WO2023211331A1

WO2023211331A1 - Reporting time-domain beam prediction information in beam failure recovery

Info

Publication number: WO2023211331A1
Application number: PCT/SE2023/050344
Authority: WO
Inventors: Icaro Leonardo DA SILVA; Henrik RYDÉN; Jingya Li; Yufei Blankenship; Chunhui Li
Original assignee: Telefonaktiebolaget LM Ericsson AB
Current assignee: Telefonaktiebolaget LM Ericsson AB
Priority date: 2022-04-29
Filing date: 2023-04-13
Publication date: 2023-11-02
Anticipated expiration: 2024-10-29
Also published as: EP4515702A1

Abstract

A method, network node and wireless device (WD) for reporting time domain beam prediction information in beam failure recovery (BFR) are disclosed. According to one aspect, in some embodiments, a method in a WD includes performing at least one time domain prediction of measurements of signals on at least one beam. The method also includes in response to a beam failure detection (BFD), transmitting to the network node at least one time domain prediction.

Description

REPORTING TIME-DOMAIN BEAM PREDICTION INFORMATION IN BEAM

FAILURE RECOVERY

TECHNICAL FIELD

The present disclosure relates to wireless communications, and in particular, to reporting time domain beam prediction information in beam failure recovery.

BACKGROUND

The Third Generation Partnership Project (3GPP) has developed and is developing standards for Fourth Generation (4G) (also referred to as Long Term Evolution (LTE)) and Fifth Generation (5G) (also referred to as New Radio (NR)) wireless communication systems. Such systems provide, among other features, broadband communication between network nodes, such as base stations, and mobile wireless devices (WD), as well as communication between network nodes and between WDs. Sixth Generation (6G) wireless communication systems are also under development.

Artificial Intelligence (Al) - Machine Learning (ML) for Air Interface: 3GPP Release 18 (Rel-18) ad 6G

Al and ML have been studied in 3GPP Technical Release 17 (3GPP Rel-17) and some initial functionality is planned to be standardized in 3GPP Rel-18. The outcome of the study in 3GPP Rel-17 is documented in the Technical Report (TR) 37.817 entitled “Study on enhancement for Data Collection for NR and EN-DC”. 3 GPP has considered principles for radio access network (RAN) intelligence enabled by Al. The functional framework (e.g., the Al functionality and the input/output of the component for Al enabled optimization) and use cases and solutions of Al enabled RAN are based on the current/exiting architecture and interfaces of 3 GPP Rel-17.

In 3GPP NR standardization work, there may be a new release 18 Study Item on AI/ML for NR air interface (e.g., RP-213560 SID on AI-ML for Air Interface), this time aiming for some impact to the air interface. One goal of the study is to explore the benefits of augmenting the air-interface with features enabling improved support of AI/ML based algorithms for enhanced performance (e.g., improved throughput, robustness, accuracy or reliability) and/or reduced complex! ty/overhead. Enhanced performance may depend on the use cases under consideration and could be, e.g., improved throughput, robustness, accuracy or reliability, or reduced overhead, etc. Through studying a few selected use cases, assessing their performance in comparison with traditional methods and the associated potential specification impacts that enable their solutions, may lay the foundation for future Air-Interface use cases leveraging AI/ML techniques. One goal is that sufficient use cases will be considered to enable the identification of a common AI/ML framework, including functional requirements of AI/ML architecture, which could be used in subsequent projects. The study may also identify areas where AI/ML could improve the performance of air interface functions. The 3GPP framework for AI/ML for air interface corresponding to each target use case is to be studied in various aspects such as performance, complexity, and potential specification impact.

The study may serve to identify what is required for an adequate AI/ML model characterization and description, and establishing pertinent notation for consideration and subsequent evaluations. Various levels of collaboration between the network node (e.g., gNB) and wireless device (WD) are identified and considered. Evaluations to exercise the attainable gains of AI/ML based techniques for the use cases under consideration may be carried out with the corresponding identification of key performance indicators (KPIs) with the goal of better understanding the attainable gains and associated complexity requirements. Finally, the specification impact will be assessed in order to improve the overall understanding of what would be required to enable AI/ML techniques for the airinterface.

Among the initial set of use cases 3GPP RANI may be considering, is beam management, e.g., beam prediction in time, and/or spatial domain for overhead and latency reduction, and/or beam selection accuracy improvement.

For the use cases under consideration, including beam management, 3GPP is considering the following:

1) Assessing potential specification impact, specifically for the considered use cases in the final representative set and for a common framework: o PHY layer aspects including (RANI):

■ Consider aspects related to, e.g., the specification of the Al Model lifecycle management, and dataset construction for training, validation and test for the selected use cases;

■ Use case and collaboration level specific specification impact, such as new signaling, assistance information, measurement, and feedback; o Protocol aspects including (Except use case study, RAN2 only start following general assessment after there is sufficient progress on use study in RANI):

■ Consider aspects related to, e.g., capability indication, configuration procedures (training/inference), validation and testing procedures, and management of data and AI/ML model;

■ Collaboration level specific specification impact per use case including signaling design to support the collaboration identified in RANI; o Interoperability and testability aspects (RAN4 only start the work after there is sufficient progress on use case study in RANI and RAN2):

■ WD and gNB requirements and testing frameworks to validate AI/ML based performance enhancements and ensuring that WD and gNB with AI/ML meet or exceed the existing minimum requirements; and

■ Consider the need and implications for AI/ML processing capabilities definition.

ALML for 6G Air Interface

However, the topic of RAN2 protocols is expected to be brought up in the European Union 6G project Hexa-X. According to information about the project, in this area the objective is to make the most out of Al technology applied to networks - to develop methodology, algorithms, and architectural requirements for an Al-native network, through Al-driven air interface and Al governance. The 6G networks should be designed to incorporate Al operation to optimize network performance, as well as operate to optimize Al performance for other services. Targets here include embedding Al functionality into the signal processing chain and developing suitable learning methods. Governance and protocols for secure Al may be developed for the integration of Al into trustworthy network systems. Further, intelligent orchestration covering dynamic resource management, data-driven optimization, and intent-based operation may be developed to streamline operations of future networks. The potential of node programmability will be studied for improved development speed and flexibility.

Beam Failure Detection (BFD) and Beam Failure Recovery (BFR) In 5G NR, BFD is a WD functionality configured by a gNodeB (gNB) wherein the WD is configured with one or more beam failure detection (BFD) reference signals (RSs), which are transmitted in spatial directions (for example, beams) such as one or more synchronization signal block (SSB) and/or channel state information reference signals (CSI-RSs). The medium access control (MAC) entity of the WD triggers a beam failure recovery (BFR) when the number of beam failure indications (BFIs) received from the physical layer, reaches a maximum value configured by the network, i.e., when BF1 COUNTER >=beamFailureInstanceMaxCount. In addition, a timer is also configured, and the counter is incremented while the timer is running (i.e., before a configured timer expires).

BFD is supported for a Special Cell (SpCell), i.e., a Primary Cell (PCell) and/or a PSCell if WD is in mutual radio access technology dual connectivity (MR- DC)), and master cell group (MCG) SCell(s) and/or secondary cell group (SCG) SCell(s), if configured. Each MAC layer entity at the WD (e.g., MCG MAC entity and SCG MAC entity) controls its own BFD procedures. That is, the MAC MCG controls the BFD for the MCG, and the MAC SCG controls the BFD for the SCG.

After BFD is declared for the SpCell (e.g. PCell), the WD performs the following actions: triggers BFR by initiating a Random Access procedure on the PCell (in case BFD is declared at the PCell); selects a suitable beam to perform BFR (if the gNB has provided dedicated Random Access resources for certain beams, those will be prioritized by the WD); and includes an indication of a beam failure on PCell in a BFR MAC control element (CE) if the Random Access (RA) procedure involves contention-based random access.

Upon completion of the Random Access procedure, beam failure recovery is considered complete.

After beam failure is detected on an SCell, the WD: triggers beam failure recovery by initiating a transmission of a BFR MAC CE for this SCell; and selects a suitable beam for this SCell (if available) and indicates it along with the information about the beam failure in the BFR MAC CE.

Upon reception of a physical downlink control channel (PDCCH) indicating an uplink grant for a new transmission for the hybrid automatic repeat request (HARQ) process used for the transmission of the BFR MAC CE, beam failure recovery for this SCell is considered complete.

A problem to be addressed is that the information the WD transmits to the network during BFR about the SpCell (and/or SCell) is very limited and based on a snapshot (or LI filtered measurements), which leads to risk of subsequent failures when the network re-configures the WD and/or activates other LI configuration(s) at the WD due to BFD.

If the WD is configured with Contention-Free Random Access (CFRA), and triggers RA due to BFR, the WD selects an SSB (or CSLRS), which is equivalent to selecting a beam out of one of the candidate beams configured in BFR configuration (parameter candidateBeamRSList in 3GPP Technical Specification (TS) 38.331). The WD transmits and the network receives the Physical Random Access Channel (PRACH) preamble in one of the configured PRACH resources corresponding to the selected SSB (or CSLRS) by the WD (e.g., PRACH-ResourceDedicatedBFR)' and identifies the following: i) that this random access procedure is triggered due to BFD and BFR; ii) the WD which has triggered BFR; ii) the SSB (or CSLRS) that the WD has selected. As the network identifies the selected SSB (or CSLRS), and knows its associated downlink (DL) beam/ spatial direction, the network may transmit the Random Access Response (RAR) in the DL beam associated to that selected SSB (or CSLRS).

If the WD relies on Contention Based Random Access (CBRA) when BFR is triggered, the WD selects an SSB, also equivalent to selecting a beam. The network receives the physical random access channel (PRACH) preamble corresponding to the selected SSB by the WD. As the network identifies the selected SSB (or CSL RS), and knows its associated downlink beam/spatial direction, the network may transmit the RAR in the DL beam associated to that selected SSB (or CSLRS).

However, at that point the network (e.g., network node) is not able to identify that this random access (RA) procedure is triggered due to BFD and BFR, and is not able to identify the WD which has triggered BFR. That is why in CBRA, after the WD receives the RAR, the WD transmits a BFR MAC CE (defined in 3 GPP Rel-16) indicating that this RA was triggered due to BFR. In both CBRA and CFRA triggered by BFR, the WD selects an SSB or CSI- RS (i.e., a downlink beam), based on which the WD transmits a random-access preamble, which will be used as a reference by the network to reconfigure and/or update beam related parameters. Such beam-related parameters include: a) Transmission Configuration Indication (TCI) state(s) which were activated or need to be deactivated, and TCI state(s) which were deactivated and need to be activated; b) BFD resources to be monitored needs to be re-configured; c) beam candidate list(s) for BFR needs to be re-configured; d) CSI-MeasConfig needs to be reconfigured; e) SSB and/or CSI-RS resources to be LI measured and/or reported needs to be activated and/or deactivated.

The WD selects the beam (i.e., SSB and/or CSI-RS, or any other reference signal that may be used for at least the purpose of beam selection) whose measurement(s) indicate a good quality or received signal power (e.g., LI -reference signal received power (RSRP), and/or other link quality measurements like reference signal received quality (RSRQ), signal to interference plus noise ratio (SINR)). However, this may change which may lead the network to configure the WD with beam related configurations associated to a downlink beam (selected SSB and/or CSI-RS) which is sub-optimal. An example is shown in FIG. 1 where the WD selects the SSB-x having an SSB RSRP (SS-RSRP) at time instance tO that is above the suitability threshold, but quickly drops.

Misconfiguration of beam related parameters after BFD and BFR may lead to further BFD(s), Radio Link Failure(s), or subsequent re-configurations via radio resource control (RRC) signaling and/or activations/deactivated via MAC CE(s), to re-adjust the parameters based on further CSI reports. More signaling from/to the WD and/or network increases the WD power consumption, increases the risk of further failures, and degrades the data rates (as the WD is not always under the coverage of the beam providing the best radio link).

FIGS. 2 and 3 are flowcharts of beam failure recovery processes for contention based random access (FIG. 2) and contention free random access (FIG. 3).

SUMMARY

Some embodiments advantageously provide methods, network nodes and wireless devices (WD) for reporting time domain beam prediction information in beam failure recovery.

According to one aspect, the WD transmits one or more indications based on one or more time domain prediction(s) of measurements on one or more beams in response to a Beam Failure Detection (BFD).

According to another aspect, the network configures the WD for the transmission(s), and, the network (optionally) performs further actions in response to the one or more indications based on the one or time domain predict! on(s) of measurements on one or more beams in response to a Beam Failure Detection (BFD).

In some embodiments, the WD reception and reporting may be viewed as one procedure. Also, the WD may receive a reconfiguration from the network node in response as one procedure, which is an optional step that may be triggered by the network.

Some embodiments improve the robustness of the connectivity and improve WD data rates and throughput. Also, signaling reduction reduces the WD energy consumption (as fewer transmissions would occur due to fewer subsequent failures).

Hence, an advantage in some embodiments is a more robust connection, i.e., due to the transmission by the WD of one or more indications based on the one or time domain prediction(s) of measurements on one or more beams in response to a Beam Failure Detection (BFD). The WD’s beam related parameters are not misconfigured after BFD and BFR, so that further failures due to these possible misconfigurations may be prevented. In addition, as misconfigurations are avoided, the signaling is also reduced as the WD would be measuring and reporting according to a CSI measurement configuration (e.g., CSI-MeasConfig) associated to the beams that the WD is supposed to measured. In addition, the WD’s power consumption will also be reduced and data rates improved, e.g., as the WD will be under the coverage of the beam(s) and beam candidates that provide the best radio link.

Another advantage is that when the network node re-configures, activates or deactivates TCI states and LI resources to be measured and reported, the network node may reduce the number of resources that needs to be measured and/or monitored, due to the predictions reported by the WD. In that case, the WD reduces the power consumption and the latency for measuring the RSs. According to one aspect, a method in a wireless device, WD, configured to communicate with a network node, includes performing at least one time domain prediction of measurements of signals on at least one beam. The method also includes, in response to a beam failure detection, BFD, transmitting to the network node at least one time domain prediction.

According to this aspect, in some embodiments, the at least one time domain prediction is based at least in part on an output of a machine learning, ML, process, configured to predict measurements based on actual measurements of the signals. In some embodiments, the at least one time domain prediction includes at least one of an average of a series of time domain predictions and a statistical measure of a distribution of time domain predictions. In some embodiments, a measurement of a signal includes at least one of reference signal received power, RSRP, reference signal received quality, RSRQ, received signal strength indicator, RS SI, and signal to interference plus noise ratio. In some embodiments, beams for which signals are measured correspond to at least one of at least one beam configured for BFD monitoring, at least one candidate beam to be selected during a beam failure recovery, BFR, procedure and at least one beam configured for a channel state information, CSI, report. In some embodiments, the method includes, in response to the BFD, performing at least one of initiating a random access procedure when the BFD is for one of a primary cell and a special cell. In some embodiments, the method includes, in response to the BFD, triggering at least one scheduling request when the BFD is for a secondary cell and no uplink scheduling resources are available for a new transmission. In some embodiments, the method includes, in response to the BFD, initiating a contention free random access, CFRA, procedure for beam failure recovery, BFR. In some embodiments, the method includes, in response to the BFD, transmitting a first medium access control, MAC, control element, CE, on a first available physical uplink shared channel when the BFD is for a secondary cell, Scell, and uplink scheduling resources are available for a new transmission. In some embodiments, the method also includes performing the time domain predictions during a prediction window with a prediction periodicity configured by the network node. In some embodiments, the prediction periodicity is an integer multiple of a channel state information reporting periodicity. In some embodiments, the time domain predictions correspond to an average power of resource elements that carry secondary synchronization signals. In some embodiments, the time domain predictions include estimates of demodulation reference signals for a physical broadcast channel, PBCH. In some embodiments, the time domain predictions are based at least in part on an autoregressive, AR, model. In some embodiments, the method includes commencing the time domain predictions when a number of beam failure indications are counted. In some embodiments, the method includes comparing each time domain prediction to a threshold and transmitting only time domain predictions above the threshold. In some embodiments, the method includes transmitting to the network node times at which the time domain predictions are above the threshold. In some embodiments, the method includes transmitting to the network node an indication of a ratio of predictions above the threshold to a total number of predictions in a prediction interval. In some embodiments, the ratio of predictions is indicated by a set of at least one bit indicating a range of the ratio of predictions. In some embodiments, the method includes comparing a number of time domain predictions above the threshold to a counter value and setting a stability flag when the number of time domain predictions above the threshold exceed the counter value.

According to another aspect, a WD configured to communicate with a network node includes processing circuitry configured to perform at least one time domain prediction of measurements of signals on at least one beam. The WD also includes a radio interface in communication with the processing circuitry and configured to, in response to a beam failure detection, BFD, transmit to the network node at least one time domain prediction.

