Device capabilities and performance monitoring for models

Abstract

Techniques for using artificial intelligence / machine learning (AI / ML) models to improve the accuracy of channel state information (CSI) are described. Due to limited model generalization and dynamic wireless environments, several methods are proposed to monitor the performance of the models. The wireless communication method includes transmitting, by a communication device, a capability message indicating that the communication device is capable of using the model and performing one or more wireless communication operations.

Description

[Technical Field]

[0001] TECHNICAL FIELD This disclosure is generally directed to digital wireless communications. [Background technology]

[0002] Wireless communication technologies are moving the world toward an increasingly connected and networked society. Compared to existing wireless networks, next-generation systems and wireless communication techniques will need to support a much broader range of use case characteristics and provide a more complex and sophisticated range of access requirements and flexibility.

[0003] Long Term Evolution (LTE) is a wireless communication standard for mobile devices and data terminals developed by the 3rd Generation Partnership Project (3GPP®). LTE Advanced (LTE-A) is a wireless communication standard that enhances the LTE standard. The fifth generation of wireless systems, known as 5G, evolves the LTE and LTE-A wireless standards and is committed to supporting higher data rates, a large number of connections, ultra-low latency, high reliability, and other emerging business needs. Summary of the Invention [Means for solving the problem]

[0004] Techniques for reporting UE capabilities, including AI / ML models, are disclosed. Several solutions for monitoring model performance in some embodiments are discussed.

[0005] The wireless communication method includes transmitting, by a communication device, a capabilities message, the capabilities message indicating that the communication device is capable of performing one or more wireless communication operations using a model by the communication device.

[0006] In some embodiments, the capability message includes a time requirement for the model. In some embodiments, the time requirement is associated with a model identifier.

[0007] In some embodiments, the model can be received by the communications device from a network.

[0008] In some embodiments, the capability message includes one of the following: a computation time, a computation time offset, or a model activation time. In some embodiments, the computation time is the time a communications device requires to perform an action, the computation time offset is the additional time a communications device requires to perform an action, and the model activation time is the time a communications device requires to activate an action.

[0009] In some embodiments, the calculation time can be a constant independent of the selected model. In some embodiments, the value of the calculation time offset is model dependent. In some embodiments, the capacity message indicates that a measurement report is to be generated after a time lapse T based on a reference signal received by the communications device, where T depends on the calculation time offset and the calculation time.

[0010] In some embodiments, the method further includes transmitting, by the communication device, an identifier message indicating that the model has been activated.

[0011] In some embodiments, the identifier message may be transmitted over the PUCCH.

[0012] In some embodiments, the method further includes receiving, by the communication device, a response indicating successful receipt of the identifier message.

[0013] In some embodiments, the method further includes deactivating, by the communication device, the model when no response is received by the communication device.

[0014] In some embodiments, the capabilities message includes the capabilities of the communication device, the capabilities including model-related and non-model-related concurrent capabilities.

[0015] Another method of wireless communication includes reporting, by a communication device, an indication of performance of a model.

[0016] In some embodiments, the performance indication includes a relationship between the auxiliary information and actual measurements made by the communications device.

[0017] In some embodiments, the relationship can be a similarity or a distance, where the similarity includes cosine similarity, generalized cosine similarity, or squared generalized cosine similarity, and the distance includes Euclidean distance or normalized mean squared error.

[0018] In some embodiments, the communication device is configured with at least a dedicated opportunity used for performance indication of the model, hi some embodiments, the performance indication includes predicted measurements and actual measurements of the dedicated opportunity.

[0019] In some embodiments, the actual measurements include RSRPs of multiple reference signals, and the predicted measurements include predicted RSRPs of the reference signals based on a model.

[0020] In some embodiments, the actual measurements include codebook-based precoding matrix indications (PMIs).

[0021] In some embodiments, the performance indication further includes a relationship between the output of the model and the input of the model.

[0022] In some embodiments, the performance indication includes a relationship between MN remaining measurements of the N measurements and a portion of the model outputs, wherein N measurements are based on a reference signal, M measurements are based on the N measurements and are used for input to the model, and M <Nである。

[0023] In some embodiments, the relationship can be a similarity or a distance, and the similarity can be at least one of the following: cosine similarity, generalized cosine similarity, or squared generalized cosine similarity, and the distance can be at least one of the following: Euclidean distance or normalized mean squared error.

