Method and apparatus for activation of ai / ML-enabled CSI reporting

Abstract

A method performed by a UE for activation of artificial intelligence (AI) / machine learning (ML)-enabled channel state information (CSI) reporting is provided. The method receives, from a base station (BS), a CSI report configuration including one or more prediction related parameters. The method in response to determining that the CSI report configuration is applicable: in response to determining that a type of the CSI report configuration is periodic, determine that the CSI report configuration is activated; and in response to determining that the type of the CSI report configuration is semi-persistent: receive, from the BS, a medium access control (MAC) control element (CE); and in response to determining that an indication is included in the MAC CE, determine that the CSI report configuration is activated.

Description

METHOD AND APPARATUS FOR ACTIVATION OF AI / ML-ENABLED CSI REPORTING

[0001] The present disclosure is related to wireless communication and, more specifically, to a User Equipment (UE), Base Station (BS), and method for artificial intelligence (AI) / machine learning (ML)-enabled channel state information (CSI) reporting in the wireless communication networks.

[0002] Various efforts have been made to improve different aspects of wireless communication for the cellular wireless communication systems, such as the 5thGeneration (5G) New Radio (NR), by improving data rate, latency, reliability, and mobility. The 5G NR system is designed to provide flexibility and configurability to optimize network services and types, accommodating various use cases, such as enhanced Mobile Broadband (eMBB), massive Machine-Type Communication (mMTC), and Ultra-Reliable and Low-Latency Communication (URLLC). As the demand for radio access continues to grow, however, there exists a need for further improvements in the next-generation wireless communication systems, such as improvements in a beam management procedure.

[0003] The present disclosure is related to a UE, a BS, and a method for AI / ML-enabled CSI reporting in the wireless communication networks.

[0004] In a first aspect of the present disclosure, a UE for AI / ML-enabled CSI reporting is provided. The UE includes at least one processor and at least one non-transitory computer-readable medium that is coupled to the at least one processor and that stores one or more computer-executable instructions. The computer-executable instructions, when executed by the at least one processor, cause the UE to: receive, from a base station (BS), a CSI report configuration including one or more prediction related parameters; and in response to determining that the CSI report configuration is applicable: in response to determining that a type of the CSI report configuration is periodic, determine that the CSI report configuration is activated; and in response to determining that the type of the CSI report configuration is semi-persistent: receive, from the BS, a medium access control (MAC) control element (CE); and in response to determining that an indication is included in the MAC CE, determine that the CSI report configuration is activated.

[0005] In some implementations of the first aspect, the one or more computer-executable instructions, when executed by the at least one processor, further cause the UE to: in response to determining that the CSI report configuration is activated: start to measure one or more channel state information (CSI)-reference signals (RSs) to obtain one or more measurement results; infer, based on the one or more measurement results and an AI / ML model associated with the CSI report configuration, one or more inference results; and report, to the BS, the one or more inference results.

[0006] In some implementations of the first aspect, the indication indicates that the CSI report configuration is activated.

[0007] In some implementations of the first aspect, the one or more computer-executable instructions, when executed by the at least one processor, further cause the UE to: in response to determining that the CSI report configuration is not applicable, determine that the CSI report configuration is deactivated.

[0008] In some implementations of the first aspect, the one or more computer-executable instructions, when executed by the at least one processor, further cause the UE to: in response to determining that the CSI report configuration is not applicable: in response to determining that the type of the CSI report configuration is semi-persistent: receive, from the BS, the MAC CE; and in response to determining that the indication is included in the MAC CE, determine that the CSI report configuration is deactivated, where the indication indicates that the CSI report configuration is activated.

[0009] In a second aspect of the present disclosure, a method performed by a user equipment (UE) for AI / ML-enabled CSI reporting is provided. The method includes: receiving, from a base station (BS), a CSI report configuration including one or more prediction related parameters; and in response to determining that the CSI report configuration is applicable: in response to determining that a type of the CSI report configuration is periodic: determining that the CSI report configuration is activated; and in response to determining that the type of the CSI report configuration is semi-persistent: receive, from the BS, a medium access control (MAC) control element (CE); and in response to determining that an indication is included in the MAC CE, determining that the CSI report configuration is activated.

[0010] In a third aspect of the present application, a BS for AI / ML-enabled CSI reporting is provided. The BS includes at least one processor and at least one non-transitory computer-readable medium that is coupled to the at least one processor and that stores one or more computer-executable instructions. The computer-executable instructions, when executed by the at least one processor, cause the BS to: transmit, to a user equipment (UE), a CSI report configuration including one or more prediction related parameters, wherein the CSI report configuration causes the UE to: in response to determining that the CSI report configuration is applicable: in response to determining that a type of the CSI report configuration is periodic, determine that the CSI report configuration is activated; and in response to determining that the type of the CSI report configuration is semi-persistent: receive, from the BS, a medium access control (MAC) control element (CE); and in response to determining that an indication is included in the MAC CE, determine that the CSI report configuration is activated.

[0011] Aspects of the present disclosure are best understood from the following detailed disclosure when read with the accompanying drawings. Various features are not drawn to scale. Dimensions of various features may be arbitrarily increased or reduced for clarity of discussion.

[0012] FIG. 1 is a diagram illustrating a MAC CE for activation and deactivation of AI / ML-enabled semi-persistent CSI reporting, according to an example implementation of the present disclosure.

[0013] FIG. 2 is a diagram illustrating a MAC CE for activation and deactivation of AI / ML-enabled semi-persistent CSI reporting, according to an example implementation of the present disclosure.

[0014] FIG. 3 is a diagram illustrating a MAC CE for activation and deactivation of AI / ML-enabled semi-persistent CSI reporting, according to an example implementation of the present disclosure.

[0015] FIG. 4 is a diagram illustrating that an applicable AI / ML-enabled CSI report configuration may become inapplicable when the UAI prohibit timer is running, according to an example implementation of the present disclosure.

[0016] FIG. 5 is a flowchart illustrating a method / process performed by a UE for activation of AI / ML-enabled CSI reporting, according to an example implementation of the present disclosure.

[0017] FIG. 6 is a block diagram illustrating a node for wireless communication, according to an example implementation of the present disclosure.

[0018] Some of the abbreviations used in the present disclosure include: Abbreviation　　　　Full name 3GPP　　　　3rdGeneration Partnership Project 5G　　　　5thGeneration BWP　　　　Bandwidth Part CA　　　　Carrier Aggregation CC　　　　Component Carrier CD-SSB 　　　　Cell Defining SSB CE 　　　　Control Element CS-RNTI　　　　Configured Scheduling Radio Network Temporary Identifier C-RNTI　　　　Cell Radio Network Temporary Identifier CSI　　　　Channel State Information DC　　　　Dual Connectivity DCI　　　　Downlink Control Information DL　　　　Downlink gNB　　　　Next Generation Node B HARQ　　　　Hybrid Automatic Repeat Request IE　　　　Information element L1　　　　Layer 1 L2　　　　Layer 2 L3　　　　Layer 3 MAC　　　　Medium Access Control (N)ES　　　　(Network) Energy Saving NR　　　　New Radio NW　　　　Network PCell　　　　Primary Cell PDCCH　　　　Physical Downlink Control Channel PDU　　　　Protocol Data Unit PDSCH　　　　Physical Downlink Shared Channel PHY　　　　Physical (layer) RLC　　　　Radio Link Control RRC　　　　Radio Resource Control RS　　　　Reference Signal RSRP　　　　Reference Signal Received Power SCell　　　　Secondary Cell SCS　　　　SubCarrier Spacing SDU　　　　Service Data Unit SFN 　　　　System Frame Number SN　　　　Sequence Number SpCell　　　　Special Cell Set A　　　　Set A of beams Set B　　　　Set B of beams SPS　　　　Semi-Persistent Scheduling SSB　　　　Synchronization Signal Block TA 　　　　Timing Advance TS　　　　Technical Specification UAI　　　　UE Assistance Information UE　　　　User Equipment UL　　　　Uplink UL-SCH　　　　Uplink Shared Channel

[0019] The following contains specific information related to implementations of the present disclosure. The drawings and their accompanying detailed disclosure are merely directed to implementations. However, the present disclosure is not limited to these implementations. Other variations and implementations of the present disclosure will be obvious to those skilled in the art.

[0020] Unless noted otherwise, like or corresponding elements among the drawings may be indicated by like or corresponding reference numerals. Moreover, the drawings and illustrations in the present disclosure are generally not to scale and are not intended to correspond to actual relative dimensions.

[0021] For the purposes of consistency and ease of understanding, like features may be identified (although, in some examples, not illustrated) by the same numerals in the drawings. However, the features in different implementations may be different in other respects and may not be narrowly confined to what is illustrated in the drawings.