According to this aspect, in some embodiments, the at least one time domain prediction is based at least in part on an output of a machine learning, ML, process, configured to predict measurements based on actual measurements of the signals. In some embodiments, the at least one time domain prediction includes at least one of an average of a series of time domain predictions and a statistical measure of a distribution of time domain predictions. In some embodiments, a measurement of a signal includes at least one of reference signal received power, RSRP, reference signal received quality, RSRQ, received signal strength indicator, RS SI, and signal to interference plus noise ratio. In some embodiments, beams for which signals are measured correspond to at least one of at least one beam configured for BFD monitoring, at least one candidate beam to be selected during a beam failure recovery, BFR, procedure and at least one beam configured for a channel state information, CSI, report. In some embodiments, the processing circuitry is configured to, in response to the BFD, perform at least one of initiating a random access procedure when the BFD is for one of a primary cell and a special cell. In some embodiments, the processing circuitry is configured to, in response to the BFD, trigger at least one scheduling request when the BFD is for a secondary cell and no uplink scheduling resources are available for a new transmission. In some embodiments, the processing circuitry is configured to, in response to the BFD, initiate a contention free random access, CFRA, procedure for beam failure recovery, BFR. In some embodiments, the processing circuitry is configured to, in response to the BFD, transmit a first medium access control, MAC, control element, CE, on a first available physical uplink shared channel when the BFD is for a secondary cell, Scell, and uplink scheduling resources are available for a new transmission. In some embodiments, the processing circuitry is configured to perform the time domain predictions during a prediction window with a prediction periodicity configured by the network node. In some embodiments, the prediction periodicity is an integer multiple of a channel state information reporting periodicity. In some embodiments, the time domain predictions correspond to an average power of resource elements that carry secondary synchronization signals. In some embodiments, the time domain predictions include estimates of demodulation reference signals for a physical broadcast channel, PBCH. In some embodiments, the time domain predictions are based at least in part on an autoregressive, AR, model. In some embodiments, the processing circuitry is configured to commence the time domain predictions when a number of beam failure indications are counted. In some embodiments, the processing circuitry is configured to compare each time domain prediction to a threshold and transmitting only time domain predictions above the threshold. In some embodiments, the processing circuitry is configured to transmit to the network node times at which the time domain predictions are above the threshold. In some embodiments, the processing circuitry is configured to transmit to the network node an indication of a ratio of predictions above the threshold to a total number of predictions in a prediction interval. In some embodiments, the ratio of predictions is indicated by a set of at least one bit indicating a range of the ratio of predictions. In some embodiments, the processing circuitry is configured to compare a number of time domain predictions above the threshold to a counter value and setting a stability flag when the number of time domain predictions above the threshold exceed the counter value. According to another aspect, a method in a network node configured to communicate with a wireless device, WD, is provided. The method includes configuring the WD with at least one parameter to transmit at least one time domain prediction of measurements of signals on at least one beam in an event of beam failure detection, BFD, by the WD. The method also includes receiving from the WD, at least one time domain prediction of measurement of signals.

According to this aspect, in some embodiments, the method includes, in response to receiving the at least one time domain prediction, performing at least one of reconfiguring radio link monitoring reference signals, reconfiguring beam failure detection reference signals, reconfiguring at least one antenna parameter, one of activating, deactivating and reconfiguring transmission configuration indicator states, reconfiguring layer 1 resources and modifying at least one BFD reference signal to be monitored. In some embodiments, the method includes configuring the WD with at least one of a prediction periodicity, a number of predictions and a prediction window. In some embodiments, the method includes the prediction periodicity is an integer multiple of a channel state information reporting periodicity. In some embodiments, the method includes receiving from the WD a set of at least one time at which the time domain predictions are above a threshold.

According to yet another aspect, a network node configured to communicate with a wireless device, WD, is provided. The network node includes processing circuitry configured to configure the WD with at least one parameter to transmit at least one time domain prediction of measurements of signals on at least one beam in an event of beam failure detection, BFD, by the WD. The network node also includes a radio interface in communication with the processing circuitry and configured to receive from the WD, at least one time domain prediction of measurement of signals.

According to this aspect, in some embodiments, the processing circuitry is configured to, in response to receiving the at least one time domain prediction, perform at least one of reconfiguring radio link monitoring reference signals, reconfiguring beam failure detection reference signals, reconfiguring at least one antenna parameter, one of activating, deactivating and reconfiguring transmission configuration indicator states, reconfiguring layer 1 resources and modifying at least one BFD reference signal to be monitored. In some embodiments, the processing circuitry is configured to configure the WD with at least one of a prediction periodicity, a number of predictions and a prediction window. In some embodiments, the prediction periodicity is an integer multiple of a channel state information reporting periodicity. In some embodiments, the processing circuitry is configured to receiving from the WD a set of at least one time at which the time domain predictions are above a threshold.

BRIEF DESCRIPTION OF THE DRAWINGS

A more complete understanding of the present embodiments, and the attendant advantages and features thereof, will be more readily understood by reference to the following detailed description when considered in conjunction with the accompanying drawings wherein:

FIG. 1 illustrates beam selection relative to a threshold;

FIG. 2 illustrates BFR based on CBRA;

FIG. 3 illustrates BFR based on CFRA;

FIG. 4 is a schematic diagram of an example network architecture illustrating a communication system connected via an intermediate network to a host computer according to the principles in the present disclosure;

FIG. 5 is a block diagram of a host computer communicating via a network node with a wireless device over an at least partially wireless connection according to some embodiments of the present disclosure;

FIG. 6 is a flowchart illustrating example methods implemented in a communication system including a host computer, a network node and a wireless device for executing a client application at a wireless device according to some embodiments of the present disclosure;

FIG. 7 is a flowchart illustrating example methods implemented in a communication system including a host computer, a network node and a wireless device for receiving user data at a wireless device according to some embodiments of the present disclosure;

FIG. 8 is a flowchart illustrating example methods implemented in a communication system including a host computer, a network node and a wireless device for receiving user data from the wireless device at a host computer according to some embodiments of the present disclosure;

FIG. 9 is a flowchart illustrating example methods implemented in a communication system including a host computer, a network node and a wireless device for receiving user data at a host computer according to some embodiments of the present disclosure;

FIG. 10 is a flowchart of an example process in a network node for reporting time domain beam prediction information in beam failure recovery according to some embodiments of the present disclosure;

FIG. 11 is a flowchart of an example process in a wireless device for reporting time domain beam prediction information in beam failure recovery according to some embodiments of the present disclosure;

FIG. 12 is a flowchart of another example process in a WD for reporting time domain beam prediction information in beam failure recovery according to some embodiments of the present disclosure;

FIG. 13 is a flowchart of another example process in a network node for reporting time domain beam prediction information in beam failure recovery according to some embodiments of the present disclosure;

FIG. 14 is a block diagram of a WD configured with ML capability;

FIG. 15 is an example of BFR based on CBRA;

FIG. 16 is an example of BFR based on CFRA;

FIG. 17 is an example of SS-RSRP predictions for two different beams;

FIG. 18 is an example of a probability density function for reference signal received power;

FIG. 19 is an example of prediction of stability for a beam having a reference signal received power greater than a threshold over a period of time;

FIG. 20 is an example of prediction of instability for a beam having a reference signal received power less than a threshold over a period of time; and

FIG. 21 is an example of prediction of instability for one beam and stability for another beam.

DETAILED DESCRIPTION

Before describing in detail example embodiments, it is noted that the embodiments reside primarily in combinations of apparatus components and processing steps related to reporting time domain beam prediction information in beam failure recovery. Accordingly, components have been represented where appropriate by conventional symbols in the drawings, showing only those specific details that are pertinent to understanding the embodiments so as not to obscure the disclosure with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein. Like numbers refer to like elements throughout the description.

As used herein, relational terms, such as “first” and “second,” “top” and “bottom,” and the like, may be used solely to distinguish one entity or element from another entity or element without necessarily requiring or implying any physical or logical relationship or order between such entities or elements. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the concepts described herein. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and/or “including” when used herein, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

In embodiments described herein, the joining term, “in communication with” and the like, may be used to indicate electrical or data communication, which may be accomplished by physical contact, induction, electromagnetic radiation, radio signaling, infrared signaling or optical signaling, for example. One having ordinary skill in the art will appreciate that multiple components may interoperate and modifications and variations are possible of achieving the electrical and data communication.

In some embodiments described herein, the term “coupled,” “connected,” and the like, may be used herein to indicate a connection, although not necessarily directly, and may include wired and/or wireless connections.

The term “network node” used herein may be any kind of network node comprised in a radio network which may further comprise any of base station (BS), radio base station, base transceiver station (BTS), base station controller (BSC), radio network controller (RNC), g Node B (gNB), evolved Node B (eNB or eNodeB), Node B, multi -standard radio (MSR) radio node such as MSR BS, multi-cell/multicast coordination entity (MCE), integrated access and backhaul (IAB) node, relay node, donor node controlling relay, radio access point (AP), transmission points, transmission nodes, Remote Radio Unit (RRU) Remote Radio Head (RRH), a core network node (e.g., mobile management entity (MME), self-organizing network (SON) node, a coordinating node, positioning node, MDT node, etc.), an external node (e.g., 3rd party node, a node external to the current network), nodes in distributed antenna system (DAS), a spectrum access system (SAS) node, an element management system (EMS), etc. The network node may also comprise test equipment. The term “radio node” used herein may be used to also denote a wireless device (WD) such as a wireless device (WD) or a radio network node.

In some embodiments, the non-limiting terms wireless device (WD) or a user equipment (UE) are used interchangeably. The WD herein may be any type of wireless device capable of communicating with a network node or another WD over radio signals, such as wireless device (WD). The WD may also be a radio communication device, target device, device to device (D2D) WD, machine type WD or WD capable of machine to machine communication (M2M), low-cost and/or low- complexity WD, a sensor equipped with WD, Tablet, mobile terminals, smart phone, laptop embedded equipped (LEE), laptop mounted equipment (LME), USB dongles, Customer Premises Equipment (CPE), an Internet of Things (loT) device, or a Narrowband loT (NB-IOT) device, etc.

Also, in some embodiments the generic term “radio network node” is used. It may be any kind of a radio network node which may comprise any of base station, radio base station, base transceiver station, base station controller, network controller, RNC, evolved Node B (eNB), Node B, gNB, Multi-cell/multicast Coordination Entity (MCE), IAB node, relay node, access point, radio access point, Remote Radio Unit (RRU) Remote Radio Head (RRH).

Note that although terminology from one particular wireless system, such as, for example, 3 GPP LTE and/or New Radio (NR), may be used in this disclosure, this should not be seen as limiting the scope of the disclosure to only the aforementioned system. Other wireless systems, including without limitation Wide Band Code Division Multiple Access (WCDMA), Worldwide Interoperability for Microwave Access (WiMax), Ultra Mobile Broadband (UMB) and Global System for Mobile Communications (GSM), may also benefit from exploiting the ideas covered within this disclosure.

Note further, that functions described herein as being performed by a wireless device or a network node may be distributed over a plurality of wireless devices and/or network nodes. In other words, it is contemplated that the functions of the network node and wireless device described herein are not limited to performance by a single physical device and, in fact, may be distributed among several physical devices.

In some embodiments, the general description elements in the form of “one of A and B” corresponds to A or B. In some embodiments, at least one of A and B corresponds to A, B or AB, or to one or more of A and B. In some embodiments, at least one of A, B and C corresponds to one or more of A, B and C, and/or A, B, C or a combination thereof.

Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. It will be further understood that terms used herein should be interpreted as having a meaning that is consistent with their meaning in the context of this specification and the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

Some embodiments provide reporting time domain beam prediction information in beam failure recovery.

Returning now to the drawing figures, in which like elements are referred to by like reference numerals, there is shown in FIG. 4 a schematic diagram of a communication system 10, according to an embodiment, such as a 3 GPP -type cellular network that may support standards such as LTE and/or NR (5G), which comprises an access network 12, such as a radio access network, and a core network 14. The access network 12 comprises a plurality of network nodes 16a, 16b, 16c (referred to collectively as network nodes 16), such as NBs, eNBs, gNBs or other types of wireless access points, each defining a corresponding coverage area 18a, 18b, 18c (referred to collectively as coverage areas 18). Each network node 16a, 16b, 16c is connectable to the core network 14 over a wired or wireless connection 20. A first wireless device (WD) 22a located in coverage area 18a is configured to wirelessly connect to, or be paged by, the corresponding network node 16a. A second WD 22b in coverage area 18b is wirelessly connectable to the corresponding network node 16b. While a plurality of WDs 22a, 22b (collectively referred to as wireless devices 22) are illustrated in this example, the disclosed embodiments are equally applicable to a situation where a sole WD is in the coverage area or where a sole WD is connecting to the corresponding network node 16. Note that although only two WDs 22 and three network nodes 16 are shown for convenience, the communication system may include many more WDs 22 and network nodes 16.

Also, it is contemplated that a WD 22 may be in simultaneous communication and/or configured to separately communicate with more than one network node 16 and more than one type of network node 16. For example, a WD 22 may have dual connectivity with a network node 16 that supports LTE and the same or a different network node 16 that supports NR. As an example, WD 22 may be in communication with an eNB for LTE/E-UTRAN and a gNB for NR/NG-RAN.

The communication system 10 may itself be connected to a host computer 24, which may be embodied in the hardware and/or software of a standalone server, a cloud-implemented server, a distributed server or as processing resources in a server farm. The host computer 24 may be under the ownership or control of a service provider, or may be operated by the service provider or on behalf of the service provider. The connections 26, 28 between the communication system 10 and the host computer 24 may extend directly from the core network 14 to the host computer 24 or may extend via an optional intermediate network 30. The intermediate network 30 may be one of, or a combination of more than one of, a public, private or hosted network. The intermediate network 30, if any, may be a backbone network or the Internet. In some embodiments, the intermediate network 30 may comprise two or more sub-networks (not shown).

The communication system of FIG. 4 as a whole enables connectivity between one of the connected WDs 22a, 22b and the host computer 24. The connectivity may be described as an over-the-top (OTT) connection. The host computer 24 and the connected WDs 22a, 22b are configured to communicate data and/or signaling via the OTT connection, using the access network 12, the core network 14, any intermediate network 30 and possible further infrastructure (not shown) as intermediaries. The OTT connection may be transparent in the sense that at least some of the participating communication devices through which the OTT connection passes are unaware of routing of uplink and downlink communications. For example, a network node 16 may not or need not be informed about the past routing of an incoming downlink communication with data originating from a host computer 24 to be forwarded (e.g., handed over) to a connected WD 22a. Similarly, the network node 16 need not be aware of the future routing of an outgoing uplink communication originating from the WD 22a towards the host computer 24.

A network node 16 is configured to include a configuration unit 32 which is configured to configure the WD with at least one parameter for performing at least one time domain prediction of measurements of signals on at least one beam in an event of beam failure detection (BFD). . A wireless device 22 is configured to include a measurement unit 34 which is configured to perform at least one time domain prediction of measurements of signals on at least one beam.

Example implementations, in accordance with an embodiment, of the WD 22, network node 16 and host computer 24 discussed in the preceding paragraphs will now be described with reference to FIG. 5. In a communication system 10, a host computer 24 comprises hardware (HW) 38 including a communication interface 40 configured to set up and maintain a wired or wireless connection with an interface of a different communication device of the communication system 10. The host computer 24 further comprises processing circuitry 42, which may have storage and/or processing capabilities. The processing circuitry 42 may include a processor 44 and memory 46. In particular, in addition to or instead of a processor, such as a central processing unit, and memory, the processing circuitry 42 may comprise integrated circuitry for processing and/or control, e.g., one or more processors and/or processor cores and/or FPGAs (Field Programmable Gate Array) and/or ASICs (Application Specific Integrated Circuitry) adapted to execute instructions. The processor 44 may be configured to access (e.g., write to and/or read from) memory 46, which may comprise any kind of volatile and/or nonvolatile memory, e.g., cache and/or buffer memory and/or RAM (Random Access Memory) and/or ROM (Read- Only Memory) and/or optical memory and/or EPROM (Erasable Programmable Read-Only Memory).

Processing circuitry 42 may be configured to control any of the methods and/or processes described herein and/or to cause such methods, and/or processes to be performed, e.g., by host computer 24. Processor 44 corresponds to one or more processors 44 for performing host computer 24 functions described herein. The host computer 24 includes memory 46 that is configured to store data, programmatic software code and/or other information described herein. In some embodiments, the software 48 and/or the host application 50 may include instructions that, when executed by the processor 44 and/or processing circuitry 42, causes the processor 44 and/or processing circuitry 42 to perform the processes described herein with respect to host computer 24. The instructions may be software associated with the host computer 24.