[0024] In yet another exemplary aspect, the methods described above are embodied in the form of processor-executable code and stored in a non-transitory computer-readable storage medium, the code contained on the computer-readable storage medium, when executed by a processor, causing the processor to perform the methods described in this patent document.

[0025] In yet another exemplary embodiment, a device configured or operable to perform the methods described above is disclosed.

[0026] These and other aspects and their implementations are described in more detail in the drawings, description, and claims. [Brief explanation of the drawings]

[0027] [Figure 1] Figure 1 shows an example of an artificial intelligence / machine learning (AI / ML) model.

[0028] [Figure 2] FIG. 2 shows an example of calculation times and calculation time offsets.

[0029] [Figure 3] FIG. 3 shows an example of the relationship between auxiliary channel information and actual channel measurements.

[0030] [Figure 4] FIG. 4 illustrates an example showing dedicated channel measurement opportunities for monitoring model performance.

[0031] [Figure 5] FIG. 5 illustrates an example of employing a relationship between a portion of an AI model output and an AI model input for model performance monitoring.

[0032] [Figure 6] FIG. 6 shows an exemplary block diagram of a hardware platform that may be part of a network or communication device.

[0033] [Figure 7] FIG. 7 illustrates an example of wireless communication involving a base station (BS) and user equipment (UE) according to some implementations of the disclosed technology. DETAILED DESCRIPTION OF THE INVENTION

[0034] (Introduction) Section headings are used herein merely to improve readability and do not limit the scope of the disclosed embodiments and techniques within each section to that section alone. Furthermore, some embodiments are described with reference to the 3rd Generation Partnership Project (3GPP®) New Radio (NR) standard ("5G") for ease of understanding, and the described techniques may be implemented in different wireless systems that implement protocols other than 5G protocols. Additionally, the AI / ML model is an example scenario, and the technical solutions described herein can be generalized or applicable to any model that determines the relationship between inputs and outputs.

[0035] (Introductory notes)

[0036] Artificial intelligence / machine learning (AI / ML) is being researched and applied in various fields.

[0037] Several studies in artificial intelligence and machine learning have been conducted to improve the efficiency of wireless communication systems, especially at the physical layer. For example, AI / ML models can be used to improve the accuracy of channel state information (CSI). In addition, AI / ML models can predict beam information. To support channel measurements by using AI / ML models, UEs in the network should have the corresponding capabilities.

[0038] This application discloses several procedures proposed to report UE capabilities, including AI / ML models. Due to limited model generalization and dynamic environments, models may degrade their performance over time. Therefore, this application discusses several solutions for monitoring model performance.

[0039] (I. Introduction)

[0040] AI / ML has been studied and used in various fields to extract features that cannot be derived by other mathematical methods. Generally, an AI / ML model is a data-driven algorithm that applies AI / ML techniques to generate a set of outputs based on a set of inputs, and includes at least three parts, as shown in Figure 1. - AI model input: Data that is fed into an AI / ML model - AI Model Output: Output of AI / ML model - AI model: an algorithm for deriving the relationship between AI model inputs and AI model outputs

[0041] To facilitate the discussion, the following terminology is introduced along with some general explanations.

[0042] AI model training is the process of training an AI / ML model by learning the input / output relationship in a data-driven manner and obtaining a trained AI / ML model for inference.

[0043] AI model inference is the process of employing a trained AI / ML model to produce a set of outputs based on a set of inputs.

[0044] In measurement reporting, such as CSI reporting or beam reporting, the UE may use an AI model to derive the measurement report. To support channel measurement by using an AI / ML model, the UE should have the corresponding capability.

[0045] In this application, several procedures are proposed for reporting UE capabilities, including AI / ML models. Furthermore, due to limited model generalization and dynamic environments, models may degrade their performance over time. In other words, the data used for AI model training and that for AI model inference may be significantly different, causing the AI model to fail to obtain the expected AI model output. In this application, several solutions for monitoring model performance are discussed.

[0046] II. ILLUSTRATIVE EMBODIMENTS

[0047] A. Capability Signaling and Auxiliary Signaling

[0048] In some embodiments, the UE may report its model (e.g., AI / ML model) related information to the network through UE capability signaling or auxiliary information signaling.

[0049] In some embodiments, the model-related information may be reported after the network sends a request message to the UE, where the request message may include a model identifier.

