional processing time for one or more actions related to the inference procedure based CSI prediction functionality or feature.

[0045] Corresponding embodiments of a UE are also disclosed. In one embodiment, a UE comprises a communication interface comprising a transmitter and a receiver. The UE further comprises processing circuitry associated with the communication interface. The processing circuitry is configured to cause the UE perform one or more actions related to an inference procedure for CSI prediction functionality or feature at one or more certain time instances, respectively, wherein the one or more certain time instances take into consideration an additional processing time related to use of an inference procedure for CSI prediction functionality or feature at the UE.

[0046] Embodiments of a method performed by a network node are also disclosed. In one embodiment, a method performed by a network node comprises performing one or more actions that enable a UE to perform one or more actions related to an inference procedure for CSI prediction functionality or feature at one or more certain time instances, respectively, wherein theone or more certain time instances take into consideration an additional processing time related to use of an inference procedure for CSI prediction functionality or feature at the UE.

[0047] Corresponding embodiments of a network node are also disclosed. In one embodiment, a network node comprises processing circuitry configured to cause the network node to perform one or more actions that enable a UE, to perform one or more actions related to an inference procedure for CSI prediction functionality or feature at one or more certain time instances, respectively, wherein the one or more certain time instances take into consideration an additional processing time related to use of an inference procedure for CSI prediction functionality or feature at the UE.BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawing figures incorporated in and forming a part of this specification illustrate several aspects of the disclosure, and together with the description serve to explain the principles of the disclosure.

[0049] Figure 1 illustrates legacy Channel State Information (CSI) Processing Unit (CPU) occupancy times for periodic, semi-persistent, and aperiodic CSI computation and reporting as defined in legacy 3rdGeneration Partnership Project (3GPP) New Radio (NR) specifications.

[0050] Figure 2 provides an example for the inference procedure for CSI prediction using a User Equipment (UE)-sided Artificial Intelligence (AI) / Machine Learning (ML) model (see 3GPP Technical Report (TR) 38.843 v2.0.1).

[0051] Figure 3 illustrates an exemplary observation window for model inference comprising K Channel State Information Reference Signal (CSLRS) measurements.

[0052] Figure 4 provides an example for the inference procedure for CSI compression using a two-sided model (see 3GPP TR 38.843 v2.0.1).

[0053] Figure 5 illustrates how an autoencoder (AE) might be used for AI / ML-enhanced CSI reporting in NR.

[0054] Figure 6 provides an example for the inference procedure for beam management for two Al based beam management cases using UE-sided models.

[0055] Figure 7 shows an example of using a UE-sided model to reduce CSI-RS overhead reduction for CSI acquisition.

[0056] Figure 8 illustrates an example of including an additional processing time, 6T, only for an initial Periodic (P) CSI report, in accordance with embodiments of the present disclosure.

[0057] Figure 9 illustrates an alternative way of configuring an Al-based P CSI report, in accordance with another embodiment of the present disclosure.

[0058] Figure 10 shows an example of including an additional processing time, 6T, only in an initial Semi -Persistent (SP) CSI report, where T' is the legacy processing time for an initial SP CSI report that starts from the triggering of the SP report, while T is the legacy processing time for the remaining SP CSI reports, in accordance with an embodiment of the present disclosure.

[0059] Figure 11 illustrates an example of including an additional processing time, 6T, in Aperiodic (AP) CSI reports, in accordance with an embodiment of the present disclosure.

[0060] Figure 12 illustrates an example where a User Equipment (UE) requests additional processing time in accordance with an embodiment of the present disclosure.

[0061] Figure 13 illustrates the operation of a UE and a network node, in accordance with at least some of the embodiments described herein.

[0062] Figure 14 illustrates step 1308 of Figure 13 in more detail for an exemplary embodiment in which the action(s) performed in step 1308 is(are) for periodic CSI reporting of AI / ML based CSI.

[0063] Figure 15 illustrates step 1308 of Figure 13 in more detail for an exemplary embodiment in which the action(s) performed in step 1308 is(are) for semi-persistent CSI reporting of AI / ML based CSI.

[0064] Figure 16 illustrates step 1308 of Figure 13 in more detail for an exemplary embodiment in which the action(s) performed in step 1308 is(are) for aperiodic CSI reporting of AI / ML based CSI.

[0065] Figure 17 shows an example of a communication system in accordance with some embodiments.

[0066] Figure 18 is another example of a communication system according to some embodiments.

[0067] Figure 19 shows a wireless device (e.g., UE), which may be configured to operate in communication system of Figure 17 or in communication system of Figure 18.

[0068] Figure 20 shows a network node in accordance with some embodiments.

[0069] Figure 21 is a block diagram illustrating a virtualization environment in which functions implemented by some embodiments may be virtualized.DETAILED DESCRIPTION

[0070] The embodiments set forth below represent information to enable those skilled in the art to practice the embodiments and illustrate the best mode of practicing the embodiments. Upon reading the following description in light of the accompanying drawing figures, those skilled in the art will understand the concepts of the disclosure and will recognize applications of theseconcepts not particularly addressed herein. It should be understood that these concepts and applications fall within the scope of the disclosure.

[0071] Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art.

[0072] There currently exist certain challenge(s). When Artificial Intelligence (Al) is used in a User Equipment (UE) for certain functionality (e.g., Channel State Information (CSI) prediction), the corresponding Al model(s) usually needs to be loaded into a specialized processing unit, e.g., an Al engine. In addition, if the UE needs to change Al models between different functionalities, e.g., from CSI prediction to beam prediction, or even within the same functionality (e.g., change different models suited for different scenarios), a first Al model may need to be unloaded before a second Al model can be loaded into the Al engine due to the UE’s hardware and / or memory limitations. All of this may introduce additional time needed for inference.

[0073] Note that it may be up to UE implementation to decide whether a UE uses a global AI / Machine Learning (ML) model that is capable of generalizing to different scenarios and / or configurations for an Al-based functionality or feature or the UE uses multiple AI / ML models with each model associated to a certain scenario / configuration. This implies that model switching within an AI / ML based functionality at a UE may be transparent to the network. In some cases, using an Al model may reduce the required time for inference, compared to using a non- Al based technique. For example, generating a predicted CSI report with an Al model can be faster than with a non- Al based technique, such as a Kalman filter. All the above will introduce uncertainties in the required time for achieving a certain functionality (e.g., calculating a predicted CSI report).

[0074] How to remove the above uncertainties to make sure the processing time is commonly known by the network and the UE is a problem that needs to be addressed.

[0075] Certain aspects of the disclosure and their embodiments may provide solutions to these or other challenges. Systems and methods are disclosed herein for defining additional processing time, which can be used to account for loading and / or unloading an Al model etc. Detailed embodiments are proposed for integrating the additional processing time into the Channel State Information (CSI) processing timeline for Al-based CSI reports with different time domain behaviors.

[0076] Embodiments of the solution(s) described herein may include any one or more of the following aspects:a single additional processing timeo Methods to integrate the additional processing time in CSI processing timeline, for periodic, semi-persistent and aperiodic CSI reporttwo additional processing timeso Methods to integrate the two additional processing times in CSI processing timeline.UE initiated requesting of additional processing timeRelated UE capability reporting

[0077] Certain embodiments may provide one or more of the following technical advantage(s). Embodiments of the proposed solution(s) offer a simple way of removing uncertainties in processing timeline for Al-based CSI reporting.

[0078] Now, a more detailed description of embodiments of the present disclosure will be provided.

[0079] When an Al model is used to achieve a functionality, e.g., calculating CSI according to a network (NW) configuration, the processing time can be different compared to using a non-AI approach for calculating CSI with the same configuration. Examples of Al based CSI reporting features include Al based CSI prediction using UE-side model(s), Al based CSI compression using two-sided model(s), Al based spatial beam prediction using UE-side model(s), Al based temporal beam prediction using UE-side model(s), Al based reference signal (RS) overhead reduction for CSI reporting using UE-side model(s), etc.

[0080] Herein, a functionality can be, for example, associated with a feature (e.g., CSI prediction and beam prediction are two functionalities) or a feature group within a feature (e.g., CSI prediction with N4= 1 and CSI prediction with N4= 4 are two feature groups within the CSI prediction feature). Alternatively, a functionality can be associated with a UE feature, e.g., CSI prediction with N4= 1 and CSI prediction with N4= 4 can be two UE features.

[0081] The difference in processing time between using an Al and a non-AI approach to achieve a functionality may be due to any one or more of the following aspects:• Model Loading: An Al model (also sometimes referred to herein as an AI / ML model) may need to be loaded onto dedicated hardware, such as an Al engine, Graphics Processing Unit (GPU), or specialized accelerators. This loading process itself can introduce latency, particularly if the model is large or needs to be fetched from external storage or network resources.Model Unloading: The dedicated hardware for Al may have limited memory and computational resources, which can restrict the number of Al models that can be loadedsimultaneously. As a result, if the hardware is already running a first model and a second model needs to be used, the first model may need to be unloaded first.• Inference Time: Taking CSI prediction as an example, to generate a predicted CSI, the inference time between using Al and non- Al approach can be different, as the computation and hardware can be quite different.

[0082] All the above, and potentially also other factor(s), will introduce uncertainties in the required time for achieving a certain functionality (e.g., calculating a predicted CSI report).

[0083] In embodiments of the solution(s) described herein, additional processing time related parameter(s) are introduced in order to remove the uncertainties in the required time for achieving a certain functionality (e.g., uncertainties in CSI calculation timeline) when an Al model is used for achieving this functionality.

[0084] Here, “processing time” refers to as the occupation time of a processing unit (e.g., a CSI processing unit (CPU) as defined per 3GPP Technical Specification (TS) 38.214 (see, e.g., VI 8.6.0), or an Al processing unit that might be defined for Al-related functionalities) for achieving a certain functionality (e.g., calculating a predicted CSI report).

[0085] In one embodiment, a single additional processing time is introduced, e.g., in 3GPP specifications, on top of a legacy processing time (e.g., the processing time defined in legacy 3GPP New Radio (NR)). The single processing time, denoted as 6Tin the present disclosure, can be used to account for the time needed for loading an Al model to a dedicated hardware. Depending on how an Al-based CSI report is configured and / or triggered, 6Tmay or may not be accounted for in the timeline.

[0086] Some embodiments for Periodic (P) CSI reporting are as follows.

[0087] In one embodiment, when a periodic (P) CSI report is configured for an Al-based CSI reporting feature, 6Tis only added in the processing time for generating an initial periodic CSI report after the Radio Resource Control (RRC) configuration of the report.

[0088] An example of including an additional processing time, 6T, only in the initial P CSI report is shown in Figure 8, where T is the legacy processing time for a P CSI report. An additional processing time, 6T, is added only in the initial CSI report of a P CSI report. This is because after the model is loaded for generating the first CSI report, the same model can be used for generating the subsequent CSI reports.