The software 48 may be executable by the processing circuitry 42. The software 48 includes a host application 50. The host application 50 may be operable to provide a service to a remote user, such as a WD 22 connecting via an OTT connection 52 terminating at the WD 22 and the host computer 24. In providing the service to the remote user, the host application 50 may provide user data which is transmitted using the OTT connection 52. The “user data” may be data and information described herein as implementing the described functionality. In one embodiment, the host computer 24 may be configured for providing control and functionality to a service provider and may be operated by the service provider or on behalf of the service provider. The processing circuitry 42 of the host computer 24 may enable the host computer 24 to observe, monitor, control, transmit to and/or receive from the network node 16 and or the wireless device 22. The host computer 24 may be configured to perform some or all functions attributed to the network node 16, herein.

The communication system 10 further includes a network node 16 provided in a communication system 10 and including hardware 58 enabling it to communicate with the host computer 24 and with the WD 22. The hardware 58 may include a communication interface 60 for setting up and maintaining a wired or wireless connection with an interface of a different communication device of the communication system 10, as well as a radio interface 62 for setting up and maintaining at least a wireless connection 64 with a WD 22 located in a coverage area 18 served by the network node 16. The radio interface 62 may be formed as or may include, for example, one or more RF transmitters, one or more RF receivers, and/or one or more RF transceivers. The communication interface 60 may be configured to facilitate a connection 66 to the host computer 24. The connection 66 may be direct or it may pass through a core network 14 of the communication system 10 and/or through one or more intermediate networks 30 outside the communication system 10.

In the embodiment shown, the hardware 58 of the network node 16 further includes processing circuitry 68. The processing circuitry 68 may include a processor 70 and a memory 72. In particular, in addition to or instead of a processor, such as a central processing unit, and memory, the processing circuitry 68 may comprise integrated circuitry for processing and/or control, e.g., one or more processors and/or processor cores and/or FPGAs (Field Programmable Gate Array) and/or ASICs (Application Specific Integrated Circuitry) adapted to execute instructions. The processor 70 may be configured to access (e.g., write to and/or read from) the memory 72, which may comprise any kind of volatile and/or nonvolatile memory, e.g., cache and/or buffer memory and/or RAM (Random Access Memory) and/or ROM (Read-Only Memory) and/or optical memory and/or EPROM (Erasable Programmable Read-Only Memory).

Thus, the network node 16 further has software 74 stored internally in, for example, memory 72, or stored in external memory (e.g., database, storage array, network storage device, etc.) accessible by the network node 16 via an external connection. The software 74 may be executable by the processing circuitry 68. The processing circuitry 68 may be configured to control any of the methods and/or processes described herein and/or to cause such methods, and/or processes to be performed, e.g., by network node 16. Processor 70 corresponds to one or more processors 70 for performing network node 16 functions described herein. The memory 72 is configured to store data, programmatic software code and/or other information described herein. In some embodiments, the software 74 may include instructions that, when executed by the processor 70 and/or processing circuitry 68, causes the processor 70 and/or processing circuitry 68 to perform the processes described herein with respect to network node 16. For example, processing circuitry 68 of the network node 16 may include a configuration unit 32 which is configured to configure the WD with at least one parameter for performing at least one time domain prediction of measurements of signals on at least one beam in an event of beam failure detection (BFD).

The communication system 10 further includes the WD 22 already referred to. The WD 22 may have hardware 80 that may include a radio interface 82 configured to set up and maintain a wireless connection 64 with a network node 16 serving a coverage area 18 in which the WD 22 is currently located. The radio interface 82 may be formed as or may include, for example, one or more RF transmitters, one or more RF receivers, and/or one or more RF transceivers.

The hardware 80 of the WD 22 further includes processing circuitry 84. The processing circuitry 84 may include a processor 86 and memory 88. In particular, in addition to or instead of a processor, such as a central processing unit, and memory, the processing circuitry 84 may comprise integrated circuitry for processing and/or control, e.g., one or more processors and/or processor cores and/or FPGAs (Field Programmable Gate Array) and/or ASICs (Application Specific Integrated Circuitry) adapted to execute instructions. The processor 86 may be configured to access (e.g., write to and/or read from) memory 88, which may comprise any kind of volatile and/or nonvolatile memory, e.g., cache and/or buffer memory and/or RAM (Random Access Memory) and/or ROM (Read-Only Memory) and/or optical memory and/or EPROM (Erasable Programmable Read-Only Memory).

Thus, the WD 22 may further comprise software 90, which is stored in, for example, memory 88 at the WD 22, or stored in external memory (e.g., database, storage array, network storage device, etc.) accessible by the WD 22. The software 90 may be executable by the processing circuitry 84. The software 90 may include a client application 92. The client application 92 may be operable to provide a service to a human or non-human user via the WD 22, with the support of the host computer 24. In the host computer 24, an executing host application 50 may communicate with the executing client application 92 via the OTT connection 52 terminating at the WD 22 and the host computer 24. In providing the service to the user, the client application 92 may receive request data from the host application 50 and provide user data in response to the request data. The OTT connection 52 may transfer both the request data and the user data. The client application 92 may interact with the user to generate the user data that it provides.

The processing circuitry 84 may be configured to control any of the methods and/or processes described herein and/or to cause such methods, and/or processes to be performed, e.g., by WD 22. The processor 86 corresponds to one or more processors 86 for performing WD 22 functions described herein. The WD 22 includes memory 88 that is configured to store data, programmatic software code and/or other information described herein. In some embodiments, the software 90 and/or the client application 92 may include instructions that, when executed by the processor 86 and/or processing circuitry 84, causes the processor 86 and/or processing circuitry 84 to perform the processes described herein with respect to WD 22. For example, the processing circuitry 84 of the wireless device 22 may include a measurement unit 34 which is configured to perform at least one time domain prediction of measurements of signals on at least one beam. In some embodiments, the inner workings of the network node 16, WD 22, and host computer 24 may be as shown in FIG. 5 and independently, the surrounding network topology may be that of FIG. 4.

In FIG. 5, the OTT connection 52 has been drawn abstractly to illustrate the communication between the host computer 24 and the wireless device 22 via the network node 16, without explicit reference to any intermediary devices and the precise routing of messages via these devices. Network infrastructure may determine the routing, which it may be configured to hide from the WD 22 or from the service provider operating the host computer 24, or both. While the OTT connection 52 is active, the network infrastructure may further take decisions by which it dynamically changes the routing (e.g., on the basis of load balancing consideration or reconfiguration of the network).

The wireless connection 64 between the WD 22 and the network node 16 is in accordance with the teachings of the embodiments described throughout this disclosure. One or more of the various embodiments improve the performance of OTT services provided to the WD 22 using the OTT connection 52, in which the wireless connection 64 may form the last segment. More precisely, the teachings of some of these embodiments may improve the data rate, latency, and/or power consumption and thereby provide benefits such as reduced user waiting time, relaxed restriction on file size, better responsiveness, extended battery lifetime, etc.

In some embodiments, a measurement procedure may be provided for the purpose of monitoring data rate, latency and other factors on which the one or more embodiments improve. There may further be an optional network functionality for reconfiguring the OTT connection 52 between the host computer 24 and WD 22, in response to variations in the measurement results. The measurement procedure and/or the network functionality for reconfiguring the OTT connection 52 may be implemented in the software 48 of the host computer 24 or in the software 90 of the WD 22, or both. In embodiments, sensors (not shown) may be deployed in or in association with communication devices through which the OTT connection 52 passes; the sensors may participate in the measurement procedure by supplying values of the monitored quantities exemplified above, or supplying values of other physical quantities from which software 48, 90 may compute or estimate the monitored quantities. The reconfiguring of the OTT connection 52 may include message format, retransmission settings, preferred routing etc.; the reconfiguring need not affect the network node 16, and it may be unknown or imperceptible to the network node 16. Some such procedures and functionalities may be known and practiced in the art. In certain embodiments, measurements may involve proprietary WD signaling facilitating the host computer’s 24 measurements of throughput, propagation times, latency and the like. In some embodiments, the measurements may be implemented in that the software 48, 90 causes messages to be transmitted, in particular empty or ‘dummy’ messages, using the OTT connection 52 while it monitors propagation times, errors, etc.

Thus, in some embodiments, the host computer 24 includes processing circuitry 42 configured to provide user data and a communication interface 40 that is configured to forward the user data to a cellular network for transmission to the WD 22. In some embodiments, the cellular network also includes the network node 16 with a radio interface 62. In some embodiments, the network node 16 is configured to, and/or the network node’s 16 processing circuitry 68 is configured to perform the functions and/or methods described herein for preparing/initiating/maintaining/ supporting/ending a transmission to the WD 22, and/or preparing/terminating/ maintaining/supporting/ending in receipt of a transmission from the WD 22.

In some embodiments, the host computer 24 includes processing circuitry 42 and a communication interface 40 that is configured to a communication interface 40 configured to receive user data originating from a transmission from a WD 22 to a network node 16. In some embodiments, the WD 22 is configured to, and/or comprises a radio interface 82 and/or processing circuitry 84 configured to perform the functions and/or methods described herein for preparing/initiating/maintaining/ supporting/ending a transmission to the network node 16, and/or preparing/ terminating/maintaining/supporting/ending in receipt of a transmission from the network node 16.

Although FIGS. 4 and 5 show various “units” such as configuration unit 32, and measurement unit 34 as being within a respective processor, it is contemplated that these units may be implemented such that a portion of the unit is stored in a corresponding memory within the processing circuitry. In other words, the units may be implemented in hardware or in a combination of hardware and software within the processing circuitry.

FIG. 6 is a flowchart illustrating an example method implemented in a communication system, such as, for example, the communication system of FIGS. 4 and 5, in accordance with one embodiment. The communication system may include a host computer 24, a network node 16 and a WD 22, which may be those described with reference to FIG. 5. In a first step of the method, the host computer 24 provides user data (Block SI 00). In an optional substep of the first step, the host computer 24 provides the user data by executing a host application, such as, for example, the host application 50 (Block SI 02). In a second step, the host computer 24 initiates a transmission carrying the user data to the WD 22 (Block SI 04). In an optional third step, the network node 16 transmits to the WD 22 the user data which was carried in the transmission that the host computer 24 initiated, in accordance with the teachings of the embodiments described throughout this disclosure (Block SI 06). In an optional fourth step, the WD 22 executes a client application, such as, for example, the client application 92, associated with the host application 50 executed by the host computer 24 (Block SI 08).

FIG. 7 is a flowchart illustrating an example method implemented in a communication system, such as, for example, the communication system of FIG. 4, in accordance with one embodiment. The communication system may include a host computer 24, a network node 16 and a WD 22, which may be those described with reference to FIGS. 4 and 5. In a first step of the method, the host computer 24 provides user data (Block SI 10). In an optional substep (not shown) the host computer 24 provides the user data by executing a host application, such as, for example, the host application 50. In a second step, the host computer 24 initiates a transmission carrying the user data to the WD 22 (Block SI 12). The transmission may pass via the network node 16, in accordance with the teachings of the embodiments described throughout this disclosure. In an optional third step, the WD 22 receives the user data carried in the transmission (Block SI 14).

FIG. 8 is a flowchart illustrating an example method implemented in a communication system, such as, for example, the communication system of FIG. 4, in accordance with one embodiment. The communication system may include a host computer 24, a network node 16 and a WD 22, which may be those described with reference to FIGS. 4 and 5. In an optional first step of the method, the WD 22 receives input data provided by the host computer 24 (Block SI 16). In an optional substep of the first step, the WD 22 executes the client application 92, which provides the user data in reaction to the received input data provided by the host computer 24 (Block SI 18). Additionally or alternatively, in an optional second step, the WD 22 provides user data (Block S120). In an optional substep of the second step, the WD provides the user data by executing a client application, such as, for example, client application 92 (Block S122). In providing the user data, the executed client application 92 may further consider user input received from the user. Regardless of the specific manner in which the user data was provided, the WD 22 may initiate, in an optional third substep, transmission of the user data to the host computer 24 (Block S124). In a fourth step of the method, the host computer 24 receives the user data transmitted from the WD 22, in accordance with the teachings of the embodiments described throughout this disclosure (Block S126).

FIG. 9 is a flowchart illustrating an example method implemented in a communication system, such as, for example, the communication system of FIG. 4, in accordance with one embodiment. The communication system may include a host computer 24, a network node 16 and a WD 22, which may be those described with reference to FIGS. 4 and 5. In an optional first step of the method, in accordance with the teachings of the embodiments described throughout this disclosure, the network node 16 receives user data from the WD 22 (Block S128). In an optional second step, the network node 16 initiates transmission of the received user data to the host computer 24 (Block SI 30). In a third step, the host computer 24 receives the user data carried in the transmission initiated by the network node 16 (Block SI 32).

FIG. 10 is a flowchart of an example process in a network node 16 for reporting time domain beam prediction information in beam failure recovery. One or more blocks described herein may be performed by one or more elements of network node 16 such as by one or more of processing circuitry 68 (including the configuration unit 32), processor 70, radio interface 62 and/or communication interface 60. Network node 16 such as via processing circuitry 68 and/or processor 70 and/or radio interface 62 and/or communication interface 60 is configured to receive at least one indication of a predicted measurement from the WD based at least in part on at least one time domain prediction of measurements on at least one beam in response to a beam failure detection, BFD, at the WD (Block SI 34). The process also includes configuring the WD with at least one parameter for performing the at least one time domain prediction of measurements based at least in part on the at least one indication (Block SI 36).

In some embodiments, the process also includes reconfiguring at least one of reference signals and transmission configuration indicator, TCI, states. In some embodiments, the at least one indication includes a statistical metric based at least in part on a distribution of time domain predictions of measurements. In some embodiments, the at least one indication includes a beam identifier based at least in part on the at least one time domain prediction of measurements. In some embodiments, the at least one indication includes a references signal identifier.

FIG. 11 is a flowchart of an example process in a wireless device 22 according to some embodiments of the present disclosure. One or more blocks described herein may be performed by one or more elements of wireless device 22 such as by one or more of processing circuitry 84 (including the measurement unit 34), processor 86, radio interface 82 and/or communication interface 60. Wireless device 22 such as via processing circuitry 84 and/or processor 86 and/or radio interface 82 is configured to perform at least one time domain prediction of measurements on at least one beam in response to a beam failure detection, BFD (Block S138). The process also includes transmitting at least one indication of the at least one time domain prediction of measurements (Block SI 40).

In some embodiments, the at least one indication includes a statistical metric based at least in part on a distribution of time domain predictions of measurements. In some embodiments, the at least one indication includes a beam identifier based at least in part on the at least one time domain prediction of measurements. In some embodiments, the at least one indication includes a references signal identifier. In some embodiments, the at least one beam includes at least one of a beam configured for BFD monitoring, a candidate beam, a beam selected during beam failure recovery, BFR, and a beam configured for a channel state information, CSI, report.

FIG. 12 is a flowchart of an example process in a wireless device 22 according to some embodiments of the present disclosure. One or more blocks described herein may be performed by one or more elements of wireless device 22 such as by one or more of processing circuitry 84 (including the measurement unit 34), processor 86, radio interface 82 and/or communication interface 60. Wireless device 22 such as via processing circuitry 84 and/or processor 86 and/or radio interface 82 is configured to perform at least one time domain prediction of measurements of signals on at least one beam (Block S142). The method also includes, in response to a beam failure detection, BFD, transmitting to the network node 16 at least one time domain prediction (Block SI 44).