[0022] References to “one implementation,” “an implementation,” “example implementation,” “various implementations,” “some implementations,” “implementations of the present application,” etc., may indicate that the implementation(s) of the present application so described may include a particular feature, structure, or characteristic, but not every possible implementation of the present application necessarily includes the particular feature, structure, or characteristic. Further, repeated use of the phrase “In some implementations,” or “in an example implementation,” “an implementation,” do not necessarily refer to the same implementation, although they may. Moreover, any use of phrases like “implementations” in connection with “the present application” are never meant to characterize that all implementations of the present application must include the particular feature, structure, or characteristic, and should instead be understood to mean “at least some implementations of the present application” includes the stated particular feature, structure, or characteristic. The term “coupled” is defined as connected, whether directly or indirectly through intervening components, and is not necessarily limited to physical connections. The term “comprising,” when utilized, means “including, but not necessarily limited to”; it specifically indicates open-ended inclusion or membership in the so-described combination, group, series, and the equivalent.

[0023] The expression “at least one of A, B and C” or “at least one of the following: A, B and C” means “only A, or only B, or only C, or any combination of A, B and C.” The terms “system” and “network” may be used interchangeably. The term “and / or” is only an association relationship for describing associated objects and represents that three relationships may exist such that A and / or B may indicate that A exists alone, A and B exist at the same time, or B exists alone. The character “ / ” generally represents that the associated objects are in an “or” relationship.

[0024] For the purposes of explanation and non-limitation, specific details, such as functional entities, techniques, protocols, and standards, are set forth for providing an understanding of the disclosed technology. In other examples, detailed disclosure of well-known methods, technologies, systems, and architectures are omitted so as not to obscure the present disclosure with unnecessary details.

[0025] Persons skilled in the art will immediately recognize that any network function(s) or algorithm(s) disclosed may be implemented by hardware, software, or a combination of software and hardware. Disclosed functions may correspond to modules which may be software, hardware, firmware, or any combination thereof.

[0026] A software implementation may include computer executable instructions stored on a computer-readable medium, such as memory or other type of storage devices. One or more microprocessors or general-purpose computers with communication processing capability may be programmed with corresponding executable instructions and perform the disclosed network function(s) or algorithm(s).

[0027] The microprocessors or general-purpose computers may include Application-Specific Integrated Circuits (ASICs), programmable logic arrays, and / or one or more Digital Signal Processor (DSPs). Although some of the disclosed implementations are oriented to software installed and executing on computer hardware, alternative implementations implemented as firmware, as hardware, or as a combination of hardware and software are well within the scope of the present disclosure. The computer-readable medium includes but is not limited to Random Access Memory (RAM), Read Only Memory (ROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), flash memory, Compact Disc Read-Only Memory (CD-ROM), magnetic cassettes, magnetic tape, magnetic disk storage, or any other equivalent medium capable of storing computer-readable instructions.

[0028] A radio communication network architecture such as a Long-Term Evolution (LTE) system, an LTE-Advanced (LTE-A) system, an LTE-Advanced Pro system, or a 5G NR Radio Access Network (RAN) typically includes at least one base station (BS), at least one UE, and one or more optional network elements that provide connection within a network. The UE communicates with the network such as a Core Network (CN), an Evolved Packet Core (EPC) network, an Evolved Universal Terrestrial RAN (E-UTRAN), a 5G Core (5GC), a 6G Core (6GC), or an internet via a RAN established by one or more BSs.

[0029] A UE may include, but is not limited to, a mobile station, a mobile terminal or device, or a user communication radio terminal. The UE may be a portable radio equipment that includes, but is not limited to, a mobile phone, a tablet, a wearable device, a sensor, a vehicle, or a Personal Digital Assistant (PDA) with wireless communication capability. The UE is configured to receive and transmit signals over an air interface to one or more cells in a RAN.

[0030] The BS may be configured to provide communication services according to at least a Radio Access Technology (RAT) such as Worldwide Interoperability for Microwave Access (WiMAX), Global System for Mobile communications (GSM) that is often referred to as 2G, GSM Enhanced Data rates for GSM Evolution (EDGE) RAN (GERAN), General Packet Radio Service (GPRS), Universal Mobile Telecommunication System (UMTS) that is often referred to as 3G based on basic wideband-code division multiple access (W-CDMA), high-speed packet access (HSPA), LTE, LTE-A, evolved LTE (eLTE) that is LTE connected to 5GC, NR (often referred to as 5G), and / or LTE-A Pro. However, the scope of the present disclosure is not limited to these protocols.

[0031] The BS may include, but is not limited to, a node B (NB) in the UMTS, an evolved node B (eNB) in LTE or LTE-A, a radio network controller (RNC) in UMTS, a BS controller (BSC) in the GSM / GERAN, an ng-eNB in an Evolved Universal Terrestrial Radio Access (E-UTRA) BS in connection with 5GC, a next generation Node B (gNB) in the 5G-RAN, or any other apparatus capable of controlling radio communication and managing radio resources within a cell. The BS may serve one or more UEs via a radio interface. Although the gNB is used as an example in some implementations within the present disclosure, it should be noted that the disclosed implementations may also be applied to other types of base stations.

[0032] The BS may be operable to provide radio coverage to a specific geographical area using multiple cells forming the RAN. The BS may support the operations of the cells. Each cell may be operable to provide services to at least one UE within its radio coverage.

[0033] Each cell (may often referred to as a serving cell) may provide services to one or more UEs within the cell’s radio coverage, such that each cell schedules the DL (and optionally UL resources) to at least one UE within its radio coverage for DL (and optionally UL packet transmissions from the UE). The BS may communicate with one or more UEs in the radio communication system via the cells.

[0034] A cell may allocate sidelink (SL) resources for supporting the Proximity Services (ProSe) or Vehicle to Everything (V2X) services. Each cell may have overlapped coverage areas with other cells.

[0035] In Multi-RAT Dual Connectivity (MR-DC) cases, the primary cell of a Master Cell Group (MCG) or a Secondary Cell Group (SCG) may be referred to as a Special Cell (SpCell). A Primary Cell (PCell) may include the SpCell of an MCG. A Primary SCG Cell (PSCell) may include the SpCell of an SCG. MCG may include a group of serving cells associated with the Master Node (MN), including the SpCell and optionally one or more Secondary Cells (SCells). An SCG may include a group of serving cells associated with the Secondary Node (SN), including the SpCell and optionally one or more SCells.

[0036] As discussed above, the frame structure for NR may support flexible configurations for accommodating various next generation (e.g., 5G) communication requirements, such as Enhanced Mobile Broadband (eMBB), Massive Machine Type Communication (mMTC), and Ultra-Reliable and Low-Latency Communication (URLLC), while fulfilling high reliability, high data rate, and low latency requirements. The Orthogonal Frequency-Division Multiplexing (OFDM) technology in the 3GPP may serve as a baseline for an NR waveform. The scalable OFDM numerology, such as adaptive sub-carrier spacing, channel bandwidth, and Cyclic Prefix (CP), may also be used.

[0037] Two coding schemes may be considered for NR, specifically, Low-Density Parity-Check (LDPC) code and Polar Code. The coding scheme adaption may be configured based on channel conditions and / or service applications.

[0038] At least the DL transmission data, a guard period, and UL transmission data should be included in a transmission time interval (TTI) of a single NR frame. The respective portions of the DL transmission data, the guard period, and the UL transmission data should also be configurable based on, for example, the network dynamics of NR. SL resources may also be provided in an NR frame to support ProSe services or V2X services.

[0039] Any two or more than two of the following paragraphs, (sub)-bullets, points, actions, behaviors, terms, or claims described in the present disclosure may be combined logically, reasonably, and properly to form a specific method.

[0040] Any sentence, paragraph, (sub)-bullet, point, action, behaviors, terms, or claims described in the present disclosure may be implemented independently and separately to form a specific method.

[0041] Dependency, e.g., “based on”, “more specifically”, “preferably”, “in one embodiment”, “in some implementations”, etc., in the present disclosure is just one possible example which would not restrict the specific method.

[0042] In some implementations, all the designs / embodiment / implementations introduced within this disclosure are not limited to be applied for dealing with the problems discussed within this disclosure. For example, the described embodiments may be applied to solve other problems that exist in the RAN of wireless communication systems. In some implementations, all of the numbers listed within the designs / embodiment / implementations introduced within this disclosure are just examples and for illustration, for example, of how the described methods are executed.

[0043] The term “A and / or B” within the present disclosure means “A”, “B”, or “A and B”. The term “A and / or B and / or C” within the present disclosure means “A”, “B”, “C”, “A and B”, “A and C”, “B and C”, or “A and B and C”. The term “A / B” within the present disclosure means “A” or “B”.

[0044] The downlink RRC message mentioned in the present disclosure may be, but is not limited to, the RRCReconfiguration, RRCResume, RRCReestablishment, RRCSetup, or any other downlink unicast RRC message.

[0045] “A specific configuration is per UE configured” or “a specific configuration is configured for a UE” mentioned in the present disclosure may represented that the specific configuration may be, but is not limited to, configured within a downlink RRC message.

[0046] “A specific configuration is per cell group configured” or “a specific configuration is configured for a cell group” mentioned in the present disclosure may represented that the specific configuration may be, but is not limited to, configured within the CellGroupConfig IE, MAC-CellGroupConfig IE, or PhysicalCellGroupConfig IE.