[0089] In Figure 8, the bar with dashed outline is the initial CSI report if a legacy non-AI based P CSI report is configured. It is hypothetical and is included here for illustration purpose only. As can be seen, one problem with the new timeline is that the uplink (UL) resource, e.g., Physical Uplink Control Channel (PUCCH) or Physical Uplink Shared Channel (PUSCH), forcarrying the report has to be periodic and is already configured in the RRC (with periodicity T). Hence, when the new timeline is introduced for P CSI report, the UL resource for carrying the initial / first Al CSI report is allocated separately compared to the remaining reports.

[0090] In one embodiment, the UL resource for carrying the initial P CSI report is separately configured compared to the remaining P CSI report.

[0091] In another embodiment, the UL resource for carrying a P CSI report is configured with periodicity T. In addition, the UL resource for carrying the initial P CSI report is offset by 8T, where 8Tfor example can be configured by the NW in CSI resource configuration or CSI report configuration.

[0092] An alternative way of configuring Al-based P CSI report is illustrated in Figure 9, where the additional processing time 8Tis added in the processing timeline for generating every P CSI report. The benefit of this alternative is that there is no need to separate configure an UL resource for carrying the initial P CSI report.

[0093] Some exemplary embodiments for Semi-Persistent (SP) CSI reporting are as follows.

[0094] In one embodiment, when a semi-persistent (SP) CSI report is configured and triggered for an Al-based CSI reporting feature, 8Tis only added in the processing time for generating an initial SP CSI report after the Physical Downlink Control Channel (PDCCH) triggering the report. This is similar to the case with P CSI report. Figure 10 shows an example for this case (i.e., an example of including an additional processing time, 8T, only in the initial SP CSI report), where T' is the legacy processing time for an initial SP CSI report that starts from the triggering of the SP report, while T is the legacy processing time for the remaining SP CSI reports. An additional processing time, 8T, is added only in the initial CSI report of the SP CSI report. This is because after the model is loaded for generating the initial CSI report, the same model can be used for generating the remaining CSI reports.

[0095] The NW is expected to trigger the SP Al-based CSI report at least T' + 8Ttime units (e.g., slots, Orthogonal Frequency Division Multiplexing (OFDM) symbols) before the uplink (UL) resource for carrying the initial SP report. If the time between the triggering of the SP CSI report and the initial SP report, the UE is not expected to report the initial CSI report.

[0096] Some exemplary embodiments for Aperiodic (AP) CSI reporting are as follows.

[0097] When an AP CSI report is triggered for an Al based CSI reporting feature, how to account for the additional processing time may depend on the most recent triggered CSI report.

[0098] In one embodiment, when an aperiodic (AP) CSI report is configured and triggered for an Al based CSI reporting feature, 8Tis added in the processing time after the PDCCH triggering the report, only if the most recent triggered ALCSI report has a different report configuration. Ina dependent embodiment, the most recent triggered CSI report is an Al-based CSI report associated with the same Al based CSI reporting feature.

[0099] In another dependent embodiment, the most recent triggered CSI reporting is an AI-based CSI report associated with a different Al based CSI reporting feature but shares the same processing unit pool or hardware resources for CSI processing.

[0100] In another dependent embodiment, the most recent triggered CSI report is a legacy non-AI based CSI report and the Al based AP CSI report shares the same processing unit pool or hardware resources with the non-AI based legacy CSI report for CSI processing.

[0101] An example of including an additional processing time, 6T, in AP CSI reports is shown in Figure 11. In Figure 11 (a), the first and the second AP CSI reports have the same report configuration. Hence, 6Tis only added in the processing time for the first AP CSI report, since the second AP CSI report can continue using the already loaded model. In Figure 11 (b), the first and the second AP CSI reports have different report configurations, e.g., with different reporting quantities such as predicted PMI and predicted beam, or with different codebook parameters such as N4= 1 and N4= 4 for CSI prediction. Hence, both the first and the second AP CSI reports need to add 6Tin the processing time.

[0102] In some embodiments, 6Tis added in the processing time after the PDCCH triggering the report, if an RRC reconfiguration has happened since the last CSI report.

[0103] In another embodiment, 6Tis added in the processing time after the PDCCH triggering the report, if the UE has received a CSI report (re)configuration, serving cell activation, or bandwidth part (BWP) change (e.g., since the last aperiodic CSI report).

[0104] In another embodiment, 6Tis added in the processing time after the PDCCH triggering the report, if the time since the last aperiodically triggered CSI report is larger than a threshold.

[0105] In some other embodiments, two additional processing times, a first one being <5T(same as above) and a second one being <5^, are also introduced (e.g., in 3GPP specifications) on top of the legacy processing time (e.g., the processing time defined in legacy NR). The use of these two additional processing times is useful, for example, when a UE needs to unload an Al model that has already been loaded onto the deliciated hardware for Al, before it can load a new model. This could happen if the dedicated hardware for Al has limited memory, resources, etc.

[0106] In one embodiment, the second additional processing time, <5^, is added in the processing time for generating a CSI report, if the most recent CSI report is an Al-based CSI report, which has a different CSI report configuration compared to the current CSI report.

[0107] In another embodiment, the second additional processing time, <5^, is added in the processing time for generating a CSI report, if there exist an Al-based CSI report in the past Ntime units (a time unit can be a slot, an OFDM symbol, etc.), which has a different CSI report configuration compared to the current CSI report.

[0108] In a related embodiment, the value of N is predefined (e.g., specified in 3GPP specifications).

[0109] In another embodiment, the value of N is reported by the UE as part of UE capability reporting.

[0110] In some embodiments, a UE may request additional processing time on a need basis. For example, even if the CSI report configuration is not changed, the UE may experience different channel variations due to mobility or change of surrounding environment. If the UE has designed multiple Al models for the same CSI report configuration, due to the channel variation, the UE may want to switch to another model, which will require additional processing time for loading the other model. In this case, the UE may send a request to the NW for additional processing time, 8a. If the requested processing time is granted by the NW, it can be added to the processing time for the next CSI report. An example where UE requests additional processing time is shown in Figure 12, where after the second CSI report, the UE sends a request to the NW for additional processing time. After the NW granted this request, the UE can add the granted additional processing time <5a, for the third CSI report.[OHl] A UE may be deployed with a single model for an Al-based CSI reporting feature or feature group. In this case, even if the CSI reporting configuration has changes (e.g., with different codebook parameters such as N4= 1 and N4= 4 for CSI prediction), there is no need for the UE to switch models; hence, no additional time is needed for CSI processing. Hence, in one set of embodiments, when an CSI report is configured and triggered for an Al based CSI reporting feature, 6Tis added in the processing time after the CSI report triggering, only if the most recent triggered CSI report is associated to a different Al-based CSI reporting feature or feature group. In a dependent embodiment, the CSI report is a SP CSI report or an AP CSI report.

[0112] For an Al-based CSI reporting feature or feature group, a UE may be deployed with multiple models, with each model associated with a certain scenario, a network-side configuration (e.g., a NW Tx beam configuration, NW Tx power level), a UE condition (e.g., an UE energy / power level, a UE speed range), and / or a channel condition. Whether to perform a model switching is decided by the UE, based on some assistance information provided by the NW if needed. In such case, a UE may perform model switching even under the same CSI report configuration, or a UE may not perform model switching even the CSI report configuration has changed. Hence, in another set of embodiments, when an aperiodic (AP) CSI report is configured and triggered for an Al based CSI reporting feature, 6Tis added in the processing time after thePDCCH triggering the report, only if the most recent triggered CSI report is associated to a different Al-based CSI reporting feature or the NW received an request from the UE.

[0113] In one embodiment, the additional processing time, 6Tand / or 6T, when applicable, is reported by the UE as part of the UE capability reporting.

[0114] In one embodiment, the required processing time for an Al-based functionality is defined relative to the required processing time for the corresponding non-AI-based functionality.

[0115] For example, for CSI prediction (UE reporting predicted PMI according the Rel-18 eType II doppler codebook), both non-AI and Al based CSI reports are supported. Assuming that the minimum processing time for the non-AI CSI report is given by Z' symbols, then the corresponding minimum processing time for the Al CSI report is given by Z' — 6Z> symbols, where 6Z> > 0. Thus, this means that the Al can reduce the required processing time for inference.

[0116] Figure 13 illustrates the operation of a UE 1300 and a network node 1302, in accordance with at least some of the embodiments described above. Optional steps are represented by dashed lines / boxes. The network node 1302 may be, for example, a Radio Access Network (RAN) node such as, e.g., a base station (e.g., a gNB in the case of NR or a 6thGeneration (6G) base station, or a network node that implements part of the functionality of a base station (e.g., a Central Unit (CU) such as a gNB-CU or a Distributed Unit (DU) such as a gNB-DU in a CU-DU split architecture).

[0117] As illustrated, the UE 1300 optionally transmits, to the network node 1302, capability information (step 1304). Examples of such capability information are described above, and those examples are equally applicable here to the description of Figure 13.

[0118] The UE 1300 may receive, from the network node 1302, information that configures the UE to provide an AI / ML model functionality or feature (i.e., an inference based functionality or feature) such as, for example, periodic, semi-persistent, or aperiodic CSI reporting where the reported CSI is generated, at least partially, using an AI / ML model (i.e., is Al-based CSI, i.e., inference based CSI) (step 1306).

[0119] The UE 1300 performs one or more actions related to the AI / ML model functionality or feature at one or more respective time instances that take into consideration an additional processing time (or more than one additional processing time) related to use of an AI / ML model (e.g., inference procedure for CSI prediction) at the UE 1300 (step 1308). The additional processing time is <5Tin accordance with any of the embodiments described above. Further, in some embodiments, there may be a second additional time <5^, as also described above. As described in the exemplary embodiments above, in some embodiments, the certain action performed is transmission of a periodic, semi-persistent, or aperiodic CSI report(s) at certain timeinstance(s) that take into consideration the additional processing time 6Tand, in some embodiments, the second additional time 8T' . The details provided above in relation to such CSI transmission are equally applicable here to step 1308 of Figure 13. Note that while AI / ML based CSI and corresponding CSI reporting are the focus of many of the embodiments described above, the present disclosure is not limited thereto. The solution(s) described here are applicable to any AI / ML model functionality or feature in which the UE 1300 uses an AI / ML model to provide certain information and is then to perform an action using this information at a certain time, e.g., a certain time relative to a reference time for the action such as, e.g., the time at which a triggering event for the action occurred or the time at which a certain reference signal(s) to be used as input to the AI / ML model or to derive an input(s) to the AI / ML model is received by the UE 1300.