[0050] In some embodiments, model-related information can be reported without first requesting a message from the network.

[0051] In some embodiments, the model-related information includes time requirements for the model.

[0052] In some embodiments, the model-related information may include a model identifier for associating with a corresponding time requirement:

[0053] The time requirement may include one of the following:

[0054] (1) Calculation time)

[0055] In one example, the computation time may include the time required by the UE to perform / operate / execute the model and / or the time required by the UE to prepare a measurement report associated with the model.

[0056] In some embodiments, the computation time is the same for all models.

[0057] In some embodiments, the calculation time is different for different reporting quantities in the measurement report. In other words, the calculation time depends on the content included in the measurement report. For example, the calculation time for a beam report may be different from that for a CSI report.

[0058] In some embodiments, the computation time is not required to be reported by the UE and reuses the value defined for non-model-based measurement reporting.

[0059] (2) Calculation time offset

[0060] In one example, the calculation time offset may include additional time required for the UE to perform / act / execute for the model.

[0061] In some embodiments, each model has its own calculation time offset.

[0062] In some embodiments, the calculation time offset is not required to be reported by the UE. In this scenario, the value of the calculation time offset is set to zero by default. Alternatively, the UE can report a zero value for the calculation time offset.

[0063] In some embodiments, as shown in FIG. 2, the UE only reports a measurement report based on a reference signal, where the reference signal is received T time units earlier than the time at which the measurement report is transmitted, and T time units is the calculation time plus the calculation time offset.

[0064] (3) Model activation / application time

[0065] In some embodiments, when a UE receives medium access control (MAC) signaling that includes an instruction command to use a model, the UE may require a certain time to activate the model. For example, when the UE transmits a PUCCH with HARQ-ACK information corresponding to a PDSCH carrying an instruction command at time n, the UE assumes that the corresponding model that is ready / to be activated for inference should be applied at time n+model activation time.

[0066] In some embodiments, when a UE receives a downlink control indication (DCI) including an instruction command to use a model, the UE may require a certain time to activate the model. For example, when a UE receives a PDCCH carrying an instruction command at time n, the UE assumes that the corresponding model that is ready / to be activated for inference should be applied at time n+model activation time.

[0067] In some embodiments, the UE can send signaling to notify the network that a model is ready / activated for inference. In some embodiments, the UE can send signaling to notify the network that a model is ready / activated for inference, and if the UE is indicated to use this model to perform an operation, the UE does not need any extra time (e.g., activation time) to activate this model.

[0068] In some embodiments, the signaling may be carried by the PUCCH, and each model may be associated with a dedicated PUCCH resource.

[0069] In some embodiments, the signaling may be carried by a PRACH, and each model may be associated with a dedicated PRACH.

[0070] In some embodiments, the UE may receive a response from the network to confirm that the signaling has been successfully received by the network. In some embodiments, the response is transmitted by MAC signaling. In some embodiments, if the UE detects a PDCCH scrambled with a dedicated RNTI, the UE has been confirmed that the signaling has been successfully received by the network.

[0071] In some embodiments, if the UE does not receive a response, the UE may automatically deactivate the model.

[0072] In some embodiments, the UE may automatically deactivate the model when the waiting time from when the UE begins transmitting signaling exceeds a time threshold.

[0073] In some embodiments, the UE may report parallel / mixed UE capabilities for model-related and non-model-related.

[0074] In some embodiments, the UE may report that the UE can be configured with a number of measurement reports that use the model and a number of measurement reports that do not use the model.

[0075] For example, a UE may report that once the UE is configured with M CSI reports using a model in a bandwidth portion / component carrier (BWP / CC), the UE is not expected to be configured with more than N other CSI reports that do not use the model, where the value of N is either not required to be reported or may be reported by a value of zero, both of which indicate that once configured with a CSI report using a model, the UE cannot be configured with other CSI reports that do not use the model.

[0076] In another example, a UE may report that once the UE is configured with M beam reports using a model in a BWP / CC (bandwidth portion / component carrier), the UE is not expected to be configured with more than N other beam reports that do not use the model, where the value of N can be either not required to be reported or reported by a value of zero, both of which indicate that once configured with a beam report using a model, the UE cannot be configured with other beam reports that do not use the model.

[0077] In some embodiments, the UE may report that the UE may simultaneously process for measurement reporting using the model and measurement reporting without using the model.