In some embodiments, the at least one time domain prediction is based at least in part on an output of a machine learning, ML, process, configured to predict measurements based on actual measurements of the signals. In some embodiments, the at least one time domain prediction includes at least one of an average of a series of time domain predictions and a statistical measure of a distribution of time domain predictions. In some embodiments, a measurement of a signal includes at least one of reference signal received power, RSRP, reference signal received quality, RSRQ, received signal strength indicator, RSSI, and signal to interference plus noise ratio. In some embodiments, beams for which signals are measured correspond to at least one of at least one beam configured for BFD monitoring, at least one candidate beam to be selected during a beam failure recovery, BFR, procedure and at least one beam configured for a channel state information, CSI, report. In some embodiments, the method includes, in response to the BFD, performing at least one of initiating a random access procedure when the BFD is for one of a primary cell and a special cell. In some embodiments, the method includes, in response to the BFD, triggering at least one scheduling request when the BFD is for a secondary cell and no uplink scheduling resources are available for a new transmission. In some embodiments, the method includes, in response to the BFD, initiating a contention free random access, CFRA, procedure for beam failure recovery, BFR. In some embodiments, the method includes, in response to the BFD, transmitting a first medium access control, MAC, control element, CE, on a first available physical uplink shared channel when the BFD is for a secondary cell, Scell, and uplink scheduling resources are available for a new transmission. In some embodiments, the method also includes performing the time domain predictions during a prediction window with a prediction periodicity configured by the network node. In some embodiments, the prediction periodicity is an integer multiple of a channel state information reporting periodicity. In some embodiments, the time domain predictions correspond to an average power of resource elements that carry secondary synchronization signals. In some embodiments, the time domain predictions include estimates of demodulation reference signals for a physical broadcast channel, PBCH. In some embodiments, the time domain predictions are based at least in part on an autoregressive, AR, model. In some embodiments, the method includes commencing the time domain predictions when a number of beam failure indications are counted. In some embodiments, the method includes comparing each time domain prediction to a threshold and transmitting only time domain predictions above the threshold. In some embodiments, the method includes transmitting to the network node times at which the time domain predictions are above the threshold. In some embodiments, the method includes transmitting to the network node an indication of a ratio of predictions above the threshold to a total number of predictions in a prediction interval. In some embodiments, the ratio of predictions is indicated by a set of at least one bit indicating a range of the ratio of predictions. In some embodiments, the method includes comparing a number of time domain predictions above the threshold to a counter value and setting a stability flag when the number of time domain predictions above the threshold exceed the counter value.

FIG. 13 is a flowchart of an example process in a network node 16 for reporting time domain beam prediction information in beam failure recovery. One or more blocks described herein may be performed by one or more elements of network node 16 such as by one or more of processing circuitry 68 (including the configuration unit 32), processor 70, radio interface 62 and/or communication interface 60. Network node 16 such as via processing circuitry 68 and/or processor 70 and/or radio interface 62 and/or communication interface 60 is configured to configure the WD 22 with at least one parameter to transmit at least one time domain prediction of measurements of signals on at least one beam in an event of beam failure detection, BFD, by the WD 22 (Block S146). The method also includes receiving from the WD 22 at least one time domain prediction of measurement of signals (Block S148)

In some embodiments, the method includes, in response to receiving the at least one time domain prediction, performing at least one of reconfiguring radio link monitoring reference signals, reconfiguring beam failure detection reference signals, reconfiguring at least one antenna parameter, one of activating, deactivating and reconfiguring transmission configuration indicator states, reconfiguring layer 1 resources and modifying at least one BFD reference signal to be monitored. In some embodiments, the method includes configuring the WD 22 with at least one of a prediction periodicity, a number of predictions and a prediction window. In some embodiments, the method includes the prediction periodicity is an integer multiple of a channel state information reporting periodicity. In some embodiments, the method includes receiving from the WD 22 a set of at least one time at which the time domain predictions are above a threshold.

Having described the general process flow of arrangements of the disclosure and having provided examples of hardware and software arrangements for implementing the processes and functions of the disclosure, the sections below provide details and examples of arrangements for reporting time domain beam prediction information in beam failure recovery.

Some embodiments include a method at a WD 22 and at a network node 16 for reporting information based on predictions in the time domain of beam measurements during a Beam Failure Recovery (BFR) procedure.

WD method

A method at a WD 22 operating with at least one ML model based on which the WD 22 performs one or more time-domain predictions, may include transmitting one or more indications based on one or more time domain prediction(s) of measurements on one or more beams in response to a Beam Failure Detection (BFD).

The one or more beams may correspond to at least the following: one or more beams configured for BFD monitoring; one or more candidate beams (candidates to be selected during BFR); one or more selected beams (selected during BFR); one or more beams configured for other procedures, e.g., not for BFD monitoring; and/or one or more beams configured for CSI report.

The signal transmitted on one or more beams may be CSLRS (including a tracking reference signal (TRS) (CSLRS for tracking)), SSB, cell specific reference signal (CRS), demodulation reference signal (DMRS), phase tracking reference signal (PTRS).

Prior to transmitting the one or more indications, the WD 22 may perform one or more time domain prediction(s) of measurements on one or more beams, such as time-domain predictions/ estimates of SS-RSRP, CSLRSRP, SS-RSRQ, CSLRSRQ, SS-SINR, CSLSINR, as defined in 3GPP Technical Standard (TS) 38.215. Then, the WD 22 may generate the one or more indications based on one or more time domain prediction(s) of measurements on one or more beams, to be transmitted to the network in response to the BFD. The one or more time-domain predictions (estimates) on one or more beams may be the output of an ML-model 94 (or Al-model, or Model Inference function) implemented at the WD 22. This is shown in FIG. 14. The output(s) are received by the function 96 which generates the one or more indications, which may correspond to the “actor” in this process. A another function 98 includes configuring a first Medium Access Control (MAC) Control Element,

In some embodiments, the WD 22 transmits the one or time domain prediction(s) of measurements on one or more beams in response to a BFD and transmitting the one or more indications based on time domain prediction(s) of measurements on the one or more beams in a first Medium Access Control (MAC) Control Element, and the WD 22 transmitting the first MAC CE to the network node 16.

In some embodiments, the WD 22 transmits one or more indications based on the one or time domain prediction(s) of measurements on one or more beams in response to a Beam Failure Detection (BFD) and initiates a Random Access (RA) procedure (triggered by BFR upon declaring BFD), when the BFD is for a primary cell/ special cell (e.g., SpCell, PCell, PSCell as defined in 3GPP TS 38.331). The WD 22 may select a first beam (and/or RS) and an associated RA resource (e.g., preamble, RA time and/or frequency resource) to transmit the preamble, transmitting the preamble and receiving a PDCCH or/and a RAR, so that upon receiving the physical downlink control channel (PDCCH) or/and the RAR, the WD 22 may generate and transmit the first MAC CE.

In some embodiments, the WD 22 transmits one or more indications based on the one or time domain prediction(s) of measurements on one or more beams in response to a Beam Failure Detection (BFD) and triggers at least one scheduling request (SR) (e.g., over physical uplink control channel (PUCCH), physical uplink shared channel (PUSCH), or PRACH) when BFD is for a SCell and no UL-SCH resource is available for a new transmission or when the WD 22 initiates a CFRA procedure for BFR. The WD 22 may receive an uplink scheduling grant from the network and may transmit its first MAC CE on the scheduled PUSCH.

In some embodiments, the WD 22 transmits one or more indications based on the one or time domain prediction(s) of measurements on one or more beams in response to a Beam Failure Detection (BFD) and transmits the first MAC CE on the first available PUSCH for new transmission, when BFD is for a SCell and UL-SCH resources are available for a new transmission.

In some embodiments, the WD 22 is configured by a network node 16 with one or more parameters and/or configurations associated to the transmitting step. These may be parameters indicating what to transmit and/or how to transmit (e.g., in which message, in which format of a given message, in which protocol layer, etc.).

In some embodiments, the WD 22 is configured by a network node 16 with one or more parameters and/or configurations for the WD 22 to perform the one or time domain prediction(s) of measurements on one or more beams. In some embodiments, the WD 22 receives a reconfiguration (and/or an update command) from the network node 16, in response to transmitting the one or more indications based on the one or time domain prediction(s) of measurements (e.g. in the first MAC CE), wherein the response indicates one or more of reconfigured radio link monitoring (RLM)-reference signals (RSs;) reconfigured BFD RSs; reconfigured one or more antenna parameters related to the RLM/BFD RSs, for selecting antenna parameters that forms more wider/ narrow beam(s); activated/deactivated TCI state(s); re-configured TCI states; re-configured LI resources to be measured/ reports; and/or modification of at least one of the BFD-RS(s) to be monitored e.g. via transmissions of a DCI or MAC CE.

Note: a reconfiguration may correspond to an RRC message (e.g., RRCReconfiguration, RRCConnectionReconfiguration). An update command may correspond to a MAC Control Element (MAC CE) indicating the activation and/or deactivation and/or switching of one or more configuration(s), such as TCI state activation/ deactivation.

Network (e.g., network node 16) method

In some embodiments, a method in a network node 16 (e.g., gNodeB, RAN node in a 6G radio access network), includes receiving one or more indications from a WD 22 based on one or more time domain predict! on(s) of measurements on one or more beams in response to a Beam Failure Detection (BFD) at the WD 22.

The method at a network node 16 may include configuring the WD 22 with one or more parameters for the WD 22 to transmit one or more indications from a WD 22 based on one or more time domain prediction(s) of measurements on one or more beams in response to a Beam Failure Detection (BFD) at the WD 22.

A method at a network node 16 may include configuring the WD 22 with one or more parameters for the WD 22 to perform one or more time domain prediction(s) of measurements on one or more beams, for deriving one or more indications and report in response to a Beam Failure Detection (BFD) at the WD 22. In one example, the one or more parameters assist the WD 22 to perform the one or more time-domain predictions.

A method at the network node 16 may include performing one or more actions in response to the reception of the one or more indications from a WD 22 based on one or time domain prediction(s) of measurements on one or more beams in response to a Beam Failure Detection (BFD) at the WD 22: reconfigure RLM-RSs; reconfigure BFD RSs; reconfigure one or more antenna parameters related to the RLM/BFD RSs, for selecting antenna parameters that forms a more wider/narrow beam; activate/ deactivate TCI state(s); re-configure TCI states; re-configure LI resources to be measured/ reports; and/or modify at least one of the BFD-RS(s) to be monitored.

FIGS. 15 and 16 are examples of how the WD 22 and network methods may be combined for BFR based on CBRA (FIG. 15) and CFRA (FIG. 16). Referring to FIG. 15, at step SI 50, the WD 22 declares a BFD and/or triggers a BFR. At step SI 52, the WD 22 selects a candidate beam at a time to, from a set of candidate beams indicated by the network node 16. At step 154, the network node 16 determines a beam to transmit a random access response when it receives a CBRA preamble from the WD 22. In step 156, the network node 16 identifies the WD and engages in BFR, which includes transmitting to the WD 22 a MAC CE for an updated TCI state based on time domain prediction(s) of measurements on one or more beams. At step S158, the WD 22 monitors BFD. At step S160, the WD 22 does not declare a BFD within a period of time after receiving BFD reference signals.

Referring to FIG. 16, at step SI 62, the WD 22 declares a BFD. At step SI 64, the WD 22 selects a candidate beam from a plurality of candidate beams indicated by the network node 16. At step SI 66, the WD 22 sets a random access preamble index to an index associated with the selected beam candidate. At step SI 68, the network node determines a beam to transmit a random access response when it receives a CFRA preamble from the WD 22. At step 170, the WD 22 monitors for BFD. At step S172, the WD 22 monitors BFD. At step S160, the WD 22 does not declare a BFD within a period of time after receiving BFD reference signals.

The terms “ML-model”, “Al-model”, “Model Inference”, “Model Inference function” are used interchangeably, herein. An AI/ML model may be defined as a functionality or be part of a functionality that is deployed or implemented in a first node (e.g., a WD 22). An AI/ML model may be defined as a feature or part of a feature that is implemented and supported in a first node, e.g., a WD 22. An ML- model (or Model Inference function) may correspond to a function which receives one or more inputs (e.g., measurements) and provide as outcome one or more prediction(s) or estimates and decisions of a certain type. An ML model or Model Inference may include a function that provides AI/ML model inference output (e.g., predictions or decisions). The Model inference function may also be responsible for data preparation (e.g., data pre-processing and cleaning, formatting, and transformation) based on Inference Data delivered by a Data Collection function, if required. The output may corresponds to the inference output of the AI/ML model produced by a Model Inference function. The predictions are time-domain predictions: thus, the input of the ML-model is one or more measurements at (or starting at) a time instance tO, and the output of the ML-model includes one or more predicted measurements at (or starting at) a future time instance, e.g., tO + T. Further terminology may refer to an “actor”, as a function that receives the output from the Model inference function and triggers or performs corresponding actions. The Actor may trigger actions directed to other entities or to itself. One actor may correspond to the BFD and/or BFR functionality at the WD 22, and/or the functionality at the WD 22 responsible for generating the data structure to transmit the one or more indications (e.g., a MAC CE) upon triggering BFR.

In one example, an ML-model may correspond to a function receiving as input one or more measurements of at least one reference signal (RS) at time instance tO (or a time interval starting or ending at tO), after a measurement period, (e.g., transmitted in beam-X, SSB-x, CSLRS resource index x) and provide as output the prediction of the RS measurement(s) in time instance tO+T (or a time interval starting or ending at tO+T). This future time instance tO+T, obtained at tO, may be in different time units such as in number of slots (frames, sub-frames, OFDM symbols, etc.) after the WD 22 has performed the last measurement or by targeting a specific slot in time in the future.

Some embodiments include a method at a WD 22 operating with at least one ML model (e.g., based on which the WD 22 performs one or more time-domain predictions) for transmitting predicted information during a Beam Failure Recovery (BFR) procedure. In some embodiments, the method includes transmitting one or more indications based on the one or time domain prediction(s) of measurements on one or more beams in response to a Beam Failure Detection (BFD).

Time domain predict! on(s) of measurements

Prior to transmitting the one or more indications, the WD 22 may perform one or more time domain prediction(s) of measurements on one or more beams, such as time-domain predictions/ estimates of SS-RSRP, CSI-RSRP, SS-RSRQ, CSI-RSRQ, SS-SINR, CSI-SINR, as defined in 3GPP TS 38.215. Then, the WD 22 generates the one or more indications based on one or time domain prediction(s) of measurements on one or more beams, to be transmitted to the network in response to the BFD. The one or more time-domain predictions/estimates on one or more beams may be the output of an ML-model (or Al-model) the WD 22 is deployed with.

The one or more beams referred to above may correspond to: one or more beams configured for BFD monitoring:

In one example, these are the beams (indicated by one or more RS index(es)) the WD 22 monitors, e.g., as indicated by the parameter failureDetectionResourcesToAddModList

In one example, these are indicated to the WD 22 by a set of periodic CSI- RS resource configuration indexes and/or a set of periodic CSI-RS resource configuration indexes and/or SS/PBCH block indexes;

In one example, at least one of these beams is configured as a RS for Radio Link Monitoring (RLM-RSs), which needs to be monitored for RLM;

In one example, at least one of these beams is configured as part of the RLM-RSs configuration(s);

In one example, these are indicated per Bandwidth Part (BWP) and/or per serving cell (e.g., PCell, PScell, SCell);

In one example, these are the beams associated to the RSs of one or more active beams in which the WD 22 is monitoring PDCCH (or any other control channel in which the WD 22 may receive scheduling information);

In one example, these are the beams associated to the RSs of one or more active/ activated Transmission Configuration Indication (TCI) states, e.g., wherein the WD 22 is monitoring PDCCH associated to the activated TCI states;

In one example, these are the beams associated to the RSs configured as Quasi-Co-Location source of one or more active/ activated Transmission Configuration Indication (TCI) states; In one example, the WD 22 determines the set to include periodic CSI-RS resource configuration indexes with same values as the RS indexes in the RS sets indicated by TCI-State for respective CORESETs that the WD 22 uses for monitoring PDCCH and, if there are two RS indexes in a TCI state, the set includes RS indexes with QCL-TypeD configuration for the corresponding TCI states. The WD 22 expects the set to include up to two RS indexes: one or more candidate beams (candidates to be selected during BFR);

In one example, the one or more candidate beams to be selected during BFR are indicated by the parameter candidateBeamRSList and/or for each beam the IE PRACH-ResourceDedicatedBFR, at least for CFRA for BFR;

In one example, for CBRA for BFR. any SSB which is transmitted and/or to be measured may be considered a candidate beam;

In one example, any SSB of a serving cell may correspond to a candidate beam: one or more selected beams (selected during BFR);

In one example, a beam is selected by the WD 22 out of the candidate beams, during RA (more specifically during RA resource selection, e.g., as defined in 3GPP TS 38.321, § 5.2.1. The WD 22 selects a beam whose RSRP is above a configurable threshold;

In one example, the selected beam corresponds to the SSB which is the WD 22 selects with SS-RSRP above rsrp-ThresholdSSB amongst the SSBs in candidateBeamRSList or a CSI-RS with CSLRSRP above rsrp- ThresholdCSI-RS amongst the CSLRSs in candidateBeamRSList;

In one example, the select beam corresponds to an SSB with SS-RSRP above rsrp-ThresholdSSB which is available: one or more beams configured for other procedures, e.g., not for BFD monitoring; one or more beams configured for CSI report; and/or

In one example, the one or more beams configured for CSI report include at least one beam whose RS is configured as part of the CSI resource configuration (e.g., within the information element (IE), CSLMeasConfig. Each RS may be configured by an RS index or identifier, or identity, or a representation of the identity/ index or identifier, e.g., SSB-Index in case of SSB, or CSI-RS resource index for the case of CSI-RS. One option is to configure at least one resource set (or a plurality of sets), wherein each set includes multiple SSBs and/or multiple CSI-RS or any other RSs.