[0120] In some embodiments, the UE 1300 may send, to the network node 1302, a request for additional processing time (step 1310) and receive, from the network node 1302, a grant for the additional processing time (step 1312). The request may be a general request for additional processing time or may include information that explicitly or implicitly indicates the amount of additional processing time requested. The UE 1300 may then perform an action(s) related to the AI / ML model functionality or feature at a certain time instance(s) that takes into consideration the requested additional processing time (or the granted additionally processing time which may be the same or different than the requested additional processing time) (step 1314). This action(s) may be, for example, periodic, semi-persistent, or aperiodic CSI reporting. Note that while steps 1310-1314 are shown in Figure 13 as optionally being performed in addition to step 1308, the present disclosure is not limited thereto. In another embodiment, steps 1310-1312 may be performed without step 1308.

[0121] Figures 14, 15, and 16 illustrate exemplary embodiments of step 1308 in which the action(s) performed in step 1308 is the transmission of a periodic CSI report(s) (Figure 14), transmission of a semi-persistent CSI report(s) (Figure 15), or transmission of an aperiodic CSI report (Figure 16). Details of various embodiments related to periodic, semi-persistent, and aperiodic CSI reporting are provided above and those details are equally applicable here to the description of Figures 14, 15, and 16.

[0122] In this regard, Figure 14 illustrates step 1308 of Figure 13 in more detail for an exemplary embodiment in which the action(s) performed in step 1308 is(are) for periodic CSI reporting of AI / ML based (i.e., inference based) CSI. Figure 14 illustrates two options, namely, “Option A” and “Option B” each having two sub-options. In Option A, the additional processing time related to use of an AI / ML model at the UE 1300 is applied by the UE 1300 for only the initial periodic CSI report after receiving configuration (e.g., RRC configuration) of the periodicCSI reporting. In a first sub-option (“Sub-Option 1”) of Option A, the UE 1300 applies a defined or configured additional processing time (e.g., <5T) to a configured periodicity T for the periodic CSI reporting for only the initial periodic CSI report, thereby determining the certain time instance at which the initial periodic CSI report is to be transmitted (step 1400A1-1). An example of this is illustrated in Figure 8 described above. The UE 1300 transmits the initial periodic CSI report at the determined certain time instance (step 1400A1-2). The UE 1300 may thereafter transmit additional periodic CSI reports without applying the additional processing time for those additional periodic CSI reports (step 1400A1-3). In a second sub-option (“Sub-Option 2”) of Option A, a separate UL resource is configured to the UE 1300 by the network node 1302 (e.g., in step 1306 or an separate configuration signaling) for the initial periodic CSI report and, as such, the UE 1300 transmits the initial periodic CSI report on this configured UL resource (step 1400A2-1). This separate UL resource may be determined by the network 1302 in a manner that takes into consideration the additional processing time. While not illustrated, the UE 1300 may then continue to transmit additional CSI reports in accordance with the periodic CSI reporting configuration.

[0123] In Option B, the UE 1300 applies the additional processing time for all of the periodic CSI reports. In Sub-Option 1 of Option B, the UE 1300 transmits the periodic CSI reports at corresponding certain time instances determined by applying a defined or configured additional processing time to a configured periodicity (T) for the periodic CSI reporting for all of the periodic CSI reports (step 1400B1-1). In Sub-Option 2 of Option B, the UE 1300 transmits the periodic CSI reports in accordance with the configured periodicity (T) for the periodic CSI reporting for all of the periodic CSI reports, but where the configured periodicity (T) includes the additional processing time (step 1400B2-1).

[0124] Figure 15 illustrates step 1308 of Figure 13 in more detail for an exemplary embodiment in which the action(s) performed in step 1308 is(are) for semi-persistent CSI reporting of AI / ML based (i.e., inference based) CSI. As illustrated, the UE 1300 applies a defined or configured additional processing time (e.g., <5T) to a configured periodicity (T) for the semi-persistent CSI reporting for an initial semi-persistent CSI report, thereby determining the certain time instance at which the initial semi-persistent CSI report is to be transmitted (step 1500). Further details are provided above and are equally applicable here. The UE 1300 then transmits the initial semi-persistent CSI report at the determined time instance (step 1502). The UE 1500 may then continue semi-persistent CSI reporting (e.g., without applying the additional processing time) (step 1504).

[0125] Figure 16 illustrates step 1308 of Figure 13 in more detail for an exemplary embodiment in which the action(s) performed in step 1308 is(are) for aperiodic CSI reporting ofAI / ML based (i.e., inference based) CSI. As illustrated, the UE 1300 detects a triggering for an aperiodic CSI report (e.g., reception of a PDCCH or DCI from the network node 1302 that triggers the aperiodic CSI report) (step 1600). The UE 1300 determines whether one or more criteria for applying the additional processing time are satisfied (step 1602). Various examples of such criteria are described above. One example is that the UE 1300 determines that the additional processing time is to be applied only if the most recent triggered CSI report including AI / ML based CSI has a different CSI reporting configuration. Further examples are provided above and are equally applicable here. As another example, the one or more criteria comprise any one or more of the following:• a criterion that the additional processing time is applied for the aperiodic CSI report if (e.g., only if) a most recently triggered CSI report including AI / ML based CSI has a different report configuration;• a criterion that the additional processing time is applied for the aperiodic CSI report if (e.g., only if) a most recently triggered CSI report including AI / ML based CSI has a different report configuration and the most recently triggered CSI report including AI / ML based CI is associated with a same AI / ML model functionality or feature (i.e., a same AI / ML based CSI reporting feature);• a criterion that the additional processing time is applied for the aperiodic CSI report if a most recently triggered CSI report including AI / ML based CSI is associated to a different AI / ML model functionality or feature (e.g., a different AI / ML based CSI reporting feature) but shares the same hardware resources (e.g., the same processing unit pool or other hardware resources) for AI / ML model inference of CSI;• a criterion that the additional processing time is applied for the aperiodic CSI report if a most recently triggered CSI report includes non-AI / ML based CSI but shares the same hardware resources (e.g., the same processing unit pool or other hardware resources) for AI / ML model inference of CSI.If the UE determines that the additional processing time is to be applied, the UE 1300 applies the additional processing time to determine the certain time instance when the aperiodic CSI report is to be transmitted (step 1606). Otherwise, if the UE 1300 determines that the additional processing time is not to be applied, the UE 1300 determines the time at which the aperiodic CSI is to be transmitted without applying the additional processing time. The UE 1300 then transmits the aperiodic CSI report at the determined time instance (step 1608).

[0126] Figure 17 shows an example of a communication system 1700 in accordance with some embodiments. Note that the UE described in the various embodiments above (e.g., the UE1300) may be, for example, one of the UEs 1712 of Figure 17. Further, the network node described in the various embodiments above (e.g., the network node 1302) may be, for example, one of the access network nodes 1710 of Figure 17.

[0127] In the example, the communication system 1700 includes a telecommunications network 1702 that includes an access network 1704, such as a radio access network (RAN), and a core network 1706, which includes one or more core network nodes 1708. The access network 1704 includes one or more access network nodes or base stations of various types, access network nodes 1710A and 1710B are depicted (which may be collectively referred to as network nodes 1710), or any other similar 3rdGeneration Partnership Project (3GPP) access nodes or non-3GPP access points (APs). Some embodiments of the access network 1704 may include more than one access network technology. The network nodes 1710 of access network 1704 facilitate direct or indirect connection of wireless devices, also referred to as user equipments (UEs), such as by connecting UEs 1712A, 1712B, 1712C, and 1712D (one or more of which may be generally referred to as UEs 1712) to the core network 1706 over one or more wireless connections.

[0128] Moreover, a network node is not necessarily limited to an implementation in which a radio portion and a baseband portion are supplied and integrated by a single vendor. Thus, it will be understood that network nodes include disaggregated implementations or portions thereof. For example, in some embodiments, the telecommunications network 1702 includes one or more Open-RAN (ORAN) network nodes. An ORAN network node is a network node in the telecommunications network 1702 that supports an ORAN specification (e.g., a specification published by the O-RAN Alliance, or any similar organization) and may operate alone or together with other network nodes to implement one or more functionalities of any network node in the telecommunications network 1702, including one or more access network nodes 1710 and / or core network nodes 1708.

[0129] Examples of an ORAN network node include an open radio unit (O-RU), an open distributed unit (O-DU), an open central unit (O-CU), including an O-CU control plane (O-CU-CP) or an O-CU user plane (O-CU-UP), a RAN intelligent controller (near-real time or non-real time) hosting software or software plug-ins, such as a near-real time control application (e.g., xApp) or a non-real time control application (e.g., rApp), or any combination thereof (the adjective “open” designating support of an ORAN specification). An ORAN network node may support a specification by, for example, supporting an interface defined by the ORAN specification, such as an Al, Fl, Wl, El, E2, X2, Xn interface, an open fronthaul user plane interface, or an open fronthaul management plane interface. Moreover, an ORAN network node may be a logical node in a physical node. Furthermore, an ORAN network node may be implemented in a virtualizationenvironment (described further below) in which one or more network functions are virtualized. For example, the virtualization environment may include an O-Cloud computing platform orchestrated by a Service Management and Orchestration Framework via an 0-2 interface defined by the 0-RAN Alliance or comparable technologies.

[0130] The network nodes 1710 facilitate direct or indirect connection of one or more UEs 1712 to the core network 1706 over one or more wireless connections. Example wireless communications over a wireless connection include transmitting and / or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and / or other types of signals suitable for conveying information without the use of wires, cables, or other material conductors. Moreover, in different embodiments, the communication system 1700 may include any number of wired or wireless networks, network nodes, UEs, and / or any other components or systems that may facilitate or participate in the communication of data and / or signals whether via wired or wireless connections. The communication system 1700 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.

[0131] The UEs 1712 may be any of a wide variety of communication devices, including wireless devices arranged, configured, and / or operable to communicate wirelessly with the network nodes 1710 and other communication devices. Similarly, the network nodes 1708, 1710 are arranged, capable, configured, and / or operable to communicate directly or indirectly (e.g., via other devices of telecommunications network 1702) with the UEs 1712 and / or with other network nodes or equipment in the telecommunications network 1702 to enable and / or provide network access, such as wireless network access, and / or to perform other functions, such as administration in the telecommunications network 1702. More specifically, UEs 1712 may send messages, data, and / or other signals to network nodes 1708, 1710 or other elements of the telecommunications network 1702 by transmitting such signals to the relevant device directly without the signals passing through any intervening devices or by transmitting such signals to the relevant device indirectly through an intervening device (or multiple intervening devices) that then transmit the signal to the relevant device. Similarly, network nodes 1708, 1710 may send messages, data, and other signals to UEs 17122, other network nodes 1708, 1710, and other devices in telecommunications network 1702 directly or indirectly. As one specific example, a core network node 108 may transmit a particular message to a UE 1712 by transmitting the message to an access network node 1710 that will then transmit the message to the intended UE 1712. Similarly, a core network node 108 may receive a particular message from a UE 1712 by receiving the message from an access network node 1710 that itself received the message from the UE 1712.