[0047] “A specific configuration is per serving cell configured” or “a specific configuration is configured for a serving cell” mentioned in the present disclosure may represented that the specific configuration may be, but is not limited to, configured within the ServingCellConfigCommon IE, ServingCellConfig IE, PUSCH-ServingCellConfig IE, PDSCH-ServingCellConfig IE.

[0048] “A specific configuration is per UL BWP or per BWP configured” or “a specific configuration is configured for a UL BWP or for a BWP” mentioned in the present disclosure may represented that the specific configuration may be, but is not limited to, configured within the BWP-Uplink IE, BWP-UplinkDedicated IE, BWP-UplinkCommon IE, PUSCH-ConfigCommon IE, or PUSCH-Config IE.

[0049] “A specific configuration is per DL BWP or per BWP configured” or “a specific configuration is configured for a DL BWP or for a BWP” mentioned in the present disclosure may represented that the specific configuration may be, but is not limited to, configured within the BWP-Downlink IE, BWP-DownlinkDedicated IE, BWP-DownlinkCommon IE, PDSCH-ConfigCommon IE, or PDSCH-Config IE.

[0050] The term “transmitted” mentioned in the present disclosure may represent that the corresponding MAC CE / MAC PDU / layer 1 signaling / higher layer signaling is started to be transmitted or completely transmitted or is already delivered to the corresponding HARQ process / buffer for transmission. The term “transmitted” mentioned in the present disclosure may represent that the HARQ_ACK feedback (e.g., response from the gNB) of the MAC PDU carrying the MAC CE / MAC PDU / layer 1 signaling / higher layer signaling is received. The term “transmitted” mentioned in the present disclosure may represent that the corresponding MAC CE / MAC PDU is built. the “HARQ_ACK feedback” may be implemented as a DCI format 0_0, 0_1, or some other format of DCI that was received by the UE from the gNB on the PDCCH. The received DCI may contain a new data indicator (NDI) which is set to a specific value (e.g., set to 1), and the DCI may indicate a HARQ process ID which is the same as a HARQ process ID applied by / indicated to be used for the HARQ process of the MAC PDU (e.g., carrying the BFRQ MAC CE) transmission.

[0051] The PDCCH mentioned in the present disclosure may be transmitted by the gNB to the UE. The PDCCH may be received by the UE from the gNB. The PDSCH mentioned in the present disclosure may be transmitted by the gNB to the UE. The PDSCH may be received by the UE from the gNB. The PUSCH mentioned in the present disclosure may be transmitted by the UE to the gNB. The PUCCH may be received by the gNB from the UE.

[0052] A PDSCH / PDSCH / PUSCH transmission may span multiple of symbols in time domain. A time duration of a PDSCH / PDSCH / PUSCH (transmission) may imply a time interval starts from the beginning of the first symbol of the PDSCH / PDSCH / PUSCH (transmission) and end at the end of the last symbol of the PDSCH / PDSCH / PUSCH (transmission).

[0053] In the present disclosure, “by specific Physical layer signaling” may be, but is not limited to, (a) by a specific format of the DCI, (b) by a specific field of the DCI, (c) by the specific field(s) of the DCI, where the field(s) may be set to the specific value(s), or (d) by the DCI with CRC bits scrambled with a specific RNTI.

[0054] In the present disclosure, “a timer” may be, but is not limited to, configured by the RRC which is indicated by the gNB. The UE may be configured with an initial value of the timer, and the unit of the value may be, but is not limited to, frame / sub-frame / milli second / sub-milli second / slot / symbol. The timer may be started and / or restarted by the UE. The timer may be started and / or restarted by the UE when some specific condition is satisfied.

[0055] Examples of some selected terms in the present disclosure are provided as follows.

[0056] Cell: Radio network object that may be uniquely identified by a User Equipment from a (cell) identification that is broadcasted over a geographical area from a UTRAN Access Point. A Cell may be operated in either FDD or TDD mode.

[0057] Dedicated signaling: Signaling sent on the DCCH logical channel between the network and a single UE.

[0058] Field: The individual contents of an information element may be referred to as fields.

[0059] Information element: A structural element containing single or multiple fields may be referred as information element.

[0060] PDCCH: In the downlink, the gNB may dynamically allocate resources to UEs at least via the C-RNTI / MCS-C-RNTI / CS-RNTI on PDCCH(s). A UE may always monitor the PDCCH(s) in order to find possible assignments when its downlink reception is enabled (e.g., activity governed by DRX when configured). When CA is configured, the same C-RNTI may apply to all serving cells.

[0061] PDSCH / PUSCH: The PDCCH may be used to schedule DL transmissions on the PDSCH and UL transmissions on the PUSCH.

[0062] Primary Cell: The MCG cell, operating on the primary frequency, in which the UE may either perform the initial connection establishment procedure or initiate the connection re-establishment procedure.

[0063] Secondary Cell: For a UE configured with CA, a cell providing additional radio resources on top of the Special Cell.

[0064] Serving Cell: For a UE in RRC_CONNECTED not configured with CA / DC, there may be only one serving cell including the primary cell. For a UE in RRC_CONNECTED configured with CA / DC, the term “serving cells” may be used to denote the set of cells including the Special Cell(s) and all secondary cells.

[0065] Special Cell: For Dual Connectivity operation, the term “Special Cell” may refer to the PCell of the MCG or the PSCell of the SCG, otherwise the term “Special Cell” may refer to the PCell.

[0066] Timer: RRC / PDCP / RLC / MAC entity may setup one or more timers for individual purposes, for example, triggering some uplink signaling retransmission or limiting some uplink signaling retransmission period. A timer may be running once it is started, until it is stopped or until it expires. Otherwise, the timer may not be running. A timer may be started if it is not running or restarted if it is running. A Timer may always be started or restarted from its initial value. The initial value may be, but is not limited to, configured by the gNB via downlink RRC signaling or be pre-defined / pre-determined value as specified in the 3GPP technical specification (TS).

[0067] According to 3GPP Rel-19 NR work item on AI / ML, one of the objectives is to enhance beam management (BM) by leveraging AI / ML technique. More specifically, DL Tx beam prediction for both UE-sided model and NW-sided model has been studied by the 3GPP. To facilitate the discussion, the use case may be further divided into the following two sub-cases (a) and (b).

[0068] (a) BM-Case 1: Spatial-domain DL Tx beam prediction for Set A (of beams) based on measurement results of Set B (of beams).

[0069] (b) BM-Case 2: Temporal DL Tx beam prediction for Set A (of beams) based on the historic measurement results of Set B (of beams).

[0070] Regarding Set A and Set B, at least one of the following scenarios (a)-(c) may be considered for BM-Case 1 and BM-Case 2.

[0071] (a) Set A and Set B may be different (e.g., Set B may not be a subset of Set A). For example, Set B may include wide beams while Set A may include narrow beams.

[0072] (b) Set B may be a subset of Set A (e.g., Set A and Set B may not be the same).

[0073] (c) Set A and Set B may be the same.

[0074] For BM-Case 1, AI / ML-enabled BM operations using UE-sided model may include the following (a)-(d).

[0075] (a) The network may activate and transmit the CSI-RS based on the Set B of beams.

[0076] (b) The UE may measure the L1-RSRP based on the Set B of beams.

[0077] (c) The UE may use the measurement result as the input of the UE-sided model to predict / infer best or top-k Tx Set A of beams (e.g., with L1-RSRP results).

[0078] (d) The UE may report the inference results to the network.

[0079] For BM-Case 2, AI / ML-enabled BM operations using UE-sided model may include the following (a)-(d).

[0080] (a) The network may activate and transmit the CSI-RS based on the Set B of beams from a window of preceding time instants (e.g., observation window).

[0081] (b) The UE may measure the L1-RSRP based on the Set B of beams during the observation window.

[0082] (c) The UE may use the measurement result as the input of the UE-sided model to predict / infer best or top-k Tx Set A of beams (e.g., with L1-RSRP results) for future time instants (e.g., prediction window).

[0083] (d) The UE may report the inference results to the network.

[0084] For AI / ML UE-side model, at least for BM-Case 1, for AI / ML-enabled BM operations (e.g., functionality applicability evaluation, inference reporting), it was agreed that the CSI framework is baseline. Specifically, for resources for channel measurements, periodic / semi-persistent / aperiodic CSI-RS resource types may be supported. In addition, periodic / aperiodic / semi-persistent CSI reporting may be supported as well. In the present disclosure, we will discuss whether any enhancement is needed when adopting the CSI framework for AI / ML-enabled BM operations. For example, enhancements on the activation mechanism of periodic / aperiodic / semi-persistent AI / ML-enabled CSI reporting may be discussed.

[0085] CSI framework

[0086] For CQI, PMI, CRI, SSBRI, LI, RI, L1-RSRP, the UE may be configured via RRC signaling with one or more CSI report configurations (e.g., the CSI-ReportConfig IE), and one or more CSI resource configurations (e.g., the CSI-ResourceConfig IE).

[0087] The CSI-ReportConfig IE may be used to configure a periodic or semi-persistent report sent on the PUCCH on the cell in which the the CSI-ReportConfig IE is included, or to configure a semi-persistent or aperiodic report sent on the PUSCH triggered by the DCI received on the cell in which the CSI-ReportConfig IE is included (e.g., in this case, the cell on which the report is sent may be determined by the received DCI). The CSI-ReportConfig IE may include at least one of the following parameters / fields (a)-(c).