Each beam may be indicated by an RS ID (e.g., an SSB-Index, a CSI resource identifier, a non-zero power (NZP)-CSI-RS-Resourceld). The RS (e.g., an SSB with SSB-index X) may be transmitted in a spatial direction (also called a beam) by the network node 16 (and received by the WD 22).

In some embodiments, measurements on one or more beams correspond to measurements of one or more measurement quantities, e.g., RSRP and/or RSRQ, and/or received signal strength indicator (RSSI), and/or SINR, measured on one or more RS(s), e.g., SSB, CSI-RS, Cell-specific Reference Signal (CRS), Discovery Reference Signal (DRS), Demodulation Reference Signal (DMRS), wherein the one or more measured RS(s) may be transmitted in different spatial direction(s), which may be referred to as different beams. For example, a measurement on a beam may correspond to a SS-RSRP (Synchronization Signal Reference Signal Received Power) on an SSB index X of a cell Y, wherein the SSB of SSB index X is transmitted in a beam in a spatial direction. More examples of measurements that may be made given in 3GPP TS 38.215, which may include SS-RSRQ, SS-SINR, CSI-RSRP, CSI-RSRQ, CSI-SINR. Measurements on one or more beams may be obtained during a measurement period, as defined in 3 GPP TS 38.133. Thus, reference to a measurement at time tO, may imply reference to a measurement period which has ended at time tO, e.g., the end of a time window, moving average of measurement samples, etc.

In some embodiments, at tO, a time domain prediction (or estimate) of a measurement may correspond to at least a value (e.g., generated as the output of an ML-model) which represents an estimate of the measurement for a future point in time, tO + T. At tO, there may be multiple predictions or estimates of the measurement for tO + 1 *T, tO + 2*T, tO + 3 *T, ... , tO + K*T, wherein T may be called the prediction/ estimation periodicity, and K the number of predictions. The value K*T may represent the total prediction interval, in time units, or prediction window. These parameters i) may be received by the WD 22, in a message from the network, as a configuration for the WD 22 to perform the predictions, and/or ii) they may be obtained in the WD’s memory if hard-coded (e.g., if they are specified), and/or iii) they may be obtained based on one or more rules depending on radio related parameters such as the WD’s currently used subcarrier spacing, carrier frequency, frequency range, usage of discontinuous reception (DRX) or not, etc.

In some embodiments, a prediction or estimate of the measurement is performed at tO + 1*T, tO + 2*T, tO + 3*T, . . ., tO + K*T, wherein T is one or more of: i) a measurement period (e.g., as defined in 3GPP TS 38.133; ii) a value derived from a measurement period (e.g., a multiple, or a fraction of it). That value may vary according to one or more properties of the RS for which the prediction needs to be derived, e.g., S SB -Measurement Timing Configuration (SMTC) periodicity, subcarrier spacing, etc. That value may vary according to other properties such as if the WD 22 is in DRX or not, if the WD 22 is configured to perform other predictions and/or measurements, etc.

In some embodiments, the WD 22 is configured by the network (e.g., network node 16) with one or more parameters indicating how in the time-domain the predictions are to be performed, such as the prediction/ estimation periodicity (T), and the number of predictions (K), the prediction window, or any of the other parameters described herein. In one example, the WD 22 is configured with the value K*T representing the total prediction interval, in time units. In one option, one or more parameters are obtained by the WD 22 in its memory (e.g., in case this has been standardized and hard coded at the WD 22).

In some embodiments, the future time instance tO+T, obtained at tO, may be in different time units. In one embodiment, the time units may be in number of measurement periods, slots (or frames, sub-frames, OFDM symbols, etc.) after the WD 22 has performed the last measurement or targeting a specific slot in time in the future. For example, at time tO, the WD 22 generates at least one prediction for time instance tO+T, which may be the estimate for the next measurement period.

In one embodiment, the time unit for the one or more predictions is defined in terms of CSI reporting periodicity, in case of periodic CSI reporting. For example, if the WD 22 is configured with periodic CSI reporting whose periodicity is set to Tcsi, (e.g., in number time slots), the WD 22 considers the prediction periodicity (T) to also be Tcsi. For example, the same value configured by the parameter reportSlotConfig and/or the IE CSI-ReportPeriodicityAndOffset for CSI reporting, may also be considered for the prediction periodicity. One advantage is that these would be the CSI reports the network would have received after BFD, with that periodicity, but only after some time. Because of the predictions, the CSI reports are made available to the network node 16 earlier. In another example, the prediction periodicity is defined as a multiple of the CSI reporting periodicity. In another example, the CSI reporting periodicity is defined as a multiple of the prediction periodicity.

For RSRP of an SSB, for example, the one or more predictions may correspond to a time series of predictions at time tO, leading to [RSRP(tO+T), RSRP(tO+2*T), RSRP(t0+3*T), ..., RSRP(tO+K*T)] as an outcome.

For example, the SS-RSRP prediction/ estimate at tO, for a time future at time tO+T, may correspond to the estimate in tO+T of the linear average over the power contributions (in Watts) of the resource elements that carry secondary synchronization signals (SSSs) which the SSB would have at time tO+T. For predicting SS-RSRP, demodulation reference signals for physical broadcast channel (PBCH) at time tO or estimates for tO+T may be used. In another example, the prediction/ estimate at tO may be performed for SS-RSRQ, SS-SINR, CSI-RSRP, CSI-RSRQ, CSLSINR.

In another example, the one or more predictions may correspond to a time series of predictions at time tO, defined by an autoregressive (AR) model. An autoregressive model is when a time-series value is regressed (predicted/ estimated/ inferred) on previous values from that same time series. For example, an AR-model with two components is illustrated below.

In some embodiments, the estimate of the SS-RSRP (or prediction for tO+T) is estimated/ predicted among the reference signals corresponding to SS/PBCH blocks (SSB) with the same SS/PBCH block index and the same physical-layer cell identity.

An SSB is an acronym for SS/PBCH block or Synchronization Sequence Block (SSB).

An example is shown below. At tO the WD 22 has obtained the SS-RSRP of SSB-x and SSB-y, quite close and similar in terms of dBm. Then, it shows the predictions at tO+T, tO+2*T, . . . , tO+K*T.

FIG. 17 is an example of SS-RSRP predictions for different beams (SSB-x and SSB-y) at tO, for future time instances tO+T, tO+2*T, . . . , tO+K*T. As it may be observed, predictions show that the SS-RSRP of SSB-x and SSB-y differ after tO, though at tO they have somewhat similar values. The benefit of knowing these predictions for tO+k*T (k=l, . . . ,K) at tO is that network may assume what happens next.

In some embodiments, the WD 22 starts performing one or more time domain predictions (or estimates) of a measurement at tO, wherein tO is before BFD occurs or BFR is triggered (i.e., before BFI COUNTER >= the max value configured by the network node 16, or when a number of BFIs are received at the MAC entity of the WD 22). Thus, the WD 22 may start to perform the time-domain predictions when it is configured, e.g., for performing BFD. One advantage is that the WD 22 has the time-domain predictions readily available to be included in the message to be transmitted (e.g., the first MAC CE) when BFD is declared, i.e., there is no need to wait extra time for performing the predictions before indicating them to the network node 16. In one example, the WD 22 performs the one or more time-domain predictions (or estimates) of a measurement before BFD occurs for the beams the WD 22 is monitoring for BFD. This may be the case if the input measurements to the ML- model that generates the predictions are being generated for BFD. In this case, there may be no need for extra measurement related efforts to generate the outputs of the ML-model.

In some embodiments, the WD 22 starts performing one or more time domain predictions (or estimates) of a measurement at tO, where tO occurs after the WD 22 declares BFD. One advantage is that there may be no need for WD 22 beam failure detection activity before BFD is declared. This is beneficial as BFD should be a rare event. In one example, the WD 22 performs the one or more time-domain predictions (or estimates) of a measurement after BFD is declared for the candidate beams or selected beams. This may be the case if the input measurements to the ML-model that generates the predictions are being generated after BFD is declared. In this case, there would be no need for extra measurement related efforts to generate the outputs of the ML-model.

In some embodiments, the WD 22 starts performing one or more time domain predictions (or estimate) of a measurement at tO, wherein tO is upon the detection of a first beam failure instance (BFI) indication. One advantage is that the WD 22 has the time-domain predictions ready to be included in the first MAC CE when BFD is declared, but at the same time, only begins to perform the predictions when there is some evidence that BFD may be declared. This may be seen as a case where the WD 22 the starts performing the one or more time domain predictions (or estimates) before BFR is triggered (or BFD is declared), except when the max number of beam failure instances (e.g., beamFailurelnstanceMaxCount) is set to 1.

One or more indications based on time domain predict! on(s) of measurements Note that the RSRP (e.g., SS-RSRP, CSI-RSRP) is usually used as an example of measurement quantity, but other measurement quantities may also be equally considered such as RSRQ, SINR, RSSI. Similarly, SSB is usually use as an example of RS which is beamformed, but other RSs may also be equally considered such as CSI-RS, DRMS, CRS, DRS, etc.

In some embodiments, the one or more indications includes at least one of the time domain prediction(s) of measurements, as explained above. For example, for a given beam (SSB-X, whose SSB index = X) the WD 22 transmits the predicted RSRP for SSB-X, e.g., predicted SS-RSRP’(tO+T), SS-RSRP’(tO+2*T), ... , SS- RSRP’(tO+K*T).

In some embodiments, the one or more indications are for beams (RSs) associated to one or more of:

A first cell group, with an SpCell (Special Cell, as defined in 3GPP TS 38.331, or any other cell with equivalent properties) and one or more Secondary Cells (SCells, as defined in 3GPP TS 38.331, or any other cell with equivalent properties). In one option, the first cell group is a Master Cell Group (MCG), and the SpCell is a Primary Cell (PCell). In one option, the first cell group is a Secondary Cell Group (SCG), and the SpCell is a SpCell of the SCG (PSCell); and/or

A serving cell e.g. SpCell of MCG, SpCel of the SCG, SCell of the MCG; SCell of the SCG.

In some embodiments, the one or more indications include an average (e.g., moving average, filtered averaged, weighted average) based on at least one time domain predict! on(s) of measurements, as explained above. For example, for a given beam (SSB-X, whose SSB index = X), the WD 22 may transmit an average of the predicted RSRP for SSB-X, e.g., for predicted SS-RSRP’(tO+T), SS-

RSRP ’(tO+2*T), ... , SS-RSRP’(tO+K*T), the WD 22 may indicate an average of these values. The WD 22 may also report an indication of the RS index/ identifier.

In some embodiments, the one or more indications includes a statistical metric derived based on the distribution of the multiple time domain prediction(s) of measurements. For example, for a given beam (SSB-X, whose SSB index = X), the WD 22 may transmit a statistical metric of the predicted RSRP(s) for SSB-X, e.g., predicted SS-RSRP’(tO+T), SS-RSRP’(tO+2*T), SS-RSRP’(tO+K*T). That may also include an indication of the RS index/ identifier. The statistics could be generated using ML-model/s/methods such as ensemble-based procedures, which includes a number of so-called weak learners, each providing a prediction of an SS- RSRP in a certain time-instance. The statistical metric could include, for each time instance, the average value and standard deviation of such value, or for example the confidence interval of the expected value, e.g., 90% probability that the value is within a certain range. In another related embodiment, the statistics of a predicted value may be reported as the below probability density function, using Gaussian mixtures for each of the tO+T, tO+2T,. . . . tO+KT, for example. See FIG. 16. The prediction may then be reported using the parameters describing the mixed gaussian components, for example the mean, variation and component weight for each of the components.

FIG. 18 is a probability density function of RSRP, for a mixed gaussian with two components: a) component 1 : mean =-100, sigma = 1, component weight = 1/3; B) component 2: mean =-90, sigma = 1, component weight = 2/3. In one set of embodiments, the one or more indications include at least one time instance (or indications of a time instance) wherein the WD 22 has performed time domain prediction(s) of measurements.

In some embodiments, the one or more indications include at least one metric (value, parameter, indication) which is derived (generated) by the WD 22 based on one or more time domain prediction(s) of measurements.

In some embodiments, the one or more indications include a beam identifier, derived (generated) by the WD 22 based on one or more time domain predict! on(s) of measurements. A beam identifier may correspond to a RS ID, such as an SSB index, CSI-RS resource identifier.

In some embodiments, the one or more indications based on time domain prediction(s) of measurements include an indication of the RS index/ identifier (e.g. SSB identifier). In some embodiments, the indication of the RS index/ identifier corresponds to the actual the RS index/ identifier, for example, an SSB is indicated by its explicit SSB identifier (X, for SSB index=X). In some embodiments, the indication of the RS index/ identifier corresponds to a configuration identifier, based on a mapping provided in the RRC configuration: for example, the WD 22 is configured with a list of SSB indexes, e.g., LIST = [SSB index-5, SSB index-12, SSB index-60], so that what is reported is the positioning in the list. For example, when the WD 22 sends the prediction for SSB index-12 it indicates the prediction is for the SSB in position 1, when the WD 22 sends the prediction for SSB index-5 it indicates the prediction is for the SSB in position 0, and when the WD 22 sends the prediction for SSB index-60 it indicates the prediction is for the SSB in position 2. This allows fewer bits to be included in the first MAC CE.

In some embodiments, the WD 22 derives the one or more indication(s) based on at least a threshold associated to a measurement quantity (e.g., RSRP, RSRQ, SINR, RSSI) which is to be predicted or estimated. For example, if RSRP is the measurement quantity, the WD 22 predicts the RSRP of at least one SSB in the time-domain (SS-RSRP), in time instances tO+T, . . . , tO+T*K, then the WD 22 derives the one or more indication(s) by comparing the predictions/ estimates with an RSRP threshold.

In one embodiment, the one or more indications indicate(s) the one or more RSRP predictions/ estimations above the threshold (e.g., good predictions). If the WD 22 generates [SS-RSRP(tO+T), RSRP(tO+T*2), ..., RSRP(tO+T*K)] and only a subset is above the threshold, the WD 22 transmits only the subset (or the subset is a candidate from which the WD 22 further selects the predictions to be reported, based on one or more additional rules): o The threshold may also have an associated uncertainty in the prediction. For example, the probability that a prediction is above a threshold with a certain probability. The RSRP prediction could be highly uncertain and potentially below the indicated threshold, with a certain probability;

In one embodiment, the one or more indications indicates the time instances for which the predictions are above the threshold. For example, If the WD 22 generates [SS-RSRP(tO+T), RSRP(tO+T*2), ... , RSRP(tO+T*K)] and only a subset is above the threshold, the WD 22 transmits indication of the time instances for that subset: o In one embodiment, the one or more indications indicates the time instances for which the predictions are above the threshold. For example, If the WD 22 generates [SS-RSRP(tO+T), RSRP(tO+T*2), ..., RSRP(tO+T*K)] and only a subset is below the threshold, the WD 22 transmits indication of the time instances for that subset. In one example, the indication of the time instances corresponds to the index associated to the prediction periodicity, e.g., if SS-RSRP(tO+k*T) is above the threshold, the WD 22 reports k;

By knowing one or the other, when one or both are reported by the WD 22, the network knows when to expect values above and/or below the threshold and prepare for counter-actions such as beam switching and/or TCI state activation / deactivation;

In one embodiment, the one or more indications indicates of the number of instances in which the predictions are above the threshold. For example, if the WD 22 generates [SS-RSRP(tO+T), RSRP(tO+T*2), ... , RSRP(tO+T*K)] and only a subset is above (or below) the threshold, the WD 22 transmits indication of the number of instances for that subset. In case the comparison is for above the threshold, a high number would indicate to the network that for most of the prediction period (K*T), the SSB whose RSRP is being predicted is good, as most predictions are above the threshold; and/or

In one embodiment, there may be different threshold for different predictions quantities, such as RSRP, RSRQ, SINR, RSSI, etc.

In some embodiments, the one or more indications includes an indication of ratio of predictions above the threshold divided by the total number of predictions (K) in a given prediction interval (K*T):

In one embodiment, the indication of a ratio is the actual ratio. One advantage, compared to some of the previous embodiments, is that fewer bits could be used to encode the indication when this is transmitted by the WD 22 to the network. For example: 3 bits are needed if K=8 [1001 1101], the index of time instances [1, 5, 6] with “0” represent that the predicted RSRP are lower than the threshold at tO+2*T, tO+6*T, and tO+7*T, respectively. Given the indication, the network node 16 may exactly know the index of time instances that is larger or lower than the threshold;

In one embodiment, the indication of the ratio is derived from the actual ratio compared to a ratio threshold. For example, the indication of the ratio is set to 1 if the ratio is higher than the threshold, or 0 otherwise. By receiving that the network knows whether most predictions are good or not. The ratio threshold may be configurable which depends on the required level of stability. If the level of stability is high, e.g., it requires 7 out of 8 predictions to be higher than threshold, then the network knows the prediction is very good if the indication bit reported by the WD 22 is set to 1.