[0078] For example, a UE may simultaneously process for M beam reports using the model and N beam reports without the model in a CC (or across all CCs), where the value of N is not required to be reported or can be reported by a value of zero.

[0079] For example, a UE may simultaneously process for M beam reports using a model and N CSI reports without a model in a CC (or across all CCs), where the value of N is not required to be reported or can be reported by a value of zero.

[0080] (B. Model Monitoring Procedure)

[0081] At the UE side, the performance of the deployed model may not always be good. Due to limited model generalization and dynamic environment, the model performance may degrade. Therefore, both the network and the UE should constantly monitor the model performance.

[0082] Here, we propose three solutions for model performance monitoring.

[0083] Method 1: The network provides auxiliary channel information to assist in model performance monitoring.

[0084] In some embodiments, the UE may report the relationship between the supplemental channel information and the actual channel measurements.

[0085] In the example shown in FIG. 3, the auxiliary channel information and the actual channel measurements are respectively H assist and H. The first AI model output is

number

number

[0086] One metric for evaluating model performance is similarity, for example, cosine similarity, generalized cosine similarity, or squared generalized cosine similarity. H assist The similarity between H and S input and

number

number

[0087] Another metric for evaluating model performance is distance, e.g., Euclidean distance or normalized mean squared error. H assist The distance between and H is D input and

number

number

[0088] In some embodiments, the UE is required to report a performance indication to the network regarding the results of the performance monitoring.

[0089] In some embodiments, the performance indication comprises an indicator within the measurement report. For example, values of 0 and 1 mean that the AI model is disabled and enabled, respectively. More specifically, a value of 0 means that S output / S input or D output / D input is lower than the threshold.

[0090] In some embodiments, the performance indication is based on a similarity score (S input and S output ) or distance (D input and D output In some embodiments, the performance indication includes a value of S output / S input or D output / D input Contains the value of

[0091] In some embodiments, the network may provide multiple pieces of supplemental channel information, where each piece of supplemental channel information may be associated with a performance indication.

[0092] Method 2: Dedicated channel measurement occasions are used to monitor model performance.

[0093] In some embodiments, the network may exhibit at least one dedicated channel measurement occasion for monitoring model performance.

[0094] In one example where an AI model is employed for channel prediction, the AI model input is based on actual channel measurements at several previous occasions (e.g., observation occasions). The AI model output is a predicted channel measurement, which may be used at several future occasions (e.g., prediction occasions). Thus, the UE does not need to obtain actual channel measurements at the prediction occasion. However, if the occasion is designated as a dedicated channel measurement occasion (e.g., a monitoring occasion) for monitoring model performance, as shown in FIG. 4, the UE may need to obtain both actual and predicted channel measurements. The UE / network can then compare the actual and predicted channel measurements to check whether the channel prediction is sufficiently accurate.

[0095] In one embodiment, the UE is required to report both the actual and predicted channel measurements for the monitoring occasion in the measurement report.

[0096] In one example, an AI model is employed for beam prediction.

[0097] In some embodiments, the actual channel measurements include RSRPs of multiple reference signals, and the predicted channel measurements include RSRPs of multiple reference signals.

[0098] In some embodiments, the network may indicate the number of RSRPs included in the actual and predicted channel measurements.

[0099] In some embodiments, the number of RSRPs included in the actual channel measurements and the predicted channel measurements are the same.

[0100] In some embodiments, each RSRP is associated with a reference signal index.

[0101] In another example, an AI model can be employed for CSI prediction.

[0102] In some embodiments, the actual channel measurements include conventional codebook-based precoding matrix indications (PMIs).

[0103] Method 3: A dedicated module in the AI module is for model performance monitoring.

[0104] In some embodiments, a portion of the AI model output can be used for model performance monitoring.

[0105] In some embodiments, part of the AI model output includes an indicator that indicates at least whether the AI model is valid, which can be reported in a measurement report.

[0106] In some embodiments, the relationship between some of the AI model outputs and the AI model inputs can be used for model performance monitoring.

[0107] In the example shown in FIG. 5, the AI model input is the channel information H, and the AI model output of the first sub-module is the compressed channel information H.

number

number

[0108] In some embodiments, the measurement report may include an indication of the relationship.

[0109] In some embodiments, the relationship can be the similarity / distance between the channel information and the reconstructed channel information.

[0110] In some embodiments, the measurement report may include both an indication of the relationship and compressed channel information.