[0132] In the depicted example, the core network 1706 connects elements of the access network 1704 (e.g., one or more of the network nodes 1710) to one or more host computing systems, such as host 1716. These connections may be direct or indirect via one or more intermediary networks or devices. In other examples, network nodes may be directly coupled to hosts. The core network 1706 includes one or more core network nodes (e.g., core network node 1708) of various types, one or more of which may be generally referred to as network nodes 1708. Network nodes 1708 are structured with hardware and software components. Features of these components may be substantially similar to those described with respect to the UEs, access network nodes, and / or hosts, such that the descriptions thereof are generally applicable to the corresponding components of the core network node 1708. Example core network nodes provide functions of one or more of a Mobile Switching Center (MSC), Mobility Management Entity (MME), Home Subscriber Server (HSS), Access and Mobility Management Function (AMF), Session Management Function (SMF), Authentication Server Function (AUSF), Subscription Identifier De-concealing function (SIDF), Unified Data Management (UDM), Security Edge Protection Proxy (SEPP), Network Exposure Function (NEF), and / or a User Plane Function (UPF).

[0133] The host 1716 may be under the ownership or control of a service provider other than an operator or provider of the access network 1704 and / or the telecommunications network 1702. The host 1716 may be operated by the service provider or on behalf of the service provider. The host 1716 may host a variety of applications to provide one or more service. Examples of such applications include live and pre-recorded audio / video content, data collection services such as retrieving and compiling data on various ambient conditions detected by a plurality of UEs, analytics functionality, social media, functions for controlling or otherwise interacting with remote devices, functions for an alarm and surveillance center, or any other such function performed by a server.

[0134] As a whole, the communication system 1700 of Figure 17 enables connectivity between the UEs, network nodes, and hosts. In that sense, the communication system 1700 may be configured to operate according to predefined rules or procedures, such as specific standards that include, but are not limited to: Global System for Mobile Communications (GSM); Universal Mobile Telecommunications System (UMTS); Long Term Evolution (LTE), and / or other suitable 2G, 3G, 4G, 5G standards, or any applicable future generation standard (e.g., 6G); wireless local area network (WLAN) standards, such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standards (Wi-Fi); and / or any other appropriate wireless communication standard, such as the Worldwide Interoperability for Microwave Access (Wi-Max), Bluetooth, Z-Wave,Near Field Communication (NFC) ZigBee, Li-Fi, and / or any low-power wide-area network (LPWAN) standards such as LoRa and Sigfox. Moreover, the communication system 1700 may be configured to support multiple different standards, protocols, or other rule sets, with individual components supporting all of the relevant rule sets or with different components or sub-systems within the communication system 1700 supporting different standards, protocols, or rule sets.

[0135] As one example, in certain embodiments, access network 1704 may contain some access network nodes 1710 that support 3 GPP radio access technologies (RAT), such as LTE or NR, while other access network nodes 1710 support (or the same access network nodes 1710 additionally support) non-3GPP RATs, such as Wi-Fi or a proprietary RAT. As another example, telecommunications network 1702 may support multiple generations of related communication standards (e.g., 4G and 5G 3GPP communication standards) and, as a result, may include an access network 104 and / or a core network 106 that supports multiple different standard generations or may include multiple access networks 104 and / or multiple core networks 106 with individual networks 104, 106 supporting different standard generations.

[0136] Telecommunications network 1702 may support network slicing to provide different logical networks to different devices that are connected to the telecommunications network 1702. For example, the telecommunications network 1702 may provide Ultra Reliable Low Latency Communication (URLLC) services to some UEs, while providing Enhanced Mobile Broadband (eMBB) services to other UEs, and / or Massive Machine Type Communication (mMTC) / Massive loT services to yet further UEs.

[0137] In some examples, one or more of the UEs 1712 are configured to transmit and / or receive information without direct human interaction. For instance, a UE may be designed to transmit information to the access network 1704 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network 1704. Additionally, a UE may be configured for operating in single- or multi-RAT or multi -standard mode. For example, a UE may operate with any one or combination of Wi-Fi, NR (New Radio) and LTE, i.e. being configured for multi-radio dual connectivity (MR-DC), such as E-UTRAN (Evolved-UMTS Terrestrial Radio Access Network) New Radio - Dual Connectivity (EN-DC).

[0138] In the example, the hub 1714 communicates with the access network 1704 to facilitate indirect communication between one or more UEs (e.g., UE 1712C and / or 1712D) and network nodes (e.g., network node 1710B). In some examples, the hub 1714 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub 1714 may be a broadband router enabling access to the core network 1706 for the UEs. As another example, the hub 1714 may be a controller that sendscommands or instructions to one or more actuators in the UEs. Commands or instructions may be received from the UEs, network nodes 1710, or by executable code, script, process, or other instructions in the hub 1714.

[0139] As another example, the hub 1714 may be a data collector that acts as temporary storage for UE data and, in some embodiments, may perform analysis or other processing of the data. As another example, the hub 1714 may be a content source. For example, for a UE that is a VR headset, display, loudspeaker or other media delivery device, the hub 1714 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub 1714 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub 1714 acts as a proxy server or orchestrator for the UEs, in particular if one or more of the UEs are low energy loT devices.

[0140] The hub 1714 may have a constant / persistent or intermittent connection to the network node 1710B. The hub 1714 may also allow for a different communication scheme and / or schedule between the hub 1714 and UEs (e.g., UE 1712C and / or 1712D), and between the hub 1714 and the core network 1706. In other examples, the hub 1714 is connected to the core network 1706 and / or one or more UEs via a wired connection. Moreover, the hub 1714 may be configured to connect to an M2M service provider over the access network 1704 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes 1710 while still connected via the hub 1714 via a wired or wireless connection. In some embodiments, the hub 1714 may be a dedicated hub - that is, a hub whose primary function is to route communications to / from the UEs from / to the network node 1710B. In other embodiments, the hub 1714 may be a non-dedicated hub - that is, a device which is capable of operating to route communications between the UEs and network node 1710B, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0141] Figure 18 is another example of a communication system 1800 according to some embodiments. As used herein, the communication system 1800 includes multiple access points (APs) 1810 (with four exemplary APs 1810A, 1810B, 1810C, and 1810D being depicted) and multiple wireless devices, referred to in the context of communication system 1800 as stations (ST As) 1812 (referred to individually as ST A 1812A, ST A 1812B, ST A 1812C, STA 1812D, and STA 1812E). STA 1812A is served by AP 1810A in a first basic service set (BSS) 1820A. STA 1810B and STA 1810C are served by AP 1810B in a second BSS, BSS 1820B. STA 1812D is served by AP 1810C in a third BSS, BSS 1820C. STA 1812E is served by AP 1810D in a fourth BSS, BSS 1820D. Stations 1812 may be non-AP STAs and correspond to various kinds of wirelessdevices, for example, user terminals, such as mobile or stationary computing devices like smartphones, laptop computers, desktop computers, tablet computers, gaming devices, headmounted displays (HMDs) for Augmented Reality (AR) or Virtual Reality (VR), or the like. Further, stations 1812 could, for example, correspond to other kinds of equipment like smart home devices, printers, multimedia devices, data storage devices, or the like.

[0142] Each of STAs 1812 may connect through a radio link to one of APs 1810. For example, depending on location or channel conditions experienced by a given STA 1812, the STA may select an appropriate AP and BSS for establishing the radio link. The radio link may be based on one or more orthogonal frequency-division multiplexing (OFDM) carriers from a frequency spectrum that is shared on the basis of a contention-based mechanism, e.g., an unlicensed or license exempt band like 2.4 GHz Industrial, Scientific, and Medical (ISM) band, the 5 GHz band, the 6 GHz band, or the 60 GHz band.

[0143] Each AP 1810 may provide data connectivity to STAs 1812 connected to a particular AP 1810. As illustrated, APs 1810 may be connected to a data network 1830. In this way, APs 1810 may also provide data connectivity between STAs 1812 and other entities, e.g., to one or more servers, service providers, data sources, data sinks, user terminals, or the like. Accordingly, the radio link established between a given STA 1812 and its serving AP 1810 may be used for providing various kinds of services to STA 1812, e.g., a voice service, a multimedia service, or other data service. Such services may be based on applications that are executed on STA 1812 and / or on a device linked to STA 1812. By way of example, Figure 18 illustrates an application service platform 1832 provided in data network 1830. The application(s) executed on STA 1812 and / or on one or more other devices linked to STA 1812 may use the radio link for data communication with one or more other STA 1812 and / or the application service platform 1832, thereby enabling utilization of the corresponding service(s) at STA 1812.

[0144] Figure 19 shows a wireless device 1900, which may be configured to operate in communication system 1700 of Figure 17 or in communication system 1800 of Figure 18. The wireless device 1900 may be alternatively referred to as a UE 1900, like a UE 1712 within the context of communication system 1700, or as a station (STA) 1900 or as a non-access-point station (non-AP STA) 1900, like a STA 1812 within the context of the communication system 1800, in accordance with respective embodiments. As used herein, a wireless device refers to a device capable, configured, arranged and / or operable to communicate wirelessly with network nodes and / or other wireless devices. Examples of a wireless device include, but are not limited to, a smart phone, mobile phone, cell phone, voice over IP (VoIP) phone, wireless local loop phone, desktop computer, personal digital assistant (PDA), wireless cameras, gaming console or device, musicstorage device, playback appliance, wearable terminal device, wireless endpoint, mobile station, tablet, laptop, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), smart device, wireless customer-premise equipment (CPE), vehicle, vehicle-mounted or vehicle embedded / integrated wireless device, and wireless terminal. Other examples include any type of UE identified by the 3rd Generation Partnership Project (3GPP), including a narrow band internet of things (NB-IoT) UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.

[0145] A wireless device 1900 may support device-to-device (D2D) communication, for example by implementing a 3 GPP standard for sidelink communication, Dedicated Short-Range Communication (DSRC), vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), or vehicle-to-everything (V2X). In other examples, wireless device 1900 may not necessarily have a user in the sense of a human user who owns and / or operates the relevant device. Instead, wireless device 1900 may represent a device that is intended for sale to, or operation by, a human user but which may not, or which may not initially, be associated with a specific human user (e.g., a smart sprinkler controller). Alternatively, wireless device 1900 may represent a device that is not intended for sale to, or operation by, an end user but which may be associated with or operated for the benefit of a user (e.g., a smart power meter).