In one set of embodiments, the WD 22 derives the one or more indication(s) based on at least a counter value associated to a measurement quantity which is to be predicted or estimated. For example, if the WD 22 predicts the RSRP of at least one SSB in the time-domain, in time instances tO+T, ..., tO+T*K, the WD 22 derives the one or more indication(s) by comparing the number of predictions/ estimates above an RSRP threshold, with the counter value:

In one embodiment, the indication is a stability flag, which indicates that a measurement or beam/ RS is stable if the number of predictions/ estimates above the threshold within the prediction/ estimation interval (K*T) are above the counter value:

In one embodiment, the stability indication is a bit set to 1 if the beam/ RS is considered stable, or 0 if is considered as not stable. The value 1 or 0 is what is transmitted to the network;

In one embodiment, the stability indication is a flag set to ‘TRUE’ if the beam/ RS is considered stable, or ‘FALSE’ if is considered as not stable. The value ‘TRUE’ or ‘FALSE’ is what is transmitted to the network;

Another way to define the stability flag is that it indicates that a measurement or beam/ RS is stable if the number of predictions/ estimates below the threshold within the prediction/ estimation interval (K*T) is below the counter value;

In one embodiment, the indication is a stability indicator, which indicates that the prediction is stable with different levels of stability if the ratio of the number of predictions above the threshold divided by the total number of predictions (K) in a given prediction interval (K*T) belongs to different ranges. The ratio ranges representing different level of stability may be configurable depending on the required graduality. The smaller granularity requires more bits for the stability indicator. For example, if the granularity is set to 0.1 and the lower bound of ratio is set to 0.6, the stability indicator is presented by only 2 bits with four different combinations, i.e., 00, 01, 10, and 11. Then, the following example mapping may be used: o 00 -> 0.6 < ratio < 0.7, o 01 -> 0.7 < ratio < 0.8, o 10 -> 0.8 < ratio < 0.9, o 11 -> 0.9 < ratio < 1.0.

The network node 16 may know the prediction is good and very stable as well. Note that in this example, a ratio lower than 0.6 is not considered because the prediction may not be sufficiently stable. However, the value of the lower bound of ratio (0.6) may be configurable, and the number of bits may change correspondingly with different granularities;

In one embodiment, the indication is an instability flag, which indicates that a measurement or beam/ RS is not stable if the number of predictions/ estimates above the threshold within the prediction/ estimation interval (K*T) is below the counter value: o In one embodiment, the instability indication is a bit set to 1 if the beam/ RS is considered instable, or 0 if is considered as stable. The value 1 or 0 is what is transmitted to the network; o In one embodiment, the instability indication is a flag set to ‘TRUE’ if the beam/ RS is considered instable, or ‘FALSE’ if is considered as stable. The value ‘TRUE’ or ‘FALSE’ is what is transmitted to the network; o Another way to define the instability flag is that it indicates that a measurement or beam/ RS is NOT stable if the number of predictions/ estimates below the threshold within the prediction/ estimation interval (K*T) is above the counter value;

In one embodiment, the indication is an instability indicator, which indicates that the prediction is instable with different levels of instability if the ratio of the number of predictions above the threshold divided by the total number of predictions (K) in a given prediction interval (K*T) belongs to different ranges. The ratio ranges representing different level of stability may be configurable depending on the required granularity. The smaller granularity requires more bits for the stability indicator. For example, if the granularity is set to 0.1 and the upper bound of ratio is set to 0.4, the stability indicator is presented by only 2 bits with four different combinations, i.e., 00, 01, 10, and I I. Then, an example mapping is: o 00 -> 0 < ratio < 0.1, o 01 -> 0.1 < ratio < 0.2, o 10 -> 0.2 < ratio < 0.3, o 11 -> 0.3 < ratio < 0.4.

The network may not only know the prediction is good (for current measurement) but instable in the near future. Note that a ratio higher than 0.4 is not considered in the example because the prediction might become stable. However, the value of the upper bound of ratio (0.4) may be configurable, and the number of bits will change correspondingly with different granularities;

One advantage of reporting the stability or instability flag (single bit) / indicator (multiple bits) is to reduce overhead over the air interface. It may also simplify the generation of the message in which the indication is transmitted.

Stability of selected beam in RA

In some embodiments, the one or more indication(s) the WD 22 transmits are based on whether at least one selected beam during BFR, i.e., during the RA procedure, which was triggered, is stable (or not, or instable) based on the one or more predictions in the time-domain of the measurements (e.g., based on WD’s AI/ML BM model).

- Note: a selected beam in this context may correspond to a selected RS associated to an RS index, where the RS is transmitted in a spatial direction. For example, the WD 22 may select a beam for RA when it selects an SSB whose RSRP is above a threshold. This corresponds to a RA resource selection as the beam selection/ SSB selection leads the WD 22 to select a specific RA configuration (preamble and/or time-frequency PRACH resources) mapped to the selected SSB;

In one embodiment, the selected beam is stable if at least one prediction of the RSRP (e.g. SS-RSRP in case the RS is an SSB) is above the RSRP threshold configured for beam selection (RA resource selection), e.g., rsrp- ThresholdSSB,'

In one embodiment, the selected beam is stable if a number of predictions of the RSRP is above the RSRP threshold configured for beam selection (RA resource selection), e.g., rsrp-ThresholdSSB,'

In one embodiment, the selected beam is stable if a number of predictions of the RSRP is above the RSRP threshold configured for beam selection (RA resource selection), e.g., rsrp-ThresholdSSB remains above the threshold for K*T time units (or at least most of the time, excluding quick falls);

The time unit T is possibly configurable, or T is also reported. This may help reducing subsequent BFDs or too many measurement re-configurations/ activations/ deactivations after the BFD, unstable situations, too many reconfigurations;

In one embodiment, one selected beam is the latest selected for which the WD 22 has received a RAR during BFR. This would be considered as successful RA procedure, but it would not preclude that in the same RA procedure triggered by BFR, the WD 22 has selected at least one different beam for which it has selected a RA resource, transmitted a preamble, but has not received a RAR (so that beam re-selection and/or power ramping would occur);

In one embodiment, one selected beam is any selected beam for which the WD 22 has received expected to receive a RAR during BFR. This would not preclude a beam which the WD 22 has selected and transmitted a preamble, but has not received a RAR (so that beam re-selection and/or power ramping would occur);

In one embodiment, the one or more indication(s) the WD 22 transmits are based on multiple beams the WD 22 has selected during the RA triggered by BFR. For example, in case the WD 22 has selected one or more beams for which it has not received a RAR, which triggered WD 22 to perform beam reselection or power ramping. Thus, one method includes the WD 22 transmitting multiple indications, per selected beam; and/or

In one embodiment, this process is performed if BFR is triggered for an SpCell, e.g., PCell or PSCell.

The example of FIG. 19 shows one advantage of the WD 22 transmitting an indication of the selected beam SSB-y being stable. The WD 22 predicts at tO, which is when the WD 22 triggers BFR and/or selects the SSB for RA resource selection, that at tO+Tl (T could be equal to tO+T) the SS-RSRP will be above the threshold. By reporting that to the network node 16, the network node 16 becomes aware that according to the prediction, it may re-configure/ update beam related parameters based on that SSB-y is stable (at least until or at tO+Tl), as shown in FIG. 17

FIG. 20 illustrates an advantage of the WD 22 transmitting an indication of the selected beam SSB-x being instable. The WD 22 predicts at tO, which is when the WD 22 triggers BFR and/or selects the SSB for RA resource selection, that at tO+Tl (T could be equal to tO+T) the SS-RSRP will be below the threshold. By reporting that to the network node 16, the network node 16 becomes aware that according to the prediction, it may not re-configure/ update beam related parameters based on that SSB-x, which is not stable (at least until or at tO+Tl). Then the network node 16 may instead request further measurements before updating the WD 22.

Stability of candidate beam(s) in RA

In some embodiments, the one or more indication(s) the WD 22 transmits are based on whether at least one candidate beam during BFR is stable (or not, or instable) based on the one or more predictions in the time-domain of the measurements (e.g., based on WD’s AI/ML BM model).

Note: a candidate beam in this context may correspond to a candidate RS (or beam) configured as part of BFR configuration and associated to an RS index, wherein the RS is transmitted in a spatial direction: o In the case of Contention-Free Random Access (CFRA) triggered by BFR, the candidate beams are the beams (RS indexes) configured in the candidate beam list (which indicates the beams the WD 22 may perform CFRA triggered by BFR), e.g., indicated in the parameter candidateBeamRSListas defined in 3GPP TS 38.331, and 3GPP TS 38.321; o In the case of Contention-Based Random Access (CBRA) triggered by BFR, the candidate beams are any of the beams (RS indexes) the WD 22 may select for BFR; o The previous embodiments concerning predictions on selected beams are applicable to a candidate beam, as the selected beam is selected among the candidate beams. The difference here is that there may be multiple candidate beams, while there may be one selected beam;

In one embodiment, a candidate beam is stable if at least one prediction of the RSRP (e.g. SS-RSRP in case the RS is an SSB) is above the RSRP threshold configured for beam selection (RA resource selection), e.g., rsrp- ThresholdSSB,'

In one embodiment, a candidate beam is stable if a number of predictions of the RSRP is above the RSRP threshold configured for beam selection (RA resource selection), e.g., rsrp-ThresholdSSB:

In one embodiment, a candidate beam is stable if a number of predictions of the RSRP is above the RSRP threshold configured for beam selection (RA resource selection), e.g., rsrp-ThresholdSSB remains above the threshold for K*T time units (or at least most of the time, excluding quick falls);

The time unit T may be configurable, or T may also be reported. This may help reducing subsequent BFDs or too many measurement re-configurations, activations and/or deactivations after the BFD, and may further reduce unstable situations, too many re-configurations, etc.;

In one embodiment, the one or more indication(s) the WD 22 transmits are based on multiple candidates beams for the RA triggered by BFR. Thus, in some embodiments, the WD 22 transmits multiple indications, per candidate beam; and/or

FIG. 21 shows an advantage of the WD 22 transmitting an indication of the candidate beams SSB-y and SSB-x being stable or unstable. The WD 22 predicts at tO, which is when the WD 22 triggers BFR and/or selects the SSB for RA resource selection, that at tO+Tl (T could be equal to tO+T) the SS-RSRP will be below the threshold for the selected beam (SSB-x). At the same time, the WD 22 transmits an indication of the other candidate beam, which is not the selected beam, SSB-y, which is above the threshold at tO+Tl. By reporting the indications for both to the network node 16, the network node 16 becomes aware that according to the prediction, it may re-configure/ update beam related parameters based on that SSB-y is stable (at least until or at tO+Tl), even though the WD 22 has selected SSB-x.

Good beam indication

In some embodiments, the one or more indication(s) the WD 22 transmits includes an indication for one or more candidate beams (e.g., of the SpCell), where the indication of a beam-X is set to 1 if candidate beam has LI -RSRP above the threshold upon RA, otherwise set to 0. Therefore, the network node 16 may ascertain which candidate beams were good or not, in addition to the selected beam. That is, in one or more embodiments, a “good beam” is a beam associated with an LI -RSRP above a threshold.

In some embodiments, the WD 22 includes for each candidate beam (e.g., SSB-X), of a given serving cell (e.g., SpCell), two indications: i) whether the beam is good or not (as above, i.e., if the beam measurement is above the RA threshold); and ii) whether the predictions indication they are stable with different level of stabilities:

In one embodiment, the indication is a stability indicator, which indicates that the prediction is stable with different levels of stabilities if the ratio of the number of predictions above the threshold divided by the total number of predictions (K) in a given prediction interval (K*T) belongs to different ranges. The ratio ranges representing different level of stability may be configurable depending on the required graduality. The smaller granularity requires more bits for the stability indicator. For example, if the granularity is set to 0.1 and the lower bound of ratio is set to 0.6, the stability indicator is presented by only 2 bits with four different combinations, i.e., 00, 01, 10, and 11. Then, the following example mapping may be employed: o 00 -> 0.6 < ratio < 0. 7, o 01 -> 0.7 < ratio < 0.8, o 10 -> 0.8 < ratio < 0.9, o 11 -> 0.9 < ratio < 1.0.

The network node 16 may know the prediction is good and very stable as well.

Note that a Ratio lower than 0.6 is not considered in the example because the prediction is not of sufficient stability. However, the value of the lower bound of ratio (0.6) may be configurable, and the number of bits will change correspondingly with different granularities.

In some embodiments, the one or more indication(s) the WD 22 transmits include an indication of at least one candidate beam (e.g., SSB-X), i.e., the RS ID(s) or an associated identifier known by the WD 22 to be associated to the RS ID(s), where the WD 22 includes the RS ID based on time-domain RSRP predictions/estimates. For example, if the SSB index is configured in a list, the WD 22 may indicate a position in that list, so the network knows that the report is associated to that SSB index.

In some embodiments, the one or more indications include an indication of the time instance until which at least one measurement is considered to be stable (according to one or more definitions of stability disclosed herein), or valid. For example, at tO, if the WD 22 selects beam X for BFR (e.g., associated to SSB-index X), it predicts in the time domain the RSRP of beam X (at tO+T, tO+2*T, . . . , tO+k*T, . . . , t0+K*T, wherein k=l, . . . ,K) and, compare the predictions to an RSRP value (e.g., threshold) and if, according to the predictions, the RSRP of beam X is above the threshold until tO+T*k, one indication may correspond to the value of k.

In some embodiments, the one or more indications include an indication of the time instance wherein the at least one measurement stops being stable (according to one or more definitions of stability disclosed herein), or valid. For example, at tO, if the WD 22 selects beam X for BFR (e.g., associated to SSB-index X), it predicts in the time domain the RSRP of beam X (at tO+T, tO+2*T, . . . , tO+k*T, . . . , tO+K*T, where k=l,. . ,,K) and, compare the predictions to an RSRP threshold and if, according to the predictions, the RSRP of beam X is above the threshold until tO+T*k, one indication may correspond to the value of k+1.

In some embodiments, the WD 22 uses an auto-regressive (AR)-model for performing the one or more time-domain predictions of measurements of one or more beams. Also, one or more indications based on the predictions correspond to one or more AR-model coefficients, possibly transmitted together with the WD 22 signal quality measurements y_to, yt₀-i in a number of time instances depending on the model size (tO,tO-l , . . .),. This may enable the network node 16 to calculate the future signal quality predictions. The WD 22 may also indicate the time-sampling of the AR- model, for example, the number of millisecond seconds between each time instance values. Note that the noise e_to indicates the uncertainty of future predictions. BFD, BFR and reporting of one or more indications

In some embodiments, one or more indications are transmitted based on the one or more time domain prediction(s) of measurements on one or more beams in response to a BFD, where the beam failure is detected at least by: the WD 22 counting beam failure instance (BFI) indication(s), e.g., from the lower layers to the MAC entity.

For example, if a BFI indication is received (e.g., at the MAC entity of the WD 22) from lower layers (e.g., Layer 1) at the WD 22, the WD 22 i) may start or restart a beam failure timer (e.g., beam 'ailureDetectionTimer ii) may increment the counter for BFI by 1; and iii) if the counter for BFI is greater (or equal) than a configurable count value, the WD 22 may initiate beam failure recovery (BFR). There may be different set of actions from that point:

If BFR is for a primary cell (e.g., SpCell, PCell, PSCell): o The WD 22 initiates a random access procedure; and/or If BFR is for a secondary cell (e.g., SCell of MCG, SCell of SCG): o The WD 22 initiates BFR for SCell;

In some embodiments, a method includes transmitting the one or more indications based on the one or more time domain prediction(s) of measurements on one or more beams in response to a Beam Failure Detection (BFD), where in response the BFD the WD 22 transmits a BFR MAC CE, as defined in 3 GPP TS 38.321.

In some embodiments, a method includes transmitting the one or more indications based on the one or more time domain prediction(s) of measurements on one or more beams in response to a Beam Failure Detection (BFD). The method includes the WD 22 making the one or time domain predict! on(s) of measurements on the one or more beams in a first Medium Access Control (MAC) Control Element (MAC CE). A method may also include the WD 22 (e.g., the WD’s MAC entity) transmitting the first MAC CE to the network node 16. In one example, the first MAC CE is a BFR MAC CE, e.g., associated to a logical channel identify or identifier. This BFR MAC CE may include the one or more indications, and further info, e.g., the occurrence of BFR for at least one SCell, the occurrence of BFR for a special cell.