[0088] (a) csi-reportConfigId: This parameter / field may be used to identify one CSI-ReportConfig IE within a list of CSI report configurations (e.g., the csi-ReportConfigToAddModList IE).

[0089] (b) resourcesForChannelMeasurement: This parameter / field may indicate the csi-ResourceConfigId IE of a CSI-ResourceConfig IE included in the configuration of the serving cell, which may identify resources for channel measurements. The indicated CSI-ResourceConfig IE may include only NZP-CSI-RS resources and / or SSB resources.

[0090] (c) reportConfigType: This parameter / field may indicate time domain behavior of reporting configuration. The value may be set to aperiodic, semiPersistentOnPUCCH, semiPersistenOnPUSCH, or periodic.

[0091] The CSI-ResourceConfig IE may define a group of one or more NZP-CSI-RS-ResourceSet, CSI-IM-ResourceSet, and / or CSI-SSB-ResourceSet. The CSI-ResourceConfig IE may include at least one of the following parameters / fields (a)-(c).

[0092] (a) csi-ResourceConfigId: This parameter / field may be used in the CSI-ReportConfig IE to refer to an instance of the CSI-ResourceConfig IE.

[0093] (b) resourceType: This parameter / field may indicate time domain behavior of this resource configuration. The value may be set to aperiodic, semiPersistent, or periodic.

[0094] (c) nzp-CSI-RS-ResourceSetList: This parameter / field may indicate a list of references to NZP CSI-RS resources used for CSI measurements and reporting in a CSI-RS resource set. This list may include up to a pre-defined value of resource sets if resourceType is “aperiodic” and 1 otherwise.

[0095] The NZP-CSI-RS-ResourceSet IE may be a set of Non-Zero-Power (NZP) CSI-RS resources (e.g., their IDs) and set-specific parameters. The NZP-CSI-RS-ResourceSet IE may include at least one of the following parameters / fields (a) and (b).

[0096] (a) nzp-CSI-ResourceSetId: The NZP-CSI-RS-ResourceSetId IE may be used in a list of NZP-CSI-RS-ResourceSets to refer one NZP-CSI-RS-ResourceSet.

[0097] (b) nzp-CSI-RS-Resources: This parameter / field may indicate NZP-CSI-RS-Resources associated with this NZP-CSI-RS resource set. For CSI, there may be at most 8 NZP CSI RS resources per resource set.

[0098] The NZP-CSI-RS-Resource IE may be used to configure the Non-Zero-Power (NZP) CSI-RS transmitted in the cell where the IE is included, which the UE may be configured to measure on.

[0099] The CSI report configuration may be aperiodic (e.g., using the PUSCH), periodic (e.g., using the PUCCH) or semi-persistent (e.g., using the PUCCH, and the DCI activated PUSCH). When the UE is configured with one or more periodic CSI report configurations, the UE may assume that the periodic CSI report(s) is activated.

[0100] AI / ML-enabled feature, model, and functionality

[0101] To facilitate AI / ML discussion, several terms (a)-(g) may be defined as below.

[0102] (a) AI / ML-enabled Feature may refer to a feature where the AI / ML may be used (e.g., the AI / ML-enabled BM).

[0103] (b) AI / ML-enabled Feature Group (FG) may refer to a feature group where the AI / ML may be used (e.g., the AI / ML-enabled BM-Case 1).

[0104] (c) AI / ML Model may refer to data driven algorithm that applies AI / ML techniques to generate a set of outputs based on a set of inputs. In the present disclosure, a model may also refer to an AI / ML model.

[0105] (d) UE-sided (AI / ML) model may refer to an AI / ML Model whose inference is performed entirely at the UE.

[0106] (e) Life cycle management (LCM) of AI / ML model(s) may include model training, model deployment, model inference, model monitoring, model updating, etc. In some implementations, the LCM may also refer to the model-based LCM.

[0107] (f) Functionality may refer to an AI / ML-enabled Feature / FG enabled by one or more specific configurations, where the one or more configurations may be supported based on conditions indicated by UE capability. In some implementations, the configuration may be a CSI report configuration. In this case, the CSI report configuration may refer to the AI / ML-enabled CSI report configuration. In some implementations, a functionality may be interpreted as the BM-Case 1 4(input)-to-8(output) prediction which is enabled by a CSI report configuration. The UE may have one AI / ML model for the functionality, or the UE may have multiple AI / ML models for the functionality. In some implementations, functionality “BM-Case 1 4-to-8 prediction” may be realized by the model with index M1. In some implementations, functionality “BM-Case 1 4-to-8 prediction” may be realized by model with index M1 and / or model with index M2.

[0108] (g) Functionality-based LCM may operate based on at least one configuration of AI / ML-enabled Feature / FG or specific configurations of an AI / ML-enabled Feature / FG. In functionality-based LCM, the network may indicate activation / deactivation / fallback / switching of AI / ML functionality via RRC signaling, MAC-CE, and / or DCI.

[0109] Functionality identification

[0110] For functionality identification, there may be one or more functionalities defined within an AI / ML-enabled feature. The UE may report supported functionalities to the network via the UE-capability transfer procedure.

[0111] In some implementations, supported functionalities may be reported per sub-use case level. For instance, the UE may report that the FG BM-Case 1 is supported via the UE-capability transfer procedure. For this case, an example of AI / ML-enabled BM with the corresponding UE capability fields and the corresponding configurations may be shown in Table 1. If BM-Case 1 is reported to be supported, the network may configure the UE with one or more AI / ML-enabled CSI report configurations (e.g., the AIML-CSI-ReportConfig IE). When an AI / ML-enabled CSI report configuration is configured, BM-Case 1 x-to-y prediction is expected to be enabled by the AI / ML-enabled CSI configuration, where x and y may be specified / identified by the AI / ML-enabled CSI configuration. Table 1 below illustrates an example of AI / ML-enabled BM with the corresponding UE capability fields and the corresponding configurations, according to an example implementation of the present disclosure.

[0112] In some implementations, supported functionalities may be reported per sub-use case level with supported input and output candidate values. For instance, the UE may report two supported beam prediction functionalities for BM-Case 1 (e.g., 4(input)-to-8(output) prediction and 8-to-16 prediction) via the UE-capability transfer procedure. For this case, an example of AI / ML-enabled BM with the corresponding UE capability fields and the corresponding configurations may be shown in Table 2. If BM-Case 1 is reported to be supported with indicated candidate value set of x and y, the network may configure the UE with one or more AI / ML-enabled CSI report configurations (e.g., AIML-CSI-ReportConfig IE). When an AI / ML-enabled CSI report configuration is configured, BM-Case 1 x-to-y prediction is expected to be enabled by the AI / ML-enabled CSI report configuration, where x and y may be specified / identified by the AI / ML-enabled CSI report configuration. Table 2 below illustrates an example of AI / ML-enabled BM with the corresponding UE capability fields and the corresponding configurations, according to an example implementation of the present disclosure.

[0113] Additional conditions and assocated ID

[0114] For an AI / ML-enabled feature / FG, additional conditions may refer to any aspects that are assumed for the training of the model but may not be a part of UE capability for the AI / ML-enabled feature / FG. Additional conditions may be divided into two categories that includes NW-side additional conditions (ACs) and UE-side additional conditions. The UE-side additional condition may refer to the UE speed, scenario (e.g., indoor, outdoor), hardware capabilities (e.g., battery, storage), etc. The NW-side additional conditions may refer to at least one of the following conditions (a)-(g).

[0115] (a) Mapping relationship of Set A and Set B.

[0116] (b) Consistency of downlink spatial domain transmission filters corresponding to the beams in Set A and Set B.

[0117] (c) QCL assumption.

[0118] (d) Transmission power.

[0119] (e) UE distribution.

[0120] (f) Antenna height.

[0121] (g) Deployment scenarios (e.g., Inter-site distance (ISD), urban micro (Umi), urban macro (Uma)).

[0122] For security issues, the network vendors may not reveal the specific NW-side ACs to UEs. Thus, to achieve consistency (e.g., of NW-side ACs) between training and inference, the associated ID may be introduced. In some implementations, if a UE-side model is developed using the dataset that is associated with an associated ID representing one or more specific NW-side ACs, the UE may expect to perform inference for this model using the dataset(s) that is associated with the same associated ID(s). The UE may not be aware the underlaying network implementation behind the associated ID(s).

[0123] AI / ML-enabled BM procedure

[0124] An overview of the AI / ML-enabled BM procedure may be shown as follows. After the UE reports its capabilities for AI / ML-enabled BM, the network may request the UE to report which AI / ML-enabled CSI report configuration is applicable. More specifically, the network may provide one or more AI / ML-enabled CSI report configurations, where the AI / ML-enabled CSI report configuration may be associated with one or more the associated ID(s). Afterward, the UE may determine whether the configured AI / ML enabled CSI report configuration is applicable and report to the network. After the UE reports one or more applicable AI / ML enabled CSI report configurations, the network may activate one or more AI / ML-enabled CSI report configurations.