[0146] In particular embodiments, wireless device 1900 includes processing circuitry 1902 that is operatively coupled via a bus 1904 to an input / output interface 1906, a power source 1908, a memory 1910, a communication interface 1912, and / or any other component, or any combination thereof. Certain embodiments of wireless device 1900 may include all or a subset of the components shown in Figure 19. The level of integration between the components may vary from one embodiment of wireless device 1900 to another. In general, in a particular embodiment of wireless device 1900, processing circuitry 1902, input / output interface 1906, power source 1908, memory 1910, and communication interface 1912 may, in whole or in part, represent or include physical components common to or shared by one or more of the other elements of wireless device 1900. Further, certain embodiments of wireless devices 1900 may contain multiple instances of a component, such as multiple processors, memories, transceivers, transmitters, receivers, etc.

[0147] The processing circuitry 1902 is configured to process instructions and data and may be configured to implement any sequential state machine operative to execute instructions stored as machine-readable computer programs in the memory 1910. The processing circuitry 1902 may be implemented as one or more hardware-implemented state machines (e.g., in discrete logic, field-programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), etc.); programmable logic together with appropriate firmware; one or more stored computer programs,general-purpose processors, such as a microprocessor or digital signal processor (DSP), together with appropriate software; or any combination of the above. For example, the processing circuitry 1902 may include multiple central processing units (CPUs).

[0148] In the example, the input / output interface 1906 may be configured to provide an interface or interfaces to an input device, output device, or one or more input and / or output devices. Examples of an output device include a speaker, a sound card, a video card, a display, a monitor, a printer, an actuator, an emitter, a smartcard, another output device, or any combination thereof. An input device may allow a user to capture information into wireless device 1900. Examples of an input device include a touch-sensitive or presence-sensitive display, a camera (e.g., a digital camera, a digital video camera, a web camera, etc.), a microphone, a sensor, a mouse, a trackball, a directional pad, a trackpad, a scroll wheel, a smartcard, and the like. The presence-sensitive display may include a capacitive or resistive touch sensor to sense input from a user. A sensor may be, for instance, an accelerometer, a gyroscope, a tilt sensor, a force sensor, a magnetometer, an optical sensor, a proximity sensor, a biometric sensor, etc., or any combination thereof. An output device may use the same type of interface port as an input device. For example, a Universal Serial Bus (USB) port may be used to provide an input device and an output device.

[0149] In some embodiments, the power source 1908 is structured as a battery or battery pack. Other types of power sources, such as an external power source (e.g., an electricity outlet), photovoltaic device, or power cell, may be used to supply power to circuitry or to charge an associated battery. The power source 1908 may further include power circuitry for delivering power from the power source 1908 itself, and / or an external power source, to the various parts of wireless device 1900 via input circuitry or an interface such as an electrical power cable. Power source 1908 may perform any formatting, converting, or other modification to make accessible power suitable for the respective components of the wireless device 1900 to which power is supplied.

[0150] The memory 1910 may be or be configured to include memory such as random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disks, optical disks, hard disks, removable cartridges, flash drives, and so forth. In one example, the memory 1910 includes one or more programs 1914, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data 1916. The memory 1910 may store, for use by wireless device 1900, any of a variety of various operating systems or combinations of operating systems.

[0151] The memory 1910 may be configured to include a number of physical drive units, such as redundant array of independent disks (RAID), flash memory, USB flash drive, external hard disk drive, thumb drive, pen drive, key drive, high-density digital versatile disc (HD-DVD) optical disc drive, internal hard disk drive, Blu-Ray optical disc drive, holographic digital data storage (HDDS) optical disc drive, external mini-dual in-line memory module (DIMM), synchronous dynamic random access memory (SDRAM), external micro-DIMM SDRAM, smartcard memory such as tamper resistant module in the form of a universal integrated circuit card (UICC) including one or more subscriber identity modules (SIMs), such as a USIM and / or ISIM, other memory, or any combination thereof. The UICC may for example be an embedded UICC (eUICC), integrated UICC (iUICC) or a removable UICC commonly known as ‘SIM card.’ The memory 1910 may allow wireless device 1900 to access instructions, programs, and the like, stored on transitory or non-transitory memory media, to off-load data, or to upload data. An article of manufacture, such as one utilizing a communication system may be tangibly embodied as or in the memory 1910, which may be or comprise a device-readable storage medium.

[0152] The processing circuitry 1902 may be configured to communicate with an access network or other network via or using the communication interface 1912. The communication interface 1912 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna 1922. The communication interface 1912 may include one or more transceivers used to communicate, such as by communicating with one or more remote transceivers of another device capable of wireless communication (e.g., another wireless device or a network node in an access network). Each transceiver may include a transmitter 1918 and / or a receiver 1920 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover, the transmitter 1918 and receiver 1920 may be coupled to one or more antennas (e.g., antenna 1922) and may share circuit components, software, or firmware, or alternatively be implemented separately.

[0153] In the illustrated embodiment, communication functions of the communication interface 1912 may include cellular communication, Wi-Fi communication (e.g., according to an IEEE 802.11 family standard), LPWAN communication, data communication, voice communication, multimedia communication, short-range communications such as Bluetooth, near-field communication, location-based communication such as the use of the global positioning system (GPS) to determine a location, another like communication function, or any combination thereof. Communications may be implemented according to one or more communication protocols and / or standards, such as IEEE 802.11, Code Division Multiplexing Access (CDMA), Wideband Code Division Multiple Access (WCDMA), GSM, LTE, New Radio (NR), UMTS, WiMax,Ethernet, transmission control protocol / intemet protocol (TCP / IP), synchronous optical networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), and so forth.

[0154] In particular embodiments, wireless device 1900 may provide an output of data captured via a sensor, through its communication interface 1912, via a wireless connection to a network node, and / or in any appropriate manner. Data captured by sensors of a wireless device 1900 can be communicated through a wireless connection to a network node via another wireless device 1900. In particular embodiments, such output may be periodic (e.g., once every 15 minutes if it reports the sensed temperature), random (e.g., to even out the load from reporting from several sensors), in response to a triggering event (e.g., when moisture is detected, an alert is sent), in response to a request (e.g., a user initiated request), or a continuous stream (e.g., a live video feed of a patient).

[0155] As another example, wireless device 1900 comprises an actuator, a motor, or a switch, related to a communication interface configured to receive wireless input from a network node via a wireless connection. In response to the received wireless input the states of the actuator, the motor, or the switch may change. For example, wireless device 1900 may comprise a motor that adjusts the control surfaces or rotors of a drone in flight according to the received input or to a robotic arm performing a medical procedure according to the received input.

[0156] Wireless device 1900, when in the form of an Internet of Things (loT) device, may be a device for use in one or more application domains, these domains comprising, but not limited to, wearable technology, extended industrial application and healthcare. Non-limiting examples of such an loT device are a device which is or which is embedded in: a connected refrigerator or freezer, a TV, a connected lighting device, an electricity meter, a robot vacuum cleaner, a voice controlled smart speaker, a home security camera, a motion detector, a thermostat, a smoke detector, a door / window sensor, a flood / moisture sensor, an electrical door lock, a connected doorbell, an air conditioning system like a heat pump, an autonomous vehicle, a surveillance system, a weather monitoring device, a vehicle parking monitoring device, an electric vehicle charging station, a smart watch, a fitness tracker, a wearable for tactile augmentation or sensory enhancement, a water sprinkler, an animal- or item-tracking device, a sensor for monitoring a plant or animal, an industrial robot, an Unmanned Aerial Vehicle (UAV), and any kind of medical device, like a heart rate monitor or a remote controlled surgical robot. In particular embodiments, wireless device 1900 represents an loT device that comprises circuitry and / or software in dependence of the intended application of the loT device in addition to other components as described in relation to the example embodiment of wireless device 1900 shown in Figure 19.

[0157] As yet another specific example, in an loT scenario, wireless device 1900 may represent a machine or other device that performs monitoring and / or measurements, and transmits the results of such monitoring and / or measurements to another wireless device and / or a network node. Wireless device 1900 may in this case be an M2M device, which may in a 3GPP context be referred to as an MTC device. As one particular example, wireless device 1900 may implement the 3 GPP NB-IoT standard. In other scenarios, wireless device 1900 may represent a vehicle, such as a car, a bus, a truck, a ship and an airplane, or other equipment that is capable of monitoring and / or reporting on its operational status or other functions associated with its operation.

[0158] In practice, any number of wireless devices 1900 may be used together with respect to a single use case. For example, a first wireless device 1900 might be or be integrated in a drone and provide the drone’s speed information (obtained through a speed sensor) to a second wireless device 1900 that is a remote controller operating the drone. When a user makes changes from the remote controller, the first wireless device 1900 may adjust the throttle on the drone (e.g., by controlling an actuator) to increase or decrease the drone’s speed. The first and / or the second wireless device 1900 can also include more than one of the functionalities described above. For example, wireless device 1900 might comprise the sensor and the actuator, and handle communication of data for both the speed sensor and the actuators.

[0159] Figure 20 shows a network node 2000 in accordance with some embodiments. As used herein, network node refers to equipment capable, configured, arranged and / or operable to communicate directly or indirectly with a UE and / or with other network nodes or equipment, in a telecommunications network. In accordance with respective embodiments, network node 2000 may be configured to operate in communication system 1700 of Figure 17, like network nodes 1708 or 1710, or in communication system 1800 of Figure 18, like an AP 1810 or a station 1812. Examples of network nodes include, but are not limited to, access points (APs) (e.g., radio access points), base stations (BSs) (e.g., radio base stations, Node Bs, evolved Node Bs (eNBs) and NR NodeBs (gNBs)), 0-RAN nodes or components of an 0-RAN node (e.g., 0-RU, 0-DU, O-CU).

[0160] Network nodes 2000 may be categorized based on the amount of coverage they provide (or, stated differently, their transmit power level) and so, depending on the provided amount of coverage, may be referred to as femto base stations, pico base stations, micro base stations, or macro base stations. Network node 2000 may be a relay node or a relay donor node controlling a relay. Network nodes 2000 may also include one or more (or all) parts of a distributed radio base station such as centralized digital units, distributed units (e.g., in an 0-RAN access node) and / or remote radio units (RRUs), sometimes referred to as Remote Radio Heads (RRHs). Such remote radio units may or may not be integrated with an antenna as an antenna integrated radio. Parts ofa distributed radio base station may also be referred to as nodes in a distributed antenna system (DAS).

[0161] Other examples of network nodes 2000 include multiple transmission point (multi-TRP) 5G access nodes, multi-standard radio (MSR) equipment such as MSR BSs, network controllers such as radio network controllers (RNCs) or base station controllers (BSCs), base transceiver stations (BTSs), transmission points, transmission nodes, multi-cell / multicast coordination entities (MCEs), Operation and Maintenance (O&M) nodes, Operations Support System (OSS) nodes, Self-Organizing Network (SON) nodes, positioning nodes (e.g., Evolved Serving Mobile Location Centers (E-SMLCs)), and / or Minimization of Drive Tests (MDTs).