In some embodiments, the first MAC CE is multiplexed with a BFR MAC CE (as defined in 3GPP TS 38.321), e.g., in the same MAC packet data unit (PDU). The MAC PDU is transmitted when the WD 22 declares a BFD and triggers BFR. If BFR is for a primary cell (e.g., SpCell, PCell, PSCell) the WD 22 initiates a Random Access procedure and the MAC PDU is part of Msg3 (transmitted by the WD 22 in response to the reception of the RAR) for a CBRA triggered by BFR.

In some embodiments, the first MAC CE is transmitted when the WD 22 declares a BFD and/or triggers BFR based on CFRA. If BFR is for a primary cell (e.g., SpCell, PCell, PSCell), the WD 22 initiates a Random Access procedure and the first MAC CE is transmitted by the WD 22 in response to the reception of the PDCCH addressed to the C-radio network temporary identifier (RNTI) in the search space for beam failure recovery.

In some embodiments, the first MAC CE is multiplexed with a BFR MAC CE (as defined in 3GPP TS 38.321), e.g., in the same MAC PDU. The MAC PDU may be transmitted when the WD 22 declares a BFD and triggers BFR. If BFR is for a secondary cell (e.g., MCG SCell, SCG SCell) the WD 22 does not initiate a Random Access procedure and only transmits the MAC PDU.

In some embodiments, the MAC entity at the WD 22 which transmits the first MAC CE is associated to a first cell group, with an SpCell (Special Cell, as defined in 3GPP TS 38.331, or any other cell with equivalent properties) and one or more Secondary Cells (SCells, as defined in 3GPP TS 38.331, or any other cell with equivalent properties). In one option, the first cell group is a Master Cell Group (MCG), and the SpCell is a Primary Cell (PCell). In one option, the first cell group is a Secondary Cell Group (SCG), and the SpCell is a Primary Cell (PCell). In one option, the WD 22 is configured to report by both MAC entities when the WD 22 is configured with multi-radio Dual Connectivity (MR-DC), e.g., with an MCG and an SCG, which implies an MCG MAC entity, and an SCG MAC entity. This may be useful as the reliability of an SCG may be lower than the reliability of the MCG, e.g., if the SCG is deployed in frequency in Frequency Range 2 (FR2).

In some embodiments, a method includes transmitting the one or more indications based on one or more time domain predict! on(s) of measurements on one or more beams in response to a BFD. The method includes including the one or more indications of the one or more time domain prediction(s) of measurements on the one or more beams in an RRC message:

In one embodiment, the RRC message is an RRC SCG failure message which is transmitted by the WD 22 when the SCG fails, such as when a Radio Link Failure (RLF) is declared for the SCG, i.e., PSCell. The action may be performed when BFD is declared for an SCG that is deactivated (UE configured with MR-DC). In other words, if the WD 22 is configured with a deactivated SCG and monitors BFD for the SCG, and BFD is detected, the WD 22 transmits the RRC SCG Failure message to the network node 16 operating as the Master Node (MN) including the one or more indications. For the deactivated SCG, this may be important as the WD 22 is not reporting typical CSI measurements for the SCG (as that is deactivated).

Hence, the one or more indications may be relevant for the network (e.g., the network node 16 operating as the Secondary Node, SN) to re-configure and/or update the beam related parameters at the WD 22. This may have required the assistance of previously received CSI reports (not available within a reasonable time window because the WD 22 was in SCG deactivated state); In one embodiment, the RRC message is an RRC MCG failure message (e.g.) which is transmitted by the WD 22 when the MCG fails, such as when a Radio Link Failure (RLF) is declared for the MCG, i.e., PCell. The action may possibly be performed when BFD is declared for an MCG which is deactivated (UE configured with MR-DC). In other words, if the WD 22 is configured with a deactivated MCG and is performing the monitoring of BFD for the SCG, and BFD is detected, the WD 22 transmits the RRC MCG failure message to the network node 16 operating as the SN including the one or more indications. For the deactivated MCG, this may be important as the WD 22 is not reporting typical CSI measurements for the MCG (as that is deactivated). Hence, the one or more indications may be relevant for the network (e.g., the network node 16 operating as the MN) to re-configure and/or update the beam related parameters at the WD 22. This may have been done with the assistance of previously received CSI reports (not available within a reasonable time window because the WD 22 was in MCG deactivated state);

In one embodiment, the RRC message is a Measurement Report; and/or In one embodiment, the RRC message is a WD 22 Assistance Information. In some embodiments, a method includes transmitting the one or more indications based on one or more time domain predict! on(s) of measurements on one or more beams in response to a BFD. The method may include including the one or more indications of the one or more time domain prediction(s) of measurements on the one or more beams in a message to the transmitted Over the Top, to a server such as host computer 24, and may be transparent to the mobile network. Configuration(s) from the network (e.g., network node 16)

The network node 16 described herein may correspond to a gNodeB, an eNodeB, a Radio Access Node for 6G radio, a Radio Access Node connected to a 6G Core Network, a Distributed Unit (e.g., wherein a radio access node has a Central Unit associated and that Distributed Unit), a Baseband Unit, a Radio unit.

In some embodiments, the WD 22 is configured by a network node 16 with one or more parameters and/or configurations for the WD 22 to perform the one or time domain prediction(s) of measurements on one or more beams.

In some embodiments, performing one or more time domain prediction(s) of measurements on one or more beams is based on one or more configuration(s) received from a network node 16 the WD 22 is connected to:

In one set of embodiments, the configuration is received in an RRC message (e.g., RRC Reconfiguration, RRC Resume, RRC Setup). This may be received during a transition to RRC CONNECTED (from RRC IDLE or RRC INACTIVE), while the WD 22 is in RRC CONNECTED, or during a mobility procedure (e.g., reconfiguration with sync, PCell change, handover);

In some embodiments, the configuration is received as part of the BFR configuration;

In some embodiments, the configuration is received as part of the BFD configuration;

In some embodiments, the configuration is received as part of the Radio Link Monitoring (RLM) configuration; and/pr

In some embodiments, the configuration is received as part of a Prediction configuration.

In some embodiments, the WD 22 is configured by a network node 16 with one or more parameters and/or configurations via RRC, and at least one, of the one or more parameters and/or configurations may be activated by the reception of a MAC CE and/or a DCI, defined for that purpose.

Capability signaling

In some embodiments, the WD 22 reports at least one capability indication, indicating one or more of the following:

- the WD 22 is capable of performing one or more time-domain prediction(s) of measurements on one or more beams for BFD/ BFR;

- the WD 22 is capable of generating one or more indications based on one or more time-domain prediction(s) of measurements on one or more beams for BFD/ BFR; and/or

- the WD 22 is capable of reporting one or more indications based on one or more time-domain prediction(s) of measurements on one or more beams for BFD/ BFR. For each of the embodiments or set of embodiments, associated to the different manners to perform the time-domain predictions these may be different capabilities. Thus, a WD 22 may implement multiple methods and report multiple capabilities.

In some embodiments, the WD 22 reports at least one capability indication related to the prediction period extension the WD 22 is capable of performing, e.g., in number of measurement periods, time slots, etc. For example, if a WD1 is more capable than a WD2, WD1 performs predictions in longer time periods (e.g., at tO, perform predictions until K1*T time instances), and may predict further in the future. The WD 22 capability signaling may include the maximum time the WD 22 may predict.

In some embodiments, all WDs in the same serving cell may perform the same time prediction periods, the corresponding parameter could be commonly configured by the network node 16. It may be regarded as a basic capability if WD 22 has AI/ML capability. But WDs might have different capabilities. If WD1 is more powerful than WD2, WD2 might only report the prediction with the basic indication that the beam is good and stable. However, WD2 with better capabilities might report the prediction with the detailed indication that the beam is good, the level of stability, and the time instance that the prediction is above the threshold and other additional info. In some embodiments, the WD 22 reports at least one capability indication related to the prediction period granularity the WD 22 is capable of performing. More capable WDs would be able to predict in a higher granularity, e.g., each OFDM symbol vs each slot or frame.

Re-configuration(s) / updates in response to the one or more indications

In some embodiments, the WD 22 receives from the network node 16 (i.e., the network node 16 transmits to the WD 22) a reconfiguration (and/or an update command), in response to transmitting the one or more indications based on the one or time domain predict! on(s) of measurements (e.g., in the first MAC CE), where the response indicates one or more of: reconfigure RLM-RSs; reconfigure BFD RSs; reconfigure one or more antenna parameters related to the RLM/BFD RSs, for selecting antenna parameters that forms more wider/ narrow beam(s); activate/ deactivate TCI state(s); re-configure TCI states; re-configure LI resources to be measured/ reports; and/or modify at least one of the BFD-RS(s) to be monitored, e.g., via transmissions of a DCI or MAC CE.

Note: a reconfiguration may correspond to an RRC message (e.g., RRCReconfiguration, RRCConnectionReconfiguration). An update command may correspond to a MAC Control Element (MAC CE) indicating the activation and/or deactivation and/or switching of one or more configuration(s), such as a TCI state activation/ deactivation.

Note that the reception of the reconfiguration from the network is an optional step after the WD 22 transmits the first MAC CE, and depends on the network node 16, e.g., the network may decide whether to transmit the reconfiguration to the WD 22.

In some embodiments, the reconfiguration from the network is a second MAC CE or in a Downlink Control Information (DCI) the WD 22 receives, wherein the MAC CE or the DCI indicates: activate/ deactivate TCI state(s); o In one example, the second MAC CE corresponds to a TCI States Activation/Deactivation for WD-specific physical downlink shared channel (PDSCH) MAC CE; o In one example, the second MAC CE corresponds to a TCI State Indication for WD-specific PDCCH MAC CE; activate/ deactivate one or more resource configurations for CSI reporting; o In one example, the second MAC CE corresponds to a SP CSL RS/CSLIM Resource Set Activation/Deactivation MAC CE; o In one example, the second MAC CE corresponds to a SP ZP CSLRS Resource Set Activation/Deactivation MAC CE: activate/ deactivate one or more reporting configurations for CSI reporting; o In one example, the second MAC CE corresponds to a SP CSI reporting on PUCCH Activation/Deactivation MAC CE: modify at least one of the RLM-RS(s) to be monitored; o In one example, the second MAC CE corresponds to a TCI State Indication for WD-specific PDCCH MAC CE, wherein the WD 22 performs RLM based on one or more RSs configured in the quasi-co- located (QCL) configuration of the TCI state(s) being activated: modify at least one of the BFD-RS(s) to be monitored; and/or o In one example, the second MAC CE corresponds to a TCI State Indication for WD-specific PDCCH MAC CE, wherein the WD 22 performs BFD based on one or more RSs configured in the QCL configuration of the TCI state(s) being activated.

In some embodiments, the reconfiguration from the network is an RRC message (e.g. RRCReconfiguration) received by the WD 22, where the RRC message indicates: reconfigure RLM-RSs; o In one example, the WD 22 receives an RRC message including the IE RadioLinkMonitoringConfig (used to configure radio link monitoring for detection of beam- and/or cell radio link failure); reconfigure BFD RSs; o In one example, the WD 22 receives an RRC message including the IE RadioLinkMonitoringConfig (used to configure radio link monitoring for detection of beam- and/or cell radio link failure). In addition, that may include the indication of at least one RadioLinkMonitoringRS with purpose set to BeamFailure; re-configure TCI states; o In one example, the WD 22 receives an RRC message including at least one IE TCLState, wherein at least one parameter/ field/ configuration within is included (which indicates that it is being modified, added or removed); o In one example, the WD 22 receives an RRC message indicating that a previously configured TCI state is being modified; o In one example, the WD 22 receives an RRC message indicating that a new TCI state is being added and/or that previously configured TCI state is being associated to a Downlink control channel (PDCCH) or data channel (PDSCH); re-configure LI resources to be measured/ reports; o In one example, the WD 22 receives an RRC message including the IE CSLMeasConfig:

■ In one example, that includes configuration of resources to be measured, such as one or more SSBs and/or one or more CSI-RS resources, e.g., in the csi-ResourceConfigToAddModList, of IE SEQUENCE (SIZE (l..maxNrofCSI-ResourceConfigurations)) OF CSI-ResourceConfig;

■ In one example, that includes configuration of CSI reports, such as one or more periodic, aperiodic and/or semi -persistent, event- triggered reporting over PUCCH and/or PUSCH e.g. csi- ReportConfigToAddModList SEQUENCE (SIZE (E.maxNrofCSI- ReportConfigurations)) OF IE CSI-ReportConfig; re-configure the measurement configuration (MeasConfig) for RRC measurement reporting, over L3; o In one example, that includes at least an IE ReportConfig (or Rep ortC onfi gNR) ; o In one example, that includes an indication for the WD 22 to include beam measurement information in RRC measurement reports. o In one example, that includes the number of beams to be combined (e.g., averaged) for performing cell quality derivation (as defined in 3GPP TS 38.331, 6.3.2, e.g., nrofSS-BlocksToAverage, nrofCSI-RS- ResourcesTo Av erage); o In one example, that includes the consolidation threshold for selecting beams for performing cell quality derivation (as defined in 3 GPP TS 38.331, 6.3.2, absThreshSS-BlocksConsolidation, absThreshCSI-RS- Consolidation); o In one example, that includes the consolidation threshold for selecting beams to be included in measurement reports per cell (as defined in 3GPP TS 38.331, 6.3.2, absThreshSS-BlocksConsolidation, absThreshCSI-RS- Consolidation). o In one example, that includes further parameters for beam reporting, as in the IE ReportConfigNR (as defined in 3GPP TS 38.331, 6.3.2, reportQuantityRS-Indexes and/or maxNrofRS-IndexesToReport and/or includeBeamMeasurements, or equivalent fields with similar functionality).

A method at a network node 16 may include receiving one or more indications from a WD 22 based on one or more time domain predict! on(s) of measurements on one or more beams in response to a Beam Failure Detection (BFD) at the WD 22. ML-model for time-domain prediction of beam measurements

In some embodiments include using different ML-model or prediction models, based on different set of parameters known at the WD 22.

The method may include the use of “real/ current measurements” as input parameters for the mobility prediction model (e.g., RSRP, RSRQ, SINR at a certain point in time tO for the same beams for which the WD 22 perform predictions, based on an RS type like SSB and/or CSLRS and/or DRMS), either instantaneous values or filtered values (e.g., with LI filter parameters).

The method may also include use of parameters from sensors, such as WD 22 positioning information (e.g., Global Positioning System (GPS) coordinates, barometric sensor information or other indicators of height), rotation sensors, proximity sensors, and mobility such as, location information, previous connected network node history, speed and mobility direction, information from mapping/guiding applications (e.g., GOOGLE maps, APPLE maps).

The method may also include the usage of metrics related to WD 22 connection, such as the input from sensors such as rotation potential blockers such as human body for a hand-held device, movement, etc., WD 22 uses some route information (e.g., current location, final destination and route) as input.

The method may also include the use of WD 22 mobility history information such as last visited beams, LI measurements, CSI measurements, etc.

The method may also include the use of time information such as the current time (e.g., 10: 15 am) and associated time zone (e.g., 10: 15 GMT). That may be relevant if the WD 22 has a predictable trajectory and it is typical that at a certain time the WD 22 is in a certain location.

The WD 22 may be configured (e.g., by the network, via an RRC message) to utilize at least one of the above parameters as input to the ML-model for beam management (in this particular case, for BFD). The availability of these parameters (e.g., in case of sensors, the availability at the WD 22 of a sensor, like barometric sensor) may depend on a capability information indicated to the network node 16. If the network node 16 is aware that the WD 22 is capable of performing certain measurements (like based on sensors) and, if the network node 16 is aware that a WD 22 benefits in using a parameter in an ML-model, the WD 22 may be configured to use at least one of these input parameters in the ML-model for which the network is configuring the WD 22 to report. In that case, a procedure where the WD 22 indicates to the network node 16 a capability related information, i.e., the WD 22 indicates to the network node 16 that the WD 22 may download and receive a prediction model from the network node 16 (for example, for mobility prediction information) according to the method. This capability may be related to the software and hardware aspects at the WD 22, availability of sensors, etc. Once the WD 22 has the function available, it may be further configured by the network node 16 to use the function, e.g., in a measurement configuration or reporting configuration, measurement object configuration, etc.

UE/WD 22 obtaining the ML-model

In some embodiments, the WD 22 may obtain from a network node 16 or host computer 24, the ML-model (Inference Model) to be used for performing the one or time domain prediction(s) of measurements on one or more beams in response to a Beam Failure Detection (BFD). The WD 22 may download the ML-model from the network node 16 (e.g., in the RAN or in the CN), or OTT server such as host computer 24.