[0125] AI / ML-enabled CSI report configuration

[0126] In some implementations, for AI / ML-enabled BM operations (e.g., inference, applicable evaluation, performance monitoring), the UE may be configured with a list of AI / ML-enabled CSI report configurations (e.g., the AIML-CSI-reportConfigToAddModlList IE), where each entry in the list may be identified by an AI / ML-enabled CSI report configuration ID (e.g., the AIML-CSI-ReportConfigId IE). For each AI / ML-enabled CSI report configuration, legacy CSI report related parameters, Set B, Set A, and / or associated ID information may be explicitly / implicitly provided. The type of an AI / ML-enabled CSI report configuration may be configured as periodic / semi-persistentOnPUCCH / semi-persistenOnPUSCH / aperiodic. The UE may be indicated with one or more AI / ML-enabled CSI report configurations to be activated via RRC / MAC CE / DCI. Once an AI / ML-enabled CSI report configuration is activated, the UE may start to perform inference and report the corresponding inference result(s) based on the AI / ML-enabled CSI report configuration.

[0127] Set B configuration

[0128] In some implementations, for the CSI resource configuration (e.g., indicated by the resourcesForChannelMeasurement IE) associated with an AI / ML-enabled CSI report configuration, the UE may expect that the indicated list of CSI resource sets (e.g., the csi-RS-ResourceSetList IE) refers to the CSI resource set(s) for Set B.

[0129] Associated ID configuration

[0130] In some implementations, an associated ID may be configured per AI / ML-enabled CSI report configuration (e.g., the AIML-CSI-reportConfig IE). If an associated ID is configured in an AI / ML-enabled CSI report configuration, the UE may assume that one or more resource sets (e.g., resource set for Set A and / or Set B) indicated (e.g., via the resourcesForChannelMeasurement IE or new IE for Set A) by the AI / ML-enabled CSI report configuration is associated with the associated ID.

[0131] In some implementations, an associated ID may be configured per CSI resource configuration (e.g., the CSI-ResourceConfig IE). If an associated ID is configured in a CSI resource configuration, the UE may assume that one or more lists of resource sets (e.g., list of resource set for Set A and / or Set B) indicated by the CSI resource configuration is associated with the associated ID. In some implementations, if the resource type is aperiodic, the UE may assume that all resource sets indicated within the same list of resource sets are associated with the same associated ID.

[0132] In some implementations, an associated ID may be configured per CSI resource set configuration (e.g., the NZP-CSI-RS-ResourceSet IE). If an associated ID is configured in a CSI resource set configuration, the UE may assume that the resource set (e.g., resource set for Set A and / or Set B) is associated with the associated ID.

[0133] In some implementations, a CSI resource set may be associated with one or more of the following (a)-(c).

[0134] (a) A first associated ID configured in the CSI resource configuration indicating the CSI resource set.

[0135] (b) A second associated ID configured in the CSI resource set configuration corresponding to the CSI resource set.

[0136] (c) A third associated ID configured in the CSI report configuration associated with the CSI resource configuration indicating the CSI resource set.

[0137] In some implementations, when a CSI resource set is associated with more than one associated ID, the UE may consider that the CSI resource set is associated with the more than one associated ID. In some implementations, when a CSI resource set is associated with more than one associated IDs, the UE may consider that the configuration is invalid.

[0138] Set A configuration

[0139] In some implementations, the CSI resource set for Set A may be configured in an AI / ML-enabled CSI report configuration. When the CSI resource set for Set A is configured, the UE may not expect the CSI resource set for Set A to be activated, and the UE may not expect to measure the CSI resource set for Set A.

[0140] In some implementations, the CSI resource set for Set B and CSI resource set for Set A may be configured by different lists of resource sets within the same CSI resource configuration, which may mean that the association between Set B and Set A is determined by the CSI resource configuration. A new IE may be introduced to indicate a list of CSI resource set IDs for Set A (e.g., the csi-RS-ResourceSetListForSetA IE).

[0141] In some implementations, the CSI resource set for Set B and CSI resource set for Set A may be configured in different CSI resource configurations. The associated CSI report configuration where the CSI resource set for Set A is configured may indicate a new IE other than the resourcesForChannelMeasurement IE to notify the CSI resource set is for Set A. Furthermore, assuming an associated ID may be configured per CSI resource configuration, the associated ID configured in a first CSI resource configuration may be the same as the associated ID configured in the second CSI resource configuration. If a CSI resource configuration is configured for Set A, the IE for resource configuration type may be absent. If a CSI resource configuration is configured for Set A, the UE may ignore the IE for resource configuration type (e.g., if it is present). If a CSI resource configuration is configured for Set A and the resource configuration type is set to aperiodic, the UE may expect the indicated CSI-RS resource set list with the size equal to 1. In some implementations, the UE may expect the indicated CSI-RS resource set list with the size greater than 1. In some implementations, the UE may expect that the size of the indicated CSI-RS resource set is the same as the size of the CSI-RS resource set list for Set B.

[0142] In some implementations, the UE may assume that the resource type within the CSI-ResourceConfig IE does not apply to the list of CSI resource set for Set A.

[0143] In some implementations, if the resource type is set to aperiodic, the UE may expect that the list of CSI resource sets for Set B and the list of CSI resource sets for Set A have the same size. The CSI resource set for Set A and the CSI resource set for Set B that have the same position within the corresponding list of resource sets may be considered as paired. For example, the resource set indicated by the first entry in the list for Set A may be paired with the resource set indicated by the first entry in the list for Set B, and the resource set indicated by the second entry in the list for Set A may be paired with the resource set indicated by the second entry in the list for Set B. Assuming an associated ID may be configured per CSI resource set configuration (e.g., the NZP-CSI-RS-ResourceSet IE), paired Set A and Set B may be expected to be associated with the same associated ID. Within the same CSI resource configuration, different paired resource sets (e.g., for Set A and for Set B) may be associated with different associated IDs.

[0144] In some implementations, Set A may not be explicitly indicated / configured within an AI / ML-enabled CSI report configuration. Assuming an associated ID is configured per CSI resource set configuration, the UE may identify the resource set for Set A by checking the configured CSI resource set for set A with the same associated ID. A new IE may be introduced within a CSI resource set configuration to indicate whether the CSI resource set is for Set A. For example, the IE may take an ENUMERATED format with value “true”. If the IE is present in the CSI resource set configuration, the UE may consider that the CSI resource set is for Set A.

[0145] Set for monitoring configuration

[0146] In some implementations, the CSI resource set for performance monitoring may be configured in an AI / ML-enabled CSI report configuration. If the CSI resource set for performance monitoring is configured, the UE may expect that the periodicity of the CSI resource set for performance monitoring is not less than the periodicity of the CSI resource set for Set B.

[0147] In some implementations, the CSI resource set for performance monitoring may be the same as the CSI resource set for Set B, which may mean that the CSI resource set for Set B can be used for inference and monitoring purposes. Besides, an indicator may be used to identify the purpose of the CSI resource for Set B.

[0148] Activation / Deactivation of AI / ML-enabled CSI report configuration

[0149] In the following, activation of periodic AI / ML-enabled CSI report configuration is discussed.

[0150] In some implementations, when the UE is configured with one or more periodic AI / ML-enabled CSI report configurations for applicability evaluation, the UE may expect that a configured periodic AI / ML-enabled CSI report configuration is activated after the AI / ML-enabled CSI report configuration is determined to be applicable. In some implementations, when the UE is configured with one or more periodic AI / ML-enabled CSI report configurations for applicability evaluation, the UE may not expect that a configured periodic AI / ML-enabled CSI report configuration is activated after the AI / ML-enabled CSI report configuration is determined to be applicable.

[0151] In some implementations, once the UE is configured with the periodic AI / ML-enabled CSI report configuration, the UE may expect to measure the configured CSI-RS resource and report the inference result regardless of whether the AI / ML-enabled CSI report configuration is applicable or not. When a periodic AI / ML-enabled CSI report configuration is configured and is determined to be inapplicable, the UE may report the inference result(s) with invalid RSRP value.

[0152] In some implementations, when the UE is configured with the periodic AI / ML-enabled CSI report configuration, the UE may expect to measure the configured CSI-RS resource and report the inference result if the AI / ML-enabled CSI report configuration is determined to be applicable. The UE may not expect to measure the configured CSI-RS resource and report the inference result if the AI / ML-enabled CSI report configuration is determined to be inapplicable.

[0153] In some implementations, when the UE is configured with the periodic AI / ML-enabled CSI report configuration, an indicator may be provided within the AI / ML-enabled report configuration to indicate the UE whether the AI / ML-enabled CSI report configuration can be activated once the AI / ML-enabled CSI report configuration is determined to be applicable. For example, the indicator may be 1 bit. If the bit value is “0”, the UE may activate / start performing inference and report the inference result while receiving the AI / ML-enabled report configuration. If the bit value is “1”, the UE may activate / start performing inference and report the inference result while the corresponding AI / ML-enabled CSI report configuration is applicable. For another example, the indicator may be 1 bit. The UE may activate / start performing inference and report the inference result while the corresponding AI / ML-enabled CSI report configuration is applicable if the bit value is “1”. Otherwise (e.g., the bit value is “0”), the UE may not activate (or keep deactivating) the configured AI / ML-enabled CSI report configuration.