[0162] In particular embodiments, network node 2000 includes a processing circuitry 2002, a memory 2004, a communication interface 2006, and a power source 2008. In general, in a particular embodiment of network node 2000, processing circuitry 2002, memory 2004, communication interface 2006, and power source 2008 may, in whole or in part, represent or include physical components common to or shared by one or more of the other elements of network node 2000.

[0163] The network node 2000 may be composed of multiple distinct network entities (e.g., a NodeB entity and an RNC entity, or a BTS entity and a BSC entity, etc.), which may each have or utilize their own respective physical components. In certain scenarios in which the network node 2000 comprises multiple such entities (e.g., BTS and BSC), one or more of the separate entities may be shared among several network nodes. For example, a single RNC may control multiple NodeBs. In such a scenario, each unique NodeB and RNC pair, may in some instances be considered a single separate network node. In some embodiments, the network node 2000 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memories 2004 or portions of memory 2004 for different RATs) and some components may be reused (e.g., a same antenna 2010 may be shared by different RATs). The network node 2000 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node 2000, for example GSM, WCDMA, LTE, NR, Wi-Fi (e.g., according to an IEEE 802.11 family standard), Zigbee, Z-wave, LoRaWAN, Radio Frequency Identification (RFID) or Bluetooth wireless technologies. These wireless technologies may be integrated into the same or different chip or set of chips and other components within network node 2000.

[0164] The processing circuitry 2002 may comprise a combination of one or more of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application-specific integrated circuit, field programmable gate array, or any other suitablecomputing device, resource, or combination of hardware, software and / or encoded logic operable to provide, either alone or in conjunction with other components, such as the memory 2004, to provide network node 2000 functionality.

[0165] In some embodiments, the processing circuitry 2002 includes a system on a chip (SOC). In some embodiments, the processing circuitry 2002 includes one or more of radio frequency (RF) transceiver circuitry 2012 and baseband processing circuitry 2014. In some embodiments, the RF transceiver circuitry 2012 and the baseband processing circuitry 2014 may be on separate chips (or sets of chips), boards, or units, such as radio units and digital units. In alternative embodiments, part or all of RF transceiver circuitry 2012 and baseband processing circuitry 2014 may be on the same chip or set of chips, boards, or units.

[0166] The memory 2004 may comprise any form of volatile or non-volatile computer-readable memory including, without limitation, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), read-only memory (ROM), mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD) or a Digital Video Disk (DVD)), and / or any other volatile or non-volatile, non-transitory device-readable and / or computer-executable memory devices that store information, data, and / or instructions that may be used by the processing circuitry 2002. The memory 2004 may store any suitable instructions, data, or information, including a computer program, software, an application including one or more of logic, rules, code, tables, and / or other instructions capable of being executed by the processing circuitry 2002 and utilized by the network node 2000. The memory 2004 may be used to store any calculations made by the processing circuitry 2002 and / or any data received via the communication interface 2006. In some embodiments, the processing circuitry 2002 and memory 2004 is integrated.

[0167] The communication interface 2006 is used in wired or wireless communication of signaling and / or data with UEs, other network nodes, and / or any other network equipment. In the illustrated embodiment, communication interface 2006 comprises port(s) / terminal(s) 2016 to send and receive data, for example to and from a network over a wired connection. In particular embodiments, network node 1900 may be capable of wireless communication and communication interface 2006 may also include radio front-end circuitry 2018 that may be coupled to, or in certain embodiments a part of, an antenna 2010. Particular embodiments of radio front-end circuitry 2018 include filter(s) 2020 and amplifier(s) 2022. The radio front-end circuitry 2018 may be connected to an antenna 2010 and processing circuitry 2002. The radio front-end circuitry may be configured to condition signals communicated between antenna 2010 and processing circuitry 2002. The radio front-end circuitry 2018 may receive digital data that is to be sent out to other network nodes orUEs via a wireless connection. The radio front-end circuitry 2018 may convert the digital data into a radio signal(s) having the appropriate channel and bandwidth parameters using a combination of filters 2020 and / or amplifiers 2022. The radio signal(s) may then be transmitted via the antenna 2010. Similarly, when receiving data, the antenna 2010 may collect radio signals which are then converted into digital data by the radio front-end circuitry 2018. The digital data may be passed to the processing circuitry 2002. In other embodiments, the communication interface may comprise different components and / or different combinations of components.

[0168] In certain alternative embodiments, network node 2000 may be capable of wireless communication but does not include separate radio front-end circuitry 2018, instead, the processing circuitry 2002 includes radio front-end circuitry and is connected to the antenna 2010. Similarly, in some embodiments, all or some of the RF transceiver circuitry 2012 is part of the communication interface 2006. In still other embodiments, the communication interface 2006 includes one or more ports or terminals 2016, the radio front-end circuitry 2018, and the RF transceiver circuitry 2012, as part of a radio unit (not shown), and the communication interface 2006 communicates with the baseband processing circuitry 2014, which is part of a digital unit (not shown).

[0169] The antenna 2010 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna 2010 may be coupled to the radio front-end circuitry 2018 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna 2010 is separate from the network node 2000 and connectable to the network node 2000 through one or more interfaces or ports.

[0170] The antenna 2010, communication interface 2006, and / or the processing circuitry 2002 may be configured to perform some or all of the receiving operations and / or obtaining operations described herein as being performed by the network node 2000. Any information, data, and / or signals may be received from a UE, another network node, and / or any other network equipment. Similarly, the antenna 2010, the communication interface 2006, and / or the processing circuitry 2002 may be configured to perform some or all of the transmitting or sending operations described herein as being performed by the network node 2000. Any information, data and / or signals may be transmitted to a UE, another network node, and / or any other network equipment.

[0171] The power source 2008 provides power to the various components of network node 2000 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source 2008 may further comprise, or be coupled to, power management circuitry to supply the components of the network node 2000 with power for performing the functionality described herein. For example, the network node 2000 may beconnectable to an external power source (e.g., the power grid, an electricity outlet) via an input circuitry or interface such as an electrical cable, whereby the external power source supplies power to power circuitry of the power source 2008. As a further example, the power source 2008 may comprise a source of power in the form of a battery or battery pack which is connected to, or integrated in, power circuitry. The battery may provide backup power should the external power source fail.

[0172] Embodiments of the network node 2000 may include additional components beyond those shown in Figure 20 for providing certain aspects of the network node’s functionality, including any of the functionality described herein and / or any functionality necessary to support the subject matter described herein. For example, the network node 2000 may include user interface equipment to allow input of information into the network node 2000 and to allow output of information from the network node 2000. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the network node 2000.

[0173] Figure 21 is a block diagram illustrating a virtualization environment 2100 in which functions implemented by some embodiments may be virtualized. In the present context, virtualizing means creating virtual versions of apparatuses or devices which may include virtualizing hardware platforms, storage devices and networking resources. As used herein, virtualization can be applied to any device described herein, or components thereof, and relates to an implementation in which at least a portion of the functionality is implemented as one or more virtual components. Some or all of the functions described herein may be implemented as virtual components executed by one or more virtual machines (VMs) implemented in one or more virtual environments 2100 hosted by one or more of hardware nodes, such as a hardware computing device that operates as an access network node, UE, core network node, or host. Further, in embodiments in which a virtual node does not require radio connectivity (e.g., a core network node or host), then the node may be entirely virtualized. In some embodiments, the virtualization environment 2100 includes components defined by the O-RAN Alliance, such as an O-Cloud environment orchestrated by a Service Management and Orchestration Framework via an O-2 interface.

[0174] Applications 2102 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment 2000 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein.

[0175] Hardware 2104 includes processing circuitry, memory that stores software and / or instructions executable by hardware processing circuitry, and / or other hardware devices asdescribed herein, such as a network interface, input / output interface, and so forth. Software may be executed by the processing circuitry to instantiate one or more virtualization layers 2106 (also referred to as hypervisors or virtual machine monitors (VMMs)), provide VM 2108 A and VM 2108B (which may be collectively referred to as VMs 2108), and / or perform any of the functions, features and / or benefits described in relation with some embodiments described herein. The virtualization layer 2106 may present a virtual operating platform that appears like networking hardware to one or more of the VMs 2108.

[0176] The VMs 2108 comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by virtualization layer 2106. Different embodiments of the instance of a virtual appliance 2102 may be implemented on one or more of VMs 2108, and the implementations may be made in different ways. Virtualization of the hardware is in some contexts referred to as network function virtualization (NFV). NFV may be used to consolidate many network equipment types onto industry standard high volume server hardware, physical switches, and physical storage, which can be located in data centers, and customer premise equipment.

[0177] In the context of NFV, each of the VMs 2108 may be a software implementation of a physical machine that runs programs as if they were executing on a physical, non-virtualized machine. Each of the VMs 2108, and that part of hardware 2104 that executes that VM, be it hardware dedicated to that VM and / or hardware shared by that VM with others of the VMs, forms separate virtual network elements. Still in the context of NFV, a virtual network function is responsible for handling specific network functions that run in one or more of the VMs 2108 on top of the hardware 2104 and corresponds to an application 2102.

[0178] Hardware 2104 may be implemented in a standalone network node with generic or specific components. Hardware 2104 may implement some functions via virtualization. Alternatively, hardware 2104 may be part of a larger cluster of hardware (e.g., such as in a data center or CPE) where many hardware nodes work together and are managed via management and orchestration 2110, which, among others, oversees lifecycle management of applications 2102. In some embodiments, hardware 2104 is coupled to one or more radio units that each include one or more transmitters and one or more receivers that may be coupled to one or more antennas. Radio units may communicate directly with other hardware nodes via one or more appropriate network interfaces and may be used in combination with the virtual components to provide a virtual node with radio capabilities, such as a radio access node or a base station. In some embodiments, some signaling can be provided with the use of a control system 2112 which may alternatively be used for communication between hardware nodes and radio units.

[0179] Although the computing devices described herein (e.g., UEs, network nodes, hosts) may include the illustrated combination of hardware components, other embodiments may comprise computing devices with different combinations of components. It is to be understood that these computing devices may comprise any suitable combination of hardware and / or software needed to perform the tasks, features, functions, and methods disclosed herein. Determining, calculating, obtaining or similar operations described herein may be performed by processing circuitry, which may process information by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored in the network node, and / or performing one or more operations based on the obtained information or converted information, and as a result of said processing making a determination. Moreover, while components are depicted as single boxes located within a larger box, or nested within multiple boxes, in practice, computing devices may comprise multiple different physical components that make up a single illustrated component, and functionality may be partitioned between separate components. For example, a communication interface may be configured to include any of the components described herein, and / or the functionality of the components may be partitioned between the processing circuitry and the communication interface. In another example, non-computationally intensive functions of any of such components may be implemented in software or firmware and computationally intensive functions may be implemented in hardware.