[0111] In some embodiments, the UE obtains N measurement results based on the received reference signals. The AI model input may include only M of the N measurement results (where M < N). In this scenario, the remaining N - M measurement results can be used for model performance monitoring.

[0112] In some embodiments, the N measurement results are N RSRP values, and each RSRP value corresponds to a beam between the network and the UE. The AI model input includes only M of the N RSRP values (where M < N). Thus, the remaining N - M RSRP values can be used for model performance monitoring. The remaining N - M RSRP values correspond to a set of beams between the network and the UE. Further, a part of the AI model output includes the predicted N - M RSRP values, and the predicted N - M RSRP values correspond to a set of beams between the network and the UE.

[0113] In some embodiments, the UE may report a validity indicator based on the remaining N - M RSRP values and the predicted N - M RSRP values.

[0114] In some embodiments, the validity indicator can be the similarity between the remaining N - M RSRP values and the predicted N - M RSRP values.

[0115] In some embodiments, the validity indicator can be the difference (i.e., distance) between the remaining N - M RSRP values and the predicted N - M RSRP values.

[0116] In some embodiments, the UE may report both the remaining N - M RSRP values and the predicted N - M RSRP values in the measurement report.

[0117] In some embodiments, one of the predicted N−M RSRP values is reported relative to one of the remaining N−M RSRP values corresponding to the same beam between the network and the UE.

[0118] In some embodiments, the N measurement results are N channel measurement results corresponding to an N−port reference signal. The AI model input includes only M (M < N) of the N channel measurement results. Thus, the remaining N−M channel measurement results can be used for model performance monitoring. The remaining N−M channel measurement results correspond to a set of ports of the N−port reference signal. Further, a part of the AI model output includes the predicted N−M channel measurement results corresponding to the set of ports of the N−port reference signal.

[0119] In some embodiments, the UE may report a validity indicator based on the remaining N−M channel measurement results and the predicted N−M channel measurement results.

[0120] In some embodiments, the validity indicator can be the similarity between the remaining N−M channel measurement results and the predicted N−M channel measurement results.

[0121] In some embodiments, the validity indicator can be the difference (i.e., distance) between the remaining N−M channel measurement results and the predicted N−M channel measurement results.

[0122] FIG. 6 shows an example block diagram of a hardware platform 600 that may be part of a network device (e.g., a base station) or a communication device (e.g., user equipment (UE)). The hardware platform 600 includes at least one processor 610 and a memory 605 that stores instructions. The instructions, when executed by the processor 610, configure the hardware platform 600 to perform the operations described in FIGS. 1-5 and 7 and in various embodiments described in this patent document. The transmitter 615 transmits or transmits information or data to another device. For example, a network device transmitter can transmit a message to a user equipment. The receiver 620 receives information or data transmitted or transmitted by another device. For example, a user equipment can receive a message from a network device.

[0123] Implementations such as those discussed above may be applied to wireless communications. Figure 7 illustrates an example of a wireless communication system (e.g., a 5G or NR cellular network) including a base station 720 and one or more user equipments (UEs) 711, 712, and 713. In some embodiments, the UE accesses a BS (e.g., a network) using a communication link to the network (sometimes referred to as the uplink direction, as depicted by dashed arrows 731, 732, and 733), which then enables subsequent communication from the BS to the UE (e.g., shown in the direction from the network to the UE, sometimes referred to as the downlink direction, as depicted by arrows 741, 742, and 743). In some embodiments, the BS transmits information to the UE (sometimes referred to as the downlink direction, as depicted by arrows 741, 742, and 743), which then enables subsequent communication from the UE to the BS (e.g., shown in the direction from the UE to the BS, sometimes referred to as the uplink direction, as depicted by dashed arrows 731, 732, and 733). The UE may be, for example, a smartphone, a tablet, a mobile computer, a machine-to-machine (M2M) device, an Internet of Things (IoT) device, and the like.

[0124] The wireless communication method includes transmitting, by a communication device, a capabilities message indicating that the communication device is capable of using a model by the communication device to perform one or more wireless communication operations.

[0125] In some embodiments, the capability message includes a time requirement for the model. In some embodiments, the time requirement is associated with a model identifier.

[0126] In some embodiments, the model can be received by the communications device from a network.