[0154] In some implementations, when the UE is configured with the periodic AI / ML-enabled CSI report configuration, if one or more IEs within the AI / ML-enabled CSI report configuration are absent, the UE may not expect that the configured AI / ML-enabled CSI report configuration can be activated even if the AI / ML-enabled CSI report configuration is determined to be applicable, where the one or more IEs may be the reportType IEs. The UE may assume that this configuration can be used only for applicability evaluation instead of inference. If the one or more IEs within the periodic AI / ML-enabled CSI report configuration are present, the UE may expect that the configured AI / ML-enabled CSI report configuration is activated.

[0155] In some implementations, when the UE is configured with the periodic AI / ML-enabled CSI report configuration, the UE may report “invalid” value if the AI / ML-enable CSI report configuration is determined to be inapplicable. On the contrary, the UE may report a value other than “invalid” if the AI / ML-enable CSI report configuration is determined to be applicable. Meanwhile, the UE may selectively decide whether to send the UAI message if the corresponding AI / ML-enabled CSI report configuration changed from “applicable” to “inapplicable” or from “inapplicable” to “applicable”. That is, the value of CSI report may implicitly help the NW to know the state of applicability if a periodic AI / ML-enabled CSI report configuration is used.

[0156] In some implementations, when the UE is configured with an AI / ML-enabled periodic CSI report configuration which may include or be associated with inference configuration and / or AI / ML related parameters (e.g., the associated ID, Set A configuration and / or Set B configuration), the UE may not perform the periodic CSI report (e.g., report inference result to the NW) until the UE sends the applicability of the AI / ML-enabled CSI report configurations to the NW via the UAI. That is, the UE may start to transmit inference report related to a periodic AI / ML-enabled CSI report configuration to the NW when the periodic CSI report configuration is applicable without the instruction from the NW.

[0157] In the following, activation command for semi-persistent AI / ML-enabled CSI reporting on PUCCH is discussed.

[0158] In some implementations, the UE may be configured with a list of AI / ML-enabled CSI report configurations (e.g., the AIML-CSI-reportConfigToAddModlList IE). One or more AI / ML-enabled CSI report configurations within the list may be configured as semi-persistent (SP) reporting on the PUCCH. The UE may expect the AI / ML-enabled semi-persistent CSI reporting on the PUCCH to be activated / deactivated by a MAC CE, which selects one or more semi-persistent AI / ML-enabled CSI report configurations to be activated.

[0159] FIG. 1 is a diagram illustrating a MAC CE 100 for activation and deactivation of AI / ML-enabled semi-persistent CSI reporting, according to an example implementation of the present disclosure. In some implementations, the network may activate and deactivate the configured AI / ML-enabled semi-persistent CSI reporting on the PUCCH of a serving cell by sending the MAC CE 100 having a fixed size of 16 bits with the following field (a)-(d).

[0160] (a) Serving Cell ID: This field may indicate the identity of the serving cell for which the MAC CE applies. The length of the field may be 5 bits.

[0161] (b) BWP ID: This field may indicate a UL BWP for which the MAC CE applies as the codepoint of the DCI bandwidth part indicator field. The length of the BWP ID field may be 2 bits.

[0162] (c) R: Reserved bit, set to 0.

[0163] (d) Si: S0may refer to the CSI report configuration which includes PUCCH resources for the SP CSI reporting in the indicated BWP and has the lowest CSI-ReportConfigId, CSI-ReportConfigId for LTM, or AIML-CSI-ReportConfigId with type set to semiPersistentOnPUCCH, and S1may refer to the report configuration which includes PUCCH resources for the SP CSI reporting in the indicated BWP and has the second lowest CSI-ReportConfigId, CSI-ReportConfigId for LTM, or AIML-CSI-ReportConfigId and so on. If the number of report configurations within the list with type set to semiPersistentOnPUCCH in the indicated BWP is less than i + 1, the MAC entity may ignore the S field. The S field may be set to 1 to indicate that the corresponding Semi-Persistent CSI report configuration i shall be activated. The Sifield may be set to 0 to indicate that the corresponding Semi-Persistent CSI report configuration i shall be deactivated.

[0164] In some implementations, the A / L field may be included in the MAC CE. This field may indicate whether the MAC CE applies to the SP CSI reporting on the PUCCH Activation / Deactivation for LTM, AIML-enabled BM, or not. If the CSI-ReportConfigToAddModList IE for LTM and the AIML-CSI-ReportConfigToAddModList IE are not configured, the R field may be present instead (e.g., set to 0). The UE may not expect both the CSI-ReportConfigToAddModList IE for LTM and the AIML-CSI-ReportConfigToAddModList IE to be configured concurrently. The Sifield may indicate the activation / deactivation status of the Semi-Persistent CSI report configuration within the AIML-CSI-ReportConfigToAddModList IE or the CSI-ReportConfigToAddModList IE for LTM if the A / L field is set to 1, or the csi-ReportConfigToAddModList IE if the A / L field is set to 0.

[0165] FIG. 2 is a diagram illustrating a MAC CE 200 for activation and deactivation of AI / ML-enabled semi-persistent CSI reporting, according to an example implementation of the present disclosure. In some implementations, the A field and L field may be included in the MAC CE 200.

[0166] The A field may indicate whether the MAC CE applies to the SP CSI reporting on the PUCCH Activation / Deactivation for AIML-enabled BM or not. If the AIML-CSI-ReportConfigToAddModList IE is not configured, the R field may be present instead (e.g., set to 0). The Sifield may indicate the activation / deactivation status of the Semi-Persistent CSI report configuration within the AIML-CSI-ReportConfigToAddModList IE if the A field is set to 1, or the csi-ReportConfigToAddModList IE if the A field is set to 0. If the CSI-ReportConfigToAddModList IE for LTM is configured, the A field is set to 0.

[0167] The L field may indicate whether the MAC CE applies to the SP CSI reporting on the PUCCH Activation / Deactivation for LTM or not. If the CSI-ReportConfigToAddModList IE for LTM is not configured, the R field may be present instead (e.g., set to 0). The Sifield may indicate the activation / deactivation status of the Semi-Persistent CSI report configuration within the CSI-ReportConfigToAddModList IE for LTM if the L field is set to 1, or the csi-ReportConfigToAddModList IE if the L field is set to 0. If the AIML-CSI-ReportConfigToAddModList IE is configured, the L field is set to 0.

[0168] The UE may not expect both the CSI-ReportConfigToAddModList IE for LTM and the AIML-CSI-ReportConfigToAddModList IE to be configured concurrently.

[0169] FIG. 3 is a diagram illustrating a MAC CE 300 for activation and deactivation of AI / ML-enabled semi-persistent CSI reporting, according to an example implementation of the present disclosure. In some implementations, a list indicator field may be included in the MAC CE. This field may indicate the list of CSI report configurations for which the MAC CE applies. The length of the field may be 2 bits. If the field is set to a first value (e.g., 1), it may indicate that the MAC CE applies to the SP CSI reporting on the PUCCH Activation / Deactivation for the csi-ReportConfigToAddModList IE for LTM. If the field is set to a second value (e.g., 2), it may indicate that the MAC CE applies to the SP CSI reporting on the PUCCH Activation / Deactivation for the AIML-csi-ReportConfigToAddModList IE. Otherwise (e.g., the value is 0 or 3), it may indicate that the MAC CE applies to the SP CSI reporting on the PUCCH Activation / Deactivation for the csi-ReportConfigToAddModList IE.

[0170] In some implementations, for inference report (e.g., a UE reports AI / ML model inference result(s)), the UE may be configured with one or more AI / ML-enabled CSI report configurations, where each AI / ML-enabled CSI report configuration may be associated with one or more inference configurations and / or AI / ML related parameters (e.g., associated ID, Set A configuration, and / or Set B configuration). The type of AI / ML-enabled CSI report configuration(s) configured to the UE may be periodic, semi-persistent and / or aperiodic. After the UE receives the one or more AI / ML-enabled CSI report configurations in an RRC message (e.g., the RRCReconfiguration message), the UE may determine the applicability of the one or more AI / ML-enabled CSI report configurations (e.g., determine which CSI report configuration(s) is / are applicable). Then, the UE may inform the NW which AI / ML-enabled CSI report configuration(s) is / are applicable via the UAI.

[0171] In some implementations, if more than one periodic AI / ML-enabled CSI report configuration is applicable among all AI / ML-enabled CSI report configurations configured to the UE for inference purpose, the UE may select one periodic CSI report configuration for inference report by itself and inform the NW that the selected periodic AI / ML-enabled CSI report configuration is applicable. After the UE transmits the UAI carrying the information related to the applicability of the one or more CSI report configurations, the UE may start to report inference results based on the selected applicable periodic CSI report configuration. In some implementations, the NW may restrict that the UE only reports one periodic CSI report configuration via the UAI. For other applicable periodic (AI / ML-enabled) CSI report configurations which are not selected by the UE, the UE may ignore these periodic CSI report configurations, release these periodic CSI report configurations, inform the NW that these applicable periodic CSI report configurations are not applicable, and / or inform the NW that these applicable periodic CSI report configurations are candidate CSI report configurations which can be used for inference report other than the applicable periodic CSI report configuration selected by the UE.