[0180] In certain embodiments, some or all of the functionality described herein may be provided by processing circuitry executing instructions stored on in memory, which in certain embodiments may be a computer program product in the form of a non-transitory computer-readable storage medium. In alternative embodiments, some or all of the functionality may be provided by the processing circuitry without executing instructions stored on a separate or discrete device-readable storage medium, such as in a hard-wired manner. In any of those particular embodiments, whether executing instructions stored on a non-transitory computer-readable storage medium or not, the processing circuitry can be configured to perform the described functionality. The benefits provided by such functionality are not limited to the processing circuitry alone or to other components of the computing device, but are enjoyed by the computing device as a whole, and / or by end users and a wireless network generally.

[0181] Those skilled in the art will recognize improvements and modifications to the embodiments of the present disclosure. All such improvements and modifications are considered within the scope of the concepts disclosed herein.EMBODIMENTSGroup A Embodiments

[0182] Embodiment 1: A method performed by a User Equipment, UE, (1300), the method comprising: performing (1308) one or more actions related to an Artificial Intelligence, Al, / Machine Learning, ML, model functionality or feature at one or more certain time instances, respectively, wherein the one or more certain time instances take into consideration an additional processing time related to use of an AI / ML model at the UE (1300).

[0183] Embodiment 2: The method of embodiment 1, wherein the additional processing time related to use of an AI / ML model at the UE (1300) is in addition to another timing parameter related to the one or more actions.

[0184] Embodiment 3: The method of embodiment 1, wherein the other timing parameter is a legacy processing time or a processing time defined or configured for a non- AI / ML functionality or feature corresponding to the AI / ML model functionality or feature.

[0185] Embodiment 4: The method of any of embodiments 1 to 3, wherein the additional processing time comprises any one or more of the following: an amount of time needed by the UE (1300) to load the AI / ML model into dedicated hardware, an amount of time needed by the UE (1300) to unload a prior AI / ML model from the dedicated hardware prior to loading the AI / ML mode into the dedicated hardware, and an inference time of the AI / ML model.

[0186] Embodiment 5: The method of any of embodiments 1 to 4, wherein performing (1308) the one or more actions comprises transmitting (1308A) a Channel State Information, CSI, report at a certain time that takes into consideration the additional processing time related to use of the AI / ML model at the UE (1300).

[0187] Embodiment 6: The method of embodiment 5, wherein the CSI report is a periodic CSI report, a semi-persistent CSI report, or an aperiodic CSI report.

[0188] Embodiment 7: The method of any of embodiments 1 to 4, wherein performing (1308) the one or more actions comprises transmitting (1308A; 1400A1-2; 1400A2-1) an initial periodic Channel State Information, CSI, report at a certain time that takes into consideration the additional processing time related to use of the AI / ML model at the UE (1300), wherein the initial periodic CSI report is a first (in time) periodic CSI report after the UE has received a corresponding periodic CSI report configuration.

[0189] Embodiment 8: The method of embodiment 7, wherein the additional processing time is only applied for the initial periodic CSI report and not for subsequent periodic CSI reports corresponding to the periodic CSI report configuration.

[0190] Embodiment 9: The method of embodiment 7 or 8, wherein performing (1308) the one or more actions further comprises applying (1400A1-1), for the initial periodic CSI report, the additional processing time to a configured periodicity of the periodic CSI report configuration, thereby determining the certain time at which the initial CSI report is to be transmitted.

[0191] Embodiment 10: The method of embodiment 9, wherein the additional processing time is predefined or configured.

[0192] Embodiment 11: The method of embodiment 7 or 8, wherein the UE (1300) receives a separate configuration of an uplink resource for transmission of the initial periodic CSI report where this separate configuration of the uplink resource takes into consideration the additional processing time, and the uplink resource defines or corresponds to the certain time at which the initial periodic CIS report is to be transmitted.

[0193] Embodiment 12: The method of any of embodiments 1 to 4, wherein performing (1308) the one or more actions comprises transmitting (1308A; 1400B1-1; 1400B2-1) a periodic Channel State Information, CSI, report at a certain time that takes into consideration the additional processing time related to use of the AI / ML model at the UE (1300), wherein the periodic CSI report is any periodic CSI report after the UE has received a corresponding periodic CSI report configuration.

[0194] Embodiment 13: The method of embodiment 12, wherein performing (1308) the one or more actions further comprises applying (1400B1-1), for the periodic CSI report, the additional processing time to a configured periodicity of the periodic CSI report configuration, thereby determining the certain time at which the CSI report is to be transmitted.

[0195] Embodiment 14: The method of embodiment 13, wherein the additional processing time is predefined or configured.

[0196] Embodiment 15: The method of embodiment 12, wherein the periodicity configured for periodic CSI reporting (e.g., via the periodic CSI report configuration) takes into consideration the additional processing time.

[0197] Embodiment 16: The method of any of embodiments 1 to 4, wherein performing (1308) the one or more actions comprises transmitting (1308A; 1502) an initial semi-persistent Channel State Information, CSI, report at a certain time that takes into consideration the additional processing time related to use of the AI / ML model at the UE (1300), wherein the initial semi-persistent CSI report is a first (in time) semi-persistent CSI report after the UE has received a corresponding trigger for the semi-persistent CSI report configuration.

[0198] Embodiment 17: The method of embodiment 16, wherein the additional processing time is only applied for the initial semi-persistent CSI report and not for subsequent semi-persistent CSI reports corresponding to the semi-persistent CSI report configuration.

[0199] Embodiment 18: The method of embodiment 16 or 17, wherein performing (1308) the one or more actions further comprises applying (1500), for the initial semi -persistent CSI report, the additional processing time to a configured periodicity of the semi-persistent CSI report configuration, thereby determining the certain time at which the initial semi-persistent CSI report is to be transmitted.

[0200] Embodiment 19: The method of embodiment 18, wherein the additional processing time is predefined or configured.

[0201] Embodiment 20: The method of any of embodiments 1 to 4, wherein performing (1308) the one or more actions comprises transmitting (1308A; 1608) an aperiodic Channel State Information, CSI, report at a certain time that takes into consideration the additional processing time related to use of the AI / ML model at the UE (1300).

[0202] Embodiment 21: The method of embodiment 20, further comprising: determining (1602) whether one or more criteria for applying the additional processing time for the aperiodic CSI report are satisfied; and applying (1606) the additional processing time for the aperiodic CSI report if (e.g., only if) the one or more criteria are satisfied.

[0203] Embodiment 22: The method of embodiment 21, wherein the additional processing time is predefined or configured.

[0204] Embodiment 23 : The method of embodiment 21 or 22, wherein the one or more criteria comprise any one or more of the following: a criterion that the additional processing time is applied for the aperiodic CSI report if (e.g., only if) a most recently triggered CSI report including AI / ML based CSI has a different report configuration; a criterion that the additional processing time is applied for the aperiodic CSI report if (e.g., only if) a most recently triggered CSI report including AI / ML based CSI has a different report configuration and the most recently triggered CSI report including AI / ML based CI is associated with a same AI / ML model functionality or feature (i.e., a same AI / ML based CSI reporting feature); a criterion that the additional processing time is applied for the aperiodic CSI report if a most recently triggered CSI report including AI / ML based CSI is associated to a different AI / ML model functionality or feature (e.g., a different AI / ML based CSI reporting feature) but shares the same hardware resources (e.g., the same processing unit pool or other hardware resources) for AI / ML model inference of CSI; a criterion that the additional processing time is applied for the aperiodic CSI report if a most recently triggered CSI reportincludes non-AI / ML based CSI but shares the same hardware resources (e.g., the same processing unit pool or other hardware resources) for AI / ML model inference of CSI.

[0205] Embodiment 24: The method of any of any of embodiments 1 to 23, further comprising transmitting (1310), to a network node (1302), a request for additional processing time for one or more actions related to the AI / ML model functionality or feature.

[0206] Embodiment 25: The method of any of any of embodiments 1 to 24, further comprising transmitting (1310), to a network node (1302), capability information related to the additional processing time.

[0207] Embodiment 26: The method of any of the previous embodiments, further comprising: providing user data; and forwarding the user data to a host via the transmission to the network node.Group B Embodiments

[0208] Embodiment 27: A method performed by a network node (1302), the method comprising: performing one or more actions that enable a User Equipment, UE, (1300), to perform one or more actions related to an Artificial Intelligence, Al, / Machine Learning, ML, model functionality or feature at one or more certain time instances, respectively, wherein the one or more certain time instances take into consideration an additional processing time related to use of an AI / ML model at the UE (1300).

[0209] Embodiment 28: The method of embodiment 27, wherein the additional processing time related to use of an AI / ML model at the UE (1300) is in addition to another timing parameter related to the one or more actions.

[0210] Embodiment 29: The method of embodiment 27, wherein the other timing parameter is a legacy processing time or a processing time defined or configured for a non-AI / ML functionality or feature corresponding to the AI / ML model functionality or feature.

[0211] Embodiment 30: The method of any of embodiments 27 to 29, wherein the additional processing time comprises any one or more of the following: an amount of time needed by the UE (1300) to load the AI / ML model into dedicated hardware, an amount of time needed by the UE (1300) to unload a prior AI / ML model from the dedicated hardware prior to loading the AI / ML mode into the dedicated hardware, and an inference time of the AI / ML model.

[0212] Embodiment 31 : The method of any of embodiments 27 to 30, wherein the one or more actions performed by the UE comprise transmission of a Channel State Information, CSI, report at a certain time that takes into consideration the additional processing time related to use of the AI / ML model at the UE (1300).

[0213] Embodiment 32: The method of embodiment 31, wherein the CSI report is a periodic CSI report, a semi-persistent CSI report, or an aperiodic CSI report.

[0214] Embodiment 33 : The method of any of embodiments 27 to 32, wherein performing the one or more actions at the network node comprises transmitting (1306) to the UE information that configures the UE for periodic CSI reporting of AI / ML based CSI and separate information that configures the UE with a separate uplink resource for transmission of an initial periodic CSI report that takes into consideration the additional processing time.

[0215] Embodiment 34: The method of any of the previous embodiments, further comprising: obtaining user data; and forwarding the user data to a host or a user equipment.Group C Embodiments

[0216] Embodiment 35: A wireless device comprising: processing circuitry configured to perform any of the operations of any of the Group A embodiments; and a power source configured to supply power to the processing circuitry.