[0127] In some embodiments, the capability message includes one of the following: a computation time, a computation time offset, or a model activation time. In some embodiments, the computation time is the time a communications device requires to perform an action, the computation time offset is the additional time a communications device requires to perform an action, and the model activation time is the time a communications device requires to activate an action.

[0128] In some embodiments, the calculation time can be a constant independent of the selected model. In some embodiments, the value of the calculation time offset is model dependent. In some embodiments, the capacity message indicates that a measurement report is to be generated after a time lapse T based on a reference signal received by the communications device, where T depends on the calculation time offset and the calculation time.

[0129] In some embodiments, the method further includes transmitting, by the communication device, an identifier message indicating whether the model is activated.

[0130] In some embodiments, the identifier message may be transmitted over the PUCCH.

[0131] In some embodiments, the method further includes receiving, by the communication device, a response indicating successful receipt of the identifier message.

[0132] In some embodiments, the method further includes deactivating, by the communication device, the model when no response is received by the communication device.

[0133] In some embodiments, the capabilities message includes the capabilities of the communication device, the capabilities including model-related and non-model-related concurrent capabilities.

[0134] Another method of wireless communication includes reporting, by a communication device, an indication of performance of a model.

[0135] In some embodiments, the performance indication includes a relationship between the auxiliary information and actual measurements made by the communications device.

[0136] In some embodiments, the relationship can be a similarity or a distance, where the similarity includes cosine similarity, generalized cosine similarity, or squared generalized cosine similarity, and the distance includes Euclidean distance or normalized mean squared error.

[0137] In some embodiments, the communication device is configured with at least a dedicated opportunity used for performance indication of the model, hi some embodiments, the performance indication includes predicted measurements and actual measurements of the dedicated opportunity.

[0138] In some embodiments, the actual measurements include RSRPs of multiple reference signals, and the predicted measurements include predicted RSRPs of the reference signals based on a model.

[0139] In some embodiments, the actual measurements include codebook-based precoding matrix indications (PMIs).

[0140] In some embodiments, the performance indication further includes a relationship between the output of the model and the input of the model.

[0141] In some embodiments, the performance indication includes a relationship between MN remaining measurements of the N measurements and a portion of the model outputs, wherein N measurements are based on a reference signal, M measurements are based on the N measurements and are used for inputs to the model, and M <Nである。

[0142] In some embodiments, the relationship can be a similarity or a distance, and the similarity can be at least one of the following: cosine similarity, generalized cosine similarity, or squared generalized cosine similarity, and the distance can be at least one of the following: Euclidean distance or normalized mean squared error.

[0143] In yet another exemplary aspect, the methods described above are embodied in the form of processor-executable code and stored in a non-transitory computer-readable storage medium, the code contained on the computer-readable storage medium, when executed by a processor, causing the processor to perform the methods described in this patent document.

[0144] In yet another exemplary embodiment, a device configured or operable to perform the methods described above is disclosed.

[0145] These and other aspects and their implementations are described in more detail in the drawings, description, and claims.

[0146] In this document, the term "exemplary" is used to mean "an example of," and does not imply an ideal or preferred embodiment, unless otherwise stated.

[0147] Some of the embodiments described herein are described in the general context of a method or process that may be implemented by a computer program product, which in one embodiment is embodied in a computer-readable medium containing computer-executable instructions, such as program code, executed by computers in a networked environment. Computer-readable media may include removable and non-removable storage devices, including, but not limited to, read-only memory (ROM), random access memory (RAM), compact discs (CDs), digital versatile discs (DVDs), and the like. Thus, computer-readable media may include non-transitory storage media. Generally, program modules may include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. Computer- or processor-executable instructions, associated data structures, and program modules represent examples of program code for executing steps of the methods disclosed herein. The particular sequence of such executable instructions or associated data structures represents examples of corresponding acts for implementing the functions described in such steps or processes.

[0148] Some of the disclosed embodiments can be implemented as devices or modules using hardware circuits, software, or a combination thereof. For example, a hardware circuit implementation may include discrete analog and / or digital components integrated, for example, as part of a printed circuit board. Alternatively or additionally, the disclosed components or modules can be implemented as application-specific integrated circuits (ASICs) and / or field-programmable gate array (FPGA) devices. Some implementations may additionally or alternatively include a digital signal processor (DSP), which is a specialized microprocessor with an architecture optimized for the operational needs of digital signal processing associated with the disclosed functionality. Similarly, various components or subcomponents within each module may be implemented in software, hardware, or firmware. Connectivity between modules and / or components within a module may be provided using any one of connectivity methods and mediums known in the art, including, but not limited to, communication via the Internet, wired, or wireless networks using appropriate protocols.