[0172] In some implementations, if more than one periodic (AI / ML-enabled) CSI report configuration is applicable among all (AI / ML-enabled) CSI report configurations configured to the UE for inference purpose, the UE may inform the NW that these periodic CSI report configurations are applicable via the UAI. In some implementations, after the UE reports the applicability of the CSI report configurations via the UAI, the UE may start to report inference results according to the one or more applicable periodic CSI report configurations without the instruction from the NW. However, before the UE reports the applicability of the CSI report configurations via the UAI, the UE may not report inference results(s). In some implementations, after the UE reports the applicability of the CSI report configurations via the UAI, the UE may start to report inference results according to the one or more applicable periodic CSI report configurations when receiving the ACK message from the NW. The ACK message may be DCI and / or MAC CE informing the UE that the NW receives the UAI. In addition, the ACK message may instruct the UE to use which applicable periodic CSI report configuration(s) for inference reports.

[0173] In some implementations, if more than one semi-persistent (AI / ML-enabled) CSI report configuration is applicable, the UE may inform the NW all applicable semi-persistent CSI report configurations via the UAI. Then, the UE may start to report inference results when receiving the instruction from the NW. For example, after the UE transmits the UAI carrying the information related to the applicability of the one or more CSI report configurations, the UE may receive a MAC CE, where the MAC CE may indicate one or more applicable semi-persistent CSI report configurations to the UE for inference report. Then, the UE may start to report inference results based on the one or more applicable semi-persistent CSI report configurations indicated in the MAC CE.

[0174] In some implementations, if more than one aperiodic (AI / ML-enabled) CSI report configuration is applicable, the UE may inform the NW all applicable aperiodic CSI report configurations via the UAI. Then, the UE may start to report inference results when receiving the instruction from the NW. For example, after the UE transmits the UAI carrying the information related to the applicability of the one or more CSI report configurations, the UE may receive one or more DCI(s), where each DCI may indicate one or more applicable semi-persistent CSI report configurations to the UE for inference report. Then, the UE may start to report inference results based on the one or more applicable semi-persistent CSI report configurations indicated in each DCI.

[0175] Interaction between activation command and UAI

[0176] FIG. 4 is a diagram illustrating that an applicable AI / ML-enabled CSI report configuration may become inapplicable when the UAI prohibit timer is running, according to an example implementation of the present disclosure. The UE may report whether an AI / ML-enabled CSI report configuration is applicable via the UAI procedure. A UAI procedure may be initiated upon applicability change of one or more AI / ML-enabled CSI report configurations and if a UAI prohibit timer is not running. However, an applicable AI / ML-enabled CSI report configuration may become inapplicable when the UAI prohibit timer is running. The UE may receive an activation command 402 before the UAI transmission (e.g., the second UAI 404), and the UE behavior may be unclear, as illustrated in FIG. 4. To address this issue, at least one of the following options may be adopted.

[0177] In some implementations, for a configured AI / ML-enabled CSI report configuration, the UE may determine that it is applicable if the UE expects the AI / ML-enabled CSI report configuration to be applicable for a period. The period may be determined by a timer (e.g., the UAI prohibit timer).

[0178] In some implementations, when the UE is configured with one or more semi-persistent / aperiodic AI / ML-enabled CSI report configurations, upon reception of the activation command (e.g., DCI, MAC CE) for one or more semi-persistent / aperiodic AI / ML-enabled CSI report configurations, the UE may expect the semi-persistent / aperiodic AI / ML-enabled CSI report configuration to be activated if the semi-persistent / aperiodic AI / ML-enabled CSI report configuration is determined to be applicable. If the semi-persistent / aperiodic AI / ML-enabled CSI report configuration is determined to be inapplicable, the UE may ignore the activation command and assume the configuration is deactivated (e.g., the UE may not perform the CSI reporting based on this configuration). Moreover, the UE may trigger the UAI procedure to report the applicability status regardless of whether the UAI prohibit timer is running as well as restart the UAI prohibit timer. The UE may report a list of inapplicable AI / ML-enabled CSI report configurations.

[0179] In some implementations, when the UE is configured with one or more semi-persistent / aperiodic AI / ML-enabled CSI report configurations, upon reception of the activation command (e.g., DCI, MAC CE) for one or more semi-persistent / aperiodic AI / ML-enabled CSI report configurations, the UE may start to report inference result based on the configuration indicated by the activation command. If the semi-persistent / aperiodic AI / ML-enabled CSI report configuration is determined to be inapplicable, the UE may notify the network the applicable status by inference result reporting so that the network can fix the issue (e.g., by deactivating the configuration). In some implementations, the UE may report a pre-defined value (e.g., the RSRP value set to infinity) which represents that the configuration becomes inapplicable.

[0180] In some implementations, a UE may be configured with one or more periodic (AI / ML-enabled) CSI report configurations associated with inference configuration and / or AI / ML-related parameters (e.g., associated ID, Set A configuration, and / or Set B configuration). After the UE receives the one or more periodic (AI / ML-enabled) CSI report configurations, the UE may report which periodic CSI report configuration(s) is / are applicable via the UAI procedure. After the UE reports the applicability of the one or more periodic CSI report configurations via the UAI procedure, the prohibit timer may start running. If the applicable periodic CSI report configuration(s) reported to the NW become inapplicable, the prohibit timer related to the UAI is still running, and the UE needs to transmit the inference report to the NW based on the inapplicable periodic CSI report configuration(s) (e.g., the applicable periodic CSI report configuration(s) which becomes inapplicable when the prohibit timer related to the UAI procedure is running), at least one of the following UE behaviors (a) and (b) may be performed.

[0181] (a) The UE may report inference results with invalid value(s) and / or invalid indication(s) (e.g., the inference report may include invalid value(s) and / or invalid indication(s) to inform the NW whether the inference report is valid or not) to the NW if the inference report(s) is / are triggered by the one or more inapplicable periodic CSI report configurations. The UE may report invalid indication to inform the NW that the corresponding CSI report configuration(s) become(s) inapplicable via signals other than UAI (e.g., MAC CE and / or PUCCH).

[0182] (b) The UE may not provide inference report(s) to the NW even if the inapplicable CSI report configuration(s) trigger(s) the inference report(s).

[0183] FIG. 5 is a flowchart illustrating a method / process 500 performed by a UE for activation of artificial intelligence (AI) / machine learning (ML)-enabled channel state information (CSI) reporting, according to an example implementation of the present disclosure.

[0184] In the action 502, the process 500 may start by receiving, from a Base Station (BS), a CSI report configuration including one or more prediction related parameters.

[0185] In the action 504, the process 500 may in response to determining that the CSI report configuration is applicable: in response to determining that a type of the CSI report configuration is periodic, determine that the CSI report configuration is activated; and in response to determining that the type of the CSI report configuration is semi-persistent: receive, from the BS, a medium access control (MAC) control element (CE); and in response to determining that an indication is included in the MAC CE, determine that the CSI report configuration is activated. In some implementations, the indication may indicate that the CSI report configuration is activated. The process 500 may then end.

[0186] In some implementations, the process 500 may in response to determining that the CSI report configuration is activated: start to measure one or more channel state information (CSI)-reference signals (RSs) to obtain one or more measurement results; infer, based on the one or more measurement results and an AI / ML model associated with the CSI report configuration, one or more inference results; and report, to the BS, the one or more inference results.

[0187] In some implementations, the process 500 may in response to determining that the CSI report configuration is not applicable, determine that the CSI report configuration is deactivated.

[0188] In some implementations, the process 500 may in response to determining that the CSI report configuration is not applicable: in response to determining that the type of the CSI report configuration is semi-persistent: receive, from the BS, the MAC CE; and in response to determining that the indication is included in the MAC CE, determine that the CSI report configuration is deactivated, where the indication may indicate that the CSI report configuration is activated.

[0189] The steps / actions shown in FIG. 5 should not be construed as necessarily order dependent. The order in which the process is described is not intended to be construed as a limitation. Moreover, some of the actions shown in FIG. 5 may be omitted in some implementations and one or more actions shown in FIG. 5 may be combined.

[0190] The technical problem addressed by the method illustrated in FIG. 5 is how to efficiently activate AI / ML-enabled channel state information (CSI) reporting in a user equipment (UE) across different CSI report configuration types (e.g., periodic and semi-persistent) while ensuring compatibility with base station (BS) signaling and minimizing unnecessary signaling overhead or resource misuse in dynamic wireless environments. The advantageous technical effect achieved by the method illustrated in FIG. 5 is that it enables adaptive and efficient activation of AI / ML-enabled CSI reporting by automatically activating periodic CSI configurations upon applicability and using a MAC control element (CE) for semi-persistent configurations, thereby optimizing resource utilization, reducing signaling overhead, and improving the accuracy and timeliness of CSI reporting for enhanced network performance.