[0217] Embodiment 36: A network node comprising: processing circuitry configured to perform any of the operations of any of the Group B embodiments; a power source circuitry configured to supply power to the processing circuitry.

[0218] Embodiment 37: A wireless device comprising: one or more antennas; communication interface connected to the one or more antennas and to processing circuitry; the processing circuitry being configured to perform any of the operations of any of the Group A embodiments; an input interface connected to the processing circuitry and configured to allow input of information into the UE to be processed by the processing circuitry; an output interface connected to the processing circuitry and configured to output information from the UE that has been processed by the processing circuitry; and a power source connected to the processing circuitry and configured to supply power to the UE.

Claims

CLAIMS1. A method performed by a User Equipment, UE, (1300), the method comprising:performing (1308) one or more actions related to an inference procedure for CSI prediction functionality or feature at one or more certain time instances, respectively, wherein the one or more certain time instances take into consideration an additional processing time related to use of an inference procedure for CSI prediction functionality or feature at the UE (1300).

2. The method of claim 1, wherein the additional processing time related to use of an inference procedure for CSI prediction functionality or feature at the UE (1300) is in addition to another timing parameter related to the one or more actions.

3. The method of claim 1, wherein the other timing parameter is a legacy processing time or a processing time defined or configured for a non-inference based functionality or feature corresponding to the inference procedure for CSI prediction functionality or feature.

4. The method of any of any of claims 1 to 3, further comprising transmitting (1310), to a network node (1302), capability information related to the additional processing time.

5. The method of any of claims 1 to 4, wherein performing (1308) the one or more actions comprises transmitting (1308A) a Channel State Information, CSI, report at a certain time that takes into consideration the additional processing time related to use of the inference procedure for CSI prediction at the UE (1300).

6. The method of claim 5, further comprising receiving (1306), from a network node (1302), information that configures the UE (1300) for CSI reporting.

7. The method of claim 5 or 6, wherein the CSI report is a periodic CSI report or a semi-persistent CSI report.

8. The method of claim 7, wherein the additional processing time is in addition to a legacy processing time for a periodic or semi-persistent CSI report, wherein the legacy processing time for a periodic or semi-persistent CSI report is a CSI processing unit occupancy time starting from a first symbol of an earliest Channel State Information Reference Signal (CSI-RS), CSI for Interference Measurement (CSLIM), or Synchronization Signal (SS) / Physical Broadcast Channel(PBCH) Block (SSB) resource for channel or interference measurement, no later than a CSI-RS reference resource, until a last symbol of a configured Physical Uplink Shared Channel (PUSCH) or Physical Uplink Control Channel (PUCCH) carrying an respective CSI report.

9. The method of claim 5, wherein the CSI report is aperiodic CSI report.

10. The method of claim 9, wherein the additional processing time is in addition to a legacy processing time for an aperiodic CSI report, wherein the legacy processing time for an aperiodic CSI report is a CSI processing unit occupancy time starting from a first symbol after a Physical Downlink Control Channel (PDCCH) triggering the aperiodic CSI report until a last symbol of a scheduled Physical Uplink Shared Channel (PUSCH) carrying the aperiodic CSI report.

11. The method of any of claims 1 to 4, wherein performing (1308) the one or more actions comprises transmitting (1308A; 1400A1-2; 1400A2-1) an initial periodic Channel State Information, CSI, report at a certain time that takes into consideration the additional processing time related to use of the inference procedure for CSI prediction at the UE (1300), wherein the initial periodic CSI report is a first in time periodic CSI report after the UE has received a corresponding periodic CSI report configuration.

12. The method of claim 11, wherein the additional processing time is only applied for the initial periodic CSI report and not for subsequent periodic CSI reports corresponding to the periodic CSI report configuration.

13. The method of claim 11 or 12, wherein performing (1308) the one or more actions further comprises applying (1400A1-1), for the initial periodic CSI report, the additional processing time to a configured periodicity of the periodic CSI report configuration, thereby determining the certain time at which the initial CSI report is to be transmitted.

14. The method of claim 13, wherein the additional processing time is predefined or configured.

15. The method of claim 11 or 12, wherein the UE (1300) receives a separate configuration of an uplink resource for transmission of the initial periodic CSI report where this separate configuration of the uplink resource takes into consideration the additional processing time, andthe uplink resource defines or corresponds to the certain time at which the initial periodic CIS report is to be transmitted.

16. The method of any of claims 1 to 4, wherein performing (1308) the one or more actions comprises transmitting (1308A; 1400B1-1; 1400B2-1) a periodic Channel State Information, CSI, report at a certain time that takes into consideration the additional processing time related to use of the inference procedure for CSI prediction at the UE (1300), wherein the periodic CSI report is any periodic CSI report after the UE has received a corresponding periodic CSI report configuration.

17. The method of claim 16, wherein performing (1308) the one or more actions further comprises applying (1400B1-1), for the periodic CSI report, the additional processing time to a configured periodicity of the periodic CSI report configuration, thereby determining the certain time at which the CSI report is to be transmitted.

18. The method of claim 17, wherein the additional processing time is predefined or configured.

19. The method of claim 16, wherein the periodicity configured for periodic CSI reporting takes into consideration the additional processing time.

20. The method of any of claims 1 to 4, wherein performing (1308) the one or more actions comprises transmitting (1308A; 1502) an initial semi-persistent Channel State Information, CSI, report at a certain time that takes into consideration the additional processing time related to use of the inference procedure for CSI prediction at the UE (1300), wherein the initial semi-persistent CSI report is a first in time semi-persistent CSI report after the UE has received a corresponding trigger for the semi-persistent CSI report configuration.

21. The method of claim 20, wherein the additional processing time is only applied for the initial semi-persistent CSI report and not for subsequent semi-persistent CSI reports corresponding to the semi-persistent CSI report configuration.

22. The method of claim 20 or 21, wherein performing (1308) the one or more actions further comprises applying (1500), for the initial semi-persistent CSI report, the additional processingtime to a configured periodicity of the semi-persistent CSI report configuration, thereby determining the certain time at which the initial semi-persistent CSI report is to be transmitted.

23. The method of claim 22, wherein the additional processing time is predefined or configured.

24. The method of any of claims 1 to 4, wherein performing (1308) the one or more actions comprises transmitting (1308A; 1608) an aperiodic Channel State Information, CSI, report at a certain time that takes into consideration the additional processing time related to use of the inference procedure for CSI prediction at the UE (1300).

25. The method of claim 24, further comprising:determining (1602) whether one or more criteria for applying the additional processing time for the aperiodic CSI report are satisfied; andapplying (1606) the additional processing time for the aperiodic CSI report upon determining that the one or more criteria are satisfied.

26. The method of claim 25, wherein the additional processing time is predefined or configured.

27. The method of claim 25 or 26, wherein the one or more criteria comprise any one or more of the following:a criterion that the additional processing time is applied for the aperiodic CSI report if a most recently triggered CSI report including inference procedure for CSI prediction has a different report configuration;a criterion that the additional processing time is applied for the aperiodic CSI report if a most recently triggered CSI report including inference procedure for CSI prediction has a different report configuration and the most recently triggered CSI report including inference procedure for CSI prediction is associated with a same inference base functionality or feature; a criterion that the additional processing time is applied for the aperiodic CSI report if a most recently triggered CSI report including inference procedure for CSI prediction is associated to a different inference based functionality or feature but shares the same hardware resources for inference of CSI;a criterion that the additional processing time is applied for the aperiodic CSI report if amost recently triggered CSI report includes non-inference based CSI but shares the same hardware resources for inference of CSI.

28. The method of any of any of claims 1 to 27, further comprising transmitting (1310), to a network node (1302), a request for additional processing time for one or more actions related to the inference procedure based CSI prediction functionality or feature.

29. A User Equipment, UE, (1300; 1900), comprising:a communication interface (1912) comprising a transmitter (1918) and a receiver (1920); andprocessing circuitry (1902) associated with the communication interface (1912), the processing circuitry (19120 configured to cause the UE (1300; 1900) to perform (1308) one or more actions related to an inference procedure for Channel State Information, CSI, prediction functionality or feature at one or more certain time instances, respectively, wherein the one or more certain time instances take into consideration an additional processing time related to use of an inference procedure for CSI prediction functionality or feature at the UE (1300).

30. The UE of claim 29, wherein the additional processing time related to use of an inference procedure for CSI prediction functionality or feature at the UE (1300) is in addition to another timing parameter related to the one or more actions.

31. The UE of claim 29, wherein the other timing parameter is a legacy processing time or a processing time defined or configured for a non-inference based functionality or feature corresponding to the inference procedure for CSI prediction functionality or feature.

32. The method of any of claims 29 to 31, wherein the one or more actions comprise transmitting (1308 A) a Channel State Information, CSI, report at a certain time that takes into consideration the additional processing time related to use of the AI / ML model at the UE (1300).

33. The method of any of any of claims 29 to 32, further comprising transmitting (1310), to a network node (1302), capability information related to the additional processing time.

34. A method performed by a network node (1302), the method comprising:performing one or more actions that enable a User Equipment, UE, (1300), to perform oneor more actions related to an inference procedure for CSI prediction functionality or feature at one or more certain time instances, respectively, wherein the one or more certain time instances take into consideration an additional processing time related to use of an inference procedure for CSI prediction functionality or feature at the UE (1300).

35. The method of claim 34, wherein the additional processing time related to use of an inference procedure for CSI prediction functionality or feature model at the UE (1300) is in addition to another timing parameter related to the one or more actions.

36. The method of claim 34, wherein the other timing parameter is a legacy processing time or a processing time defined or configured for a non-inference base functionality or feature corresponding to the AI / ML model functionality or feature.

37. The method of any of claims 34 to 36, wherein the one or more actions performed by the UE comprise transmission of a Channel State Information, CSI, report at a certain time that takes into consideration the additional processing time related to use of the inference procedure for CSI prediction functionality or feature at the UE (1300).

38. The method of claim 37, wherein the CSI report is a periodic CSI report, a semi-persistent CSI report, or an aperiodic CSI report.

39. The method of any of claims 34 to 38, wherein performing the one or more actions at the network node comprises transmitting (1306) to the UE information that configures the UE for periodic CSI reporting of inference based CSI and separate information that configures the UE with a separate uplink resource for transmission of an initial periodic CSI report that takes into consideration the additional processing time.

40. A network node (1302; 2000) comprising processing circuitry (2002) configured to cause the network node (1302; 2000) to:perform one or more actions that enable a User Equipment, UE, (1300), to perform one or more actions related to an inference procedure for CSI prediction functionality or feature at one or more certain time instances, respectively, wherein the one or more certain time instances take into consideration an additional processing time related to use of an inference procedure for CSI prediction functionality or feature at the UE (1300).

Images