[0149] While this document contains many details, these should be construed as descriptions of features specific to particular embodiments, rather than as limitations on the scope of the claimed invention or what may be claimed. Certain features described herein in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination. Also, while features may be described above as acting in a combination and even initially claimed as such, one or more features from a claimed combination can, in some cases, be deleted from the combination, and the claimed combination may be directed to a subcombination or a variation of the subcombination. Similarly, although operations are depicted in the figures in a particular order, this should not be understood as requiring such operations to be performed in the particular order shown, or in a sequential order, or that all of the illustrated operations be performed, to achieve desirable results.

[0150] Only some implementations and examples are described; other implementations, enhancements, and variations can be made based on what is described and illustrated in this disclosure.

Claims

1. 1. A wireless communication method, the method comprising: transmitting, by the communication device, a capability message; The method, wherein the capabilities message indicates that the communication device is capable of using a model by the communication device to perform one or more wireless communication operations.

2. The method of claim 1 , wherein the capability message includes a time requirement for the model.

3. The method of claim 2 , wherein the time requirement is associated with a model identifier.

4. The method of claim 3 , wherein the model can be received by the communication device from a network.

5. the capability message includes one of a calculation time, a calculation time offset, or a model activation time; 3. The method of claim 2, wherein the computation time is the time the communication device requires to perform an action, the computation time offset is the additional time the communication device requires to perform an action, and the model activation time is the time the communication device requires to activate an action.

6. The method of claim 5 , wherein the computation time can be a constant that is independent of the model selected.

7. The method of claim 5 , wherein the value of the calculation time offset depends on the model.

8. 6. The method of claim 5, wherein the capacity message indicates that a measurement report is to be generated after a time lapse T based on a reference signal received by the communication device, where T depends on the calculation time offset and the calculation time.

9. The method of claim 1 , further comprising transmitting, by the communication device, an identifier message indicating that the model has been activated.

10. The method of claim 9 , wherein the identifier message can be transmitted over a PUCCH.

11. The method of claim 9 , further comprising receiving, by the communication device, a response indicating successful receipt of the identifier message.

12. The method of claim 11 , further comprising deactivating, by the communication device, the model when the response is not received by the communication device.

13. The method of claim 1 , wherein the capabilities message includes capabilities of the communication device, the capabilities including model-related and non-model-related concurrent capabilities.

14. 1. A method of wireless communication, the method including reporting, by a communication device, an indication of performance of a model.

15. The method of claim 14 , wherein the performance indication includes a relationship between auxiliary information and actual measurements made by the communications device.

16. 16. The method of claim 15, wherein the relationship can be a similarity or a distance, wherein the similarity comprises cosine similarity, generalized cosine similarity, or squared generalized cosine similarity, and the distance comprises Euclidean distance or normalized mean squared error.

17. The method of claim 14 , wherein the communication device is configured with dedicated opportunities used for at least the performance indication of the model.

18. The method of claim 14 , wherein the performance indication includes predicted and actual measurements of the dedicated opportunity.

19. 20. The method of claim 18, wherein the actual measurements include RSRPs of a plurality of reference signals, and the predicted measurements include predicted RSRPs of the reference signals based on the model.

20. 20. The method of claim 18, wherein the actual measurements include codebook-based precoding matrix indications (PMIs).

21. The method of claim 14 , wherein the performance indication further comprises a relationship between the model output and the model input.

22. 15. The method of claim 14, wherein the performance indication includes a relationship between M-N remaining measurements of N measurements and a portion of the model output, the N measurements being based on the reference signal, and the M measurements being based on the N measurements and used for input to the model, and M<N.

23. 23. The method of claim 21 or 22, wherein the relationship can be a similarity or a distance, wherein the similarity can be at least one of a cosine similarity, a generalized cosine similarity, or a squared generalized cosine similarity, and wherein the distance can be at least one of a Euclidean distance or a normalized mean squared error.

24. An apparatus for wireless communication, said apparatus comprising a processor configured to perform the method set forth in one or more of claims 1-24.

25. A non-transitory computer readable program storage medium storing code that, when executed by a processor, causes the processor to perform a method as recited in one or more of claims 1-24.

Images