[0191] FIG. 6 is a block diagram illustrating a node 600 for wireless communication in accordance with various aspects of the present disclosure. As illustrated in FIG. 6, a node 600 may include a transceiver 620, a processor 628, a memory 634, one or more presentation components 638, and at least one antenna 636. The node 600 may also include a radio frequency (RF) spectrum band module, a BS communications module, a network communications module, and a system communications management module, Input / Output (I / O) ports, I / O components, and a power supply (not illustrated in FIG. 6).

[0192] Each of the components may directly or indirectly communicate with each other over one or more buses 640. The node 600 may be a UE or a BS that performs various functions disclosed with reference to FIGS. 1 through 5.

[0193] The transceiver 620 has a transmitter 622 (e.g., transmitting / transmission circuitry) and a receiver 624 (e.g., receiving / reception circuitry) and may be configured to transmit and / or receive time and / or frequency resource partitioning information. The transceiver 620 may be configured to transmit in different types of subframes and slots including, but not limited to, usable, non-usable, and flexibly usable subframes and slot formats. The transceiver 620 may be configured to receive data and control channels.

[0194] The node 600 may include a variety of computer-readable media. Computer-readable media may be any available media that may be accessed by the node 600 and include volatile (and / or non-volatile) media and removable (and / or non-removable) media.

[0195] The computer-readable media may include computer-storage media and communication media. Computer-storage media may include both volatile (and / or non-volatile media), and removable (and / or non-removable) media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules, or data.

[0196] Computer-storage media may include RAM, ROM, EPROM, EEPROM, flash memory (or other memory technology), CD-ROM, Digital Versatile Disks (DVD) (or other optical disk storage), magnetic cassettes, magnetic tape, magnetic disk storage (or other magnetic storage devices), etc. Computer-storage media may not include a propagated data signal. Communication media may typically embody computer-readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave, or other transport mechanisms and include any information delivery media.

[0197] The term “modulated data signal” may mean a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. Communication media may include wired media, such as a wired network or direct-wired connection, and wireless media, such as acoustic, RF, infrared, and other wireless media. Combinations of any of the above listed components should also be included within the scope of computer-readable media.

[0198] The memory 634 may include computer-storage media in the form of volatile and / or non-volatile memory. The memory 634 may be removable, non-removable, or a combination thereof. Example memory may include solid-state memory, hard drives, optical-disc drives, etc. As illustrated in FIG. 6, the memory 634 may store a computer-readable and / or computer-executable instructions 632 (e.g., software codes) that are configured to, when executed, cause the processor 628 to perform various functions disclosed herein, for example, with reference to FIGS. 1 through 5. Alternatively, the instructions 632 may not be directly executable by the processor 628 but may be configured to cause the node 600 (e.g., when compiled and executed) to perform various functions disclosed herein.

[0199] The processor 628 (e.g., having processing circuitry) may include an intelligent hardware device, e.g., a Central Processing Unit (CPU), a microcontroller, an ASIC, etc. The processor 628 may include memory. The processor 628 may process the data 630 and the instructions 632 received from the memory 634, and information transmitted and received via the transceiver 620, the baseband communications module, and / or the network communications module. The processor 628 may also process information to send to the transceiver 620 for transmission via the antenna 636 to the network communications module for transmission to a CN.

[0200] One or more presentation components 638 may present data indications to a person or another device. Examples of presentation components 638 may include a display device, a speaker, a printing component, a vibrating component, etc.

[0201] In view of the present disclosure, it is obvious that various techniques may be used for implementing the disclosed concepts without departing from the scope of those concepts. Moreover, while the concepts have been disclosed with specific reference to certain implementations, a person of ordinary skill in the art may recognize that changes may be made in form and detail without departing from the scope of those concepts. As such, the disclosed implementations are to be considered in all respects as illustrative and not restrictive. It should also be understood that the present disclosure is not limited to the particular implementations disclosed and many rearrangements, modifications, and substitutions are possible without departing from the scope of the present disclosure.

Claims

1. A user equipment (UE) for activation of artificial intelligence (AI) / machine learning (ML)-enabled channel state information (CSI) reporting, the UE comprising: 　　　　at least one processor; and 　　　　at least one non-transitory computer-readable medium coupled to at least one processor and storing one or more computer-executable instructions that, when executed by the at least one processor, cause the UE to: 　　　　　　　　receive, from a base station (BS), a CSI report configuration comprising one or more prediction related parameters; and 　　　　　　　　in response to determining that the CSI report configuration is applicable: 　　　　　　　　　　　　in response to determining that a type of the CSI report configuration is periodic, determine that the CSI report configuration is activated; and 　　　　　　　　　　　　in response to determining that the type of the CSI report configuration is semi-persistent: 　　　　　　　　　　　　　　　　receive, from the BS, a medium access control (MAC) control element (CE); and 　　　　　　　　　　　　　　　　in response to determining that an indication is included in the MAC CE, determine that the CSI report configuration is activated.

2. The UE of claim 1, wherein the one or more computer-executable instructions, when executed by the at least one processor, further cause the UE to: 　　　　in response to determining that the CSI report configuration is activated: 　　　　　　　　start to measure one or more channel state information (CSI)-reference signals (RSs) to obtain one or more measurement results; 　　　　　　　　infer, based on the one or more measurement results and an AI / ML model associated with the CSI report configuration, one or more inference results; and 　　　　　　　　report, to the BS, the one or more inference results.

3. The UE of claim 1, wherein the indication indicates that the CSI report configuration is activated.

4. The UE of claim 1, wherein the one or more computer-executable instructions, when executed by the at least one processor, further cause the UE to: 　　　　in response to determining that the CSI report configuration is not applicable, determine that the CSI report configuration is deactivated.

5. The UE of claim 1, wherein the one or more computer-executable instructions, when executed by the at least one processor, further cause the UE to: 　　　　in response to determining that the CSI report configuration is not applicable: 　　　　　　　　in response to determining that the type of the CSI report configuration is semi-persistent: 　　　　　　　　　　　　receive, from the BS, the MAC CE; and 　　　　　　　　　　　　in response to determining that the indication is included in the MAC CE, determine that the CSI report configuration is deactivated, wherein 　　　　　　　　　　　　the indication indicates that the CSI report configuration is activated.

6. A method performed by a user equipment (UE) for activation of artificial intelligence (AI) / machine learning (ML)-enabled channel state information (CSI) reporting, the method comprising: 　　　　receiving, from a base station (BS), a CSI report configuration comprising one or more prediction related parameters; and 　　　　in response to determining that the CSI report configuration is applicable: 　　　　　　　　in response to determining that a type of the CSI report configuration is periodic, determining that the CSI report configuration is activated; and 　　　　　　　　in response to determining that the type of the CSI report configuration is semi-persistent: 　　　　　　　　　　　　receiving, from the BS, a medium access control (MAC) control element (CE); and 　　　　　　　　　　　　in response to determining that an indication is included in the MAC CE, determining that the CSI report configuration is activated.

7. A base station (BS) for activation of artificial intelligence (AI) / machine learning (ML)-enabled channel state information (CSI) reporting, the BS comprising: 　　　　at least one processor; and 　　　　at least one non-transitory computer-readable medium coupled to at least one processor and storing one or more computer-executable instructions that, when executed by the at least one processor, cause the BS to: 　　　　　　　　transmit, to a user equipment (UE), a CSI report configuration comprising one or more prediction related parameters, wherein the CSI report configuration causes the UE to: 　　　　　　　　　　　　in response to determining that the CSI report configuration is applicable: 　　　　　　　　　　　　　　　　in response to determining that a type of the CSI report configuration is periodic, determine that the CSI report configuration is activated; and 　　　　　　　　　　　　　　　　in response to determining that the type of the CSI report configuration is semi-persistent: 　　　　　　　　　　　　　　　　　　　　receive, from the BS, a medium access control (MAC) control element (CE); and 　　　　　　　　　　　　　　　　　　　　in response to determining that an indication is included in the MAC CE, determine that the CSI report configuration is activated.

8. The BS of claim 7, wherein the CSI report configuration further causes the UE to: 　　　　in response to determining that the CSI report configuration is activated: 　　　　　　　　start to measure one or more channel state information (CSI)-reference signals (RSs) to obtain one or more measurement results; 　　　　　　　　infer, based on the one or more measurement results and an AI / ML model associated with the CSI report configuration, one or more inference results; and 　　　　　　　　report, to the BS, the one or more inference results.

9. The BS of claim 7, wherein the indication indicates that the CSI report configuration is activated.

10. The BS of claim 7, wherein the CSI report configuration further causes the UE to: 　　　　in response to determining that the CSI report configuration is not applicable, determine that the CSI report configuration is deactivated.

11. The BS of claim 7, wherein the CSI report configuration further causes the UE to: 　　　　in response to determining that the CSI report configuration is not applicable: 　　　　　　　　in response to determining that the type of the CSI report configuration is semi-persistent: 　　　　　　　　　　　　receive, from the BS, the MAC CE; and 　　　　　　　　　　　　in response to determining that the indication is included in the MAC CE, determine that the CSI report configuration is deactivated, wherein 　　　　　　　　　　　　the indication indicates that the CSI report configuration is activated.

Images