The following alternatives (i.e., alternative embodiments) may be defined.

Alternative 1 - WD 22 receives one or more ML-model parameters/ configuration(s):

An ML-model may be signaled using existing model formats such as Open Neural Network Exchange (ONNX), or formats used in commonly used toolboxes such as Keras or Pytorch. In general, the ML-model may be signaled using a high- level model description, plus a detailed information regarding the weights of each layer if the model includes a neural network. The high-level model description (model parameter vector) may for example include parameters defining the structure and characteristics of the model, such as for example number of layers, activation function of respective layer, nature of connections between nodes of respective layer, weights, loss function, just to mention a few, of a neural network. The detailed information may include the value(s) for each parameter in the ML-model.

Alternative 2 - container-based signaling:

The network node 16 may in one embodiment, create a containerized image with the ML-model. The network node 16 may for example use Docker containers to create, and signal to the WD 22 an image capable of executing the trained ML- model. When specifying the model parameters as described in alternative 1, the WD 22 may be configured ensure that it has the correct libraries, runtimes, and other technical dependencies are installed in order to execute the ML-model. Another approach is to use a so-called container. Docker is one such example, where the Docker containers contain all components which are needed for the ML model, including code, libraries, runtimes, and system tools. Containers may therefore be used to ensure that the WD 22 does not risk missing or having incompatible libraries leading to errors. However, since the containers supports more than only the model parameters itself, the over-the-air signaling size may be larger in comparison to alternative 1.

Alternative 3 - ML-model at the WD 22:

In one embodiment, the WD 22 is equipped with a set of ML-models (e.g., from factory, obtained from the USIM card) each capable of predicting a time series of RSRP measurements, where the model parameters could be specified in existing standards. The WD 22 may thus be equipped with a set of ML-models with a general configuration, e.g., trained on an aggregated dataset from multiple deployment scenarios (real data or simulations). The network, in this embodiment, may not need to transmit the model parameters to the WD 22 but could instead transmit an index of which ML-models, in the set of ML-models, that it should use.

Some example embodiments are as follows:

Embodiment Al . A network node configured to communicate with a wireless device, WD, the network node configured to, and/or comprising a radio interface and/or comprising processing circuitry configured to: receive at least one indication of a predicted measurement from the WD based at least in part on at least one time domain prediction of measurements on at least one beam in response to a beam failure detection, BFD, at the WD; and configure the WD with at least one parameter for performing the at least one time domain prediction of measurements based at least in part on the at least one indication.

Embodiment A2. The network node of Embodiment Al, wherein the network node, radio interface and/or processing circuitry are further configured to reconfigure at least one of reference signals and transmission configuration indicator, TCI, states.

Embodiment A3. The network node of any of Embodiments Al and A2, wherein the at least one indication includes a statistical metric based at least in part on a distribution of time domain predictions of measurements.

Embodiment A4. The network node of any of Embodiments A1-A3, wherein the at least one indication includes a beam identifier based at least in part on the at least one time domain prediction of measurements.

Embodiment A5. The network node of any of Embodiments A1-A4, wherein the at least one indication includes a references signal identifier.

Embodiment Bl. A method implemented in a network node, the method comprising: receiving at least one indication of a predicted measurement from the WD based at least in part on at least one time domain prediction of measurements on at least one beam in response to a beam failure detection, BFD, at the WD; and configuring the WD with at least one parameter for performing the at least one time domain prediction of measurements based at least in part on the at least one indication.

Embodiment B2. The method of Embodiment Bl, further comprising reconfiguring at least one of reference signals and transmission configuration indicator, TCI, states.

Embodiment B3. The method of any of Embodiments Bl and B2, wherein the at least one indication includes a statistical metric based at least in part on a distribution of time domain predictions of measurements.

Embodiment B4. The method of any of Embodiments B 1-B3, wherein the at least one indication includes a beam identifier based at least in part on the at least one time domain prediction of measurements.

Embodiment B5. The method of any of Embodiments B 1-B4, wherein the at least one indication includes a references signal identifier.

Embodiment Cl . A wireless device (WD) configured to communicate with a network node, the WD configured to, and/or comprising a radio interface and/or processing circuitry configured to: perform at least one time domain prediction of measurements on at least one beam in response to a beam failure detection, BFD; and transmit at least one indication of the at least one time domain prediction of measurements.

Embodiment C2. The WD of Embodiment Cl, wherein the at least one indication includes a statistical metric based at least in part on a distribution of time domain predictions of measurements.

Embodiment C3. The WD of any of Embodiments Cl and C2, wherein the at least one indication includes a beam identifier based at least in part on the at least one time domain prediction of measurements.

Embodiment C4. The WD of any of Embodiments C1-C3, wherein the at least one indication includes a references signal identifier.

Embodiment C5. The WD of any of Embodiments C1-C4, wherein the at least one beam includes at least one of a beam configured for BFD monitoring, a candidate beam, a beam selected during beam failure recovery, BFR, and a beam configured for a channel state information, CSI, report.

Embodiment DI . A method implemented in a wireless device (WD), the method comprising: performing at least one time domain prediction of measurements on at least one beam in response to a beam failure detection, BFD; and transmitting at least one indication of the at least one time domain prediction of measurements.

Embodiment D2. The method of Embodiment DI, wherein the at least one indication includes a statistical metric based at least in part on a distribution of time domain predictions of measurements.

Embodiment D3. The method of any of Embodiments DI and D2, wherein the at least one indication includes a beam identifier based at least in part on the at least one time domain prediction of measurements.

Embodiment D4. The method of any of Embodiments D1-D3, wherein the at least one indication includes a references signal identifier.

Embodiment D5. The method of any of Embodiments D1-D4, wherein the at least one beam includes at least one of a beam configured for BFD monitoring, a candidate beam, a beam selected during beam failure recovery, BFR, and a beam configured for a channel state information, CSI, report.

As will be appreciated by one of skill in the art, the concepts described herein may be embodied as a method, data processing system, computer program product and/or computer storage media storing an executable computer program. Accordingly, the concepts described herein may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects all generally referred to herein as a “circuit” or “module.” Any process, step, action and/or functionality described herein may be performed by, and/or associated to, a corresponding module, which may be implemented in software and/or firmware and/or hardware. Furthermore, the disclosure may take the form of a computer program product on a tangible computer usable storage medium having computer program code embodied in the medium that may be executed by a computer. Any suitable tangible computer readable medium may be utilized including hard disks, CD-ROMs, electronic storage devices, optical storage devices, or magnetic storage devices.

Some embodiments are described herein with reference to flowchart illustrations and/or block diagrams of methods, systems and computer program products. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer (to thereby create a special purpose computer), special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer readable memory or storage medium that may direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instruction means which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.

It is to be understood that the functions/acts noted in the blocks may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Although some of the diagrams include arrows on communication paths to show a primary direction of communication, it is to be understood that communication may occur in the opposite direction to the depicted arrows.

Computer program code for carrying out operations of the concepts described herein may be written in an object oriented programming language such as Python, Java® or C++. However, the computer program code for carrying out operations of the disclosure may also be written in conventional procedural programming languages, such as the "C" programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer. In the latter scenario, the remote computer may be connected to the user's computer through a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).

Many different embodiments have been disclosed herein, in connection with the above description and the drawings. It will be understood that it would be unduly repetitious and obfuscating to literally describe and illustrate every combination and subcombination of these embodiments. Accordingly, all embodiments may be combined in any way and/or combination, and the present specification, including the drawings, shall be construed to constitute a complete written description of all combinations and subcombinations of the embodiments described herein, and of the manner and process of making and using them, and shall support claims to any such combination or subcombination.

It will be appreciated by persons skilled in the art that the embodiments described herein are not limited to what has been particularly shown and described herein above. In addition, unless mention was made above to the contrary, it should be noted that all of the accompanying drawings are not to scale. A variety of modifications and variations are possible in light of the above teachings without departing from the scope of the following claims.

Claims

What is claimed is:

1. A method in a wireless device, WD (22), configured to communicate with a network node (16), the method comprising: performing (S142) at least one time domain prediction of measurements of signals on at least one beam; and in response to a beam failure detection, BFD, transmitting (S144) to the network node (16) at least one time domain prediction.

2. The method of Claim 1, wherein the at least one time domain prediction is based at least in part on an output of a machine learning, ML, process, configured to predict measurements based at least in part on actual measurements of the signals.

3. The method of any of Claims 1 and 2, wherein the at least one time domain prediction includes at least one of an average of a series of time domain predictions and a statistical measure of a distribution of time domain predictions.

4. The method of any of Claims 1-3, wherein a measurement of a signal includes at least one of reference signal received power, RSRP, reference signal received quality, RSRQ, received signal strength indicator, RS SI, and signal to interference plus noise ratio.

5. The method of any of Claims 1-4, wherein beams for which signals are measured correspond to at least one of at least one beam configured for BFD monitoring, at least one candidate beam to be selected during a beam failure recovery, BFR, procedure and at least one beam configured for a channel state information, CSI, report.

6. The method of any of Claims 1-5, further comprising, in response to the BFD, performing at least one of initiating a random access procedure when the BFD is for one of a primary cell and a special cell.

7. The method of any of Claims 1-6, further comprising, in response to the BFD, triggering at least one scheduling request when the BFD is for a secondary cell and no uplink scheduling resources are available for a new transmission

8. The method of any of Claims 1-7, further comprising, in response to the BFD, initiating a contention free random access, CFRA, procedure for beam failure recovery, BFR.

9. The method of any of Claims 1-8, further comprising, in response to the BFD, transmitting a first medium access control, MAC, control element, CE, on a first available physical uplink shared channel when the BFD is for a secondary cell, Scell, and uplink scheduling resources are available for a new transmission.

10. The method of any of Claims 1-9, further comprising performing the time domain predictions during a prediction window with a prediction periodicity configured by the network node (16).

11. The method of Claim 10, wherein the prediction periodicity is an integer multiple of a channel state information reporting periodicity.

12. The method of any of Claims 1-11, wherein the time domain predictions correspond to an average power of resource elements that carry secondary synchronization signals.

13. The method of any of Claims 1-12, wherein the time domain predictions include estimates of demodulation reference signals for a physical broadcast channel, PBCH.

14. The method of any of Claims 1-13, the time domain predictions are based at least in part on an autoregressive, AR, model.

15. The method of any of Claims 1-14, further comprising commencing the time domain predictions when a number of beam failure indications are counted.

16. The method of any of Claims 1-15, further comprising comparing each time domain prediction to a threshold and transmitting only time domain predictions above the threshold.

17. The method of Claim 16, further comprising transmitting to the network node (16) times at which the time domain predictions are above the threshold.

18. The method of any of Claims 16 and 17, further comprising transmitting to the network node (16) an indication of a ratio of predictions above the threshold to a total number of predictions in a prediction interval.

19. The method of Claim 18, wherein the ratio of predictions is indicated by a set of at least one bit indicating a range of the ratio of predictions.

20. The method of any of Claims 16-19, further comprising comparing a number of time domain predictions above the threshold to a counter value and setting a stability flag when the number of time domain predictions above the threshold exceed the counter value.

21. A wireless device, WD (22), configured to communicate with a network node (16), the WD (22) comprising: processing circuitry (84) configured to perform at least one time domain prediction of measurements of signals on at least one beam; and a radio interface (82) in communication with the processing circuitry (84) and configured to, in response to a beam failure detection, BFD, transmit to the network node (16) at least one time domain prediction.

22. The WD (22) of Claim 12, wherein the at least one time domain prediction is based at least in part on an output of a machine learning, ML, process, configured to predict measurements based at least in part on actual measurements of the signals.

23. The WD (22) of any of Claims 21 and 22, wherein the at least one time domain prediction includes at least one of an average of a series of time domain predictions and a statistical measure of a distribution of time domain predictions.

24. The WD (22) of any of Claims 21-23, wherein a measurement of a signal includes at least one of reference signal received power, RSRP, reference signal received quality, RSRQ, received signal strength indicator, RS SI, and signal to interference plus noise ratio.

25. The WD (22) of any of Claims 21-24, wherein beams for which signals are measured correspond to at least one of at least one beam configured for BFD monitoring, at least one candidate beam to be selected during a beam failure recovery, BFR, procedure and at least one beam configured for a channel state information, CSI, report.

26. The WD (22) of any of Claims 21-25, wherein the processing circuitry (84) is configured to, in response to the BFD, perform at least one of initiating a random access procedure when the BFD is for one of a primary cell and a special cell.

27. The WD (22) of any of Claims 21-26, wherein the processing circuitry (84) is configured to, in response to the BFD, trigger at least one scheduling request when the BFD is for a secondary cell and no uplink scheduling resources are available for a new transmission

28. The WD (22) of any of Claims 21-27, wherein the processing circuitry (84) is configured to, in response to the BFD, initiate a contention free random access, CFRA, procedure for beam failure recovery, BFR.

29. The WD (22) of any of Claims 21-28, wherein the processing circuitry (84) is configured to, in response to the BFD, transmit a first medium access control, MAC, control element, CE, on a first available physical uplink shared channel when the BFD is for a secondary cell, Scell, and uplink scheduling resources are available for a new transmission.

30. The WD (22) of any of Claims 21-29, wherein the processing circuitry (84) is configured to perform the time domain predictions during a prediction window with a prediction periodicity configured by the network node (16).

31. The WD (22) of Claim 30, wherein the prediction periodicity is an integer multiple of a channel state information reporting periodicity.

32. The WD (22) of any of Claims 21-31, wherein the time domain predictions correspond to an average power of resource elements that carry secondary synchronization signals.

33. The WD (22) of any of Claims 21-32, wherein the time domain predictions include estimates of demodulation reference signals for a physical broadcast channel, PBCH.

34. The WD (22) of any of Claims 21-33, the time domain predictions are based at least in part on an autoregressive, AR, model.

35. The WD (22) of any of Claims 21-34, wherein the processing circuitry is configured to commence the time domain predictions when a number of beam failure indications are counted.

36. The WD (22) of any of Claims 21-35, wherein the processing circuitry (84) is configured to compare each time domain prediction to a threshold and transmitting only time domain predictions above the threshold.

37. The WD (22) of Claim 36, wherein the processing circuitry (84) is configured to transmit to the network node (16) times at which the time domain predictions are above the threshold.

38. The WD (22) of any of Claims 36 and 37, wherein the processing circuitry (84) is configured to transmit to the network node (16) an indication of a ratio of predictions above the threshold to a total number of predictions in a prediction interval.

39. The WD (22) of Claim 38, wherein the ratio of predictions is indicated by a set of at least one bit indicating a range of the ratio of predictions.

40. The WD (22) of any of Claims 36-39, wherein the processing circuitry (84) is configured to compare a number of time domain predictions above the threshold to a counter value and setting a stability flag when the number of time domain predictions above the threshold exceed the counter value.

41. A method in a network node (16) configured to communicate with a wireless device, WD (22), the method comprising: configuring (S146) the WD (22) with at least one parameter to transmit at least one time domain prediction of measurements of signals on at least one beam in an event of beam failure detection, BFD, by the WD (22); and receiving (SI 48) from the WD (22), at least one time domain prediction of measurement of signals.

42. The method of Claim 41, further comprising, in response to receiving the at least one time domain prediction, performing at least one of reconfiguring radio link monitoring reference signals, reconfiguring beam failure detection reference signals, reconfiguring at least one antenna parameter, one of activating, deactivating and reconfiguring transmission configuration indicator states, reconfiguring layer 1 resources and modifying at least one BFD reference signal to be monitored.

43. The method of any of Claims 41 and 42, further comprising configuring the WD (22) with at least one of a prediction periodicity, a number of predictions and a prediction window.

44. The method of Claim 43, wherein the prediction periodicity is an integer multiple of a channel state information reporting periodicity.

45. The method of any of Claims 41-44, further comprising receiving from the WD (22) a set of at least one time at which the time domain predictions are above a threshold.

46. A network node (16) configured to communicate with a wireless device, WD (22), the network node (16) comprising: processing circuitry (68) configured to configure the WD (22) with at least one parameter to transmit at least one time domain prediction of measurements of signals on at least one beam in an event of beam failure detection, BFD, by the WD (22); and a radio interface (62) in communication with the processing circuitry (68) and configured to receive from the WD (22), at least one time domain prediction of measurement of signals.

47. The network node (16) of Claim 41, wherein the processing circuitry (68) is configured to, in response to receiving the at least one time domain prediction, perform at least one of reconfiguring radio link monitoring reference signals, reconfiguring beam failure detection reference signals, reconfiguring at least one antenna parameter, one of activating, deactivating and reconfiguring transmission configuration indicator states, reconfiguring layer 1 resources and modifying at least one BFD reference signal to be monitored.

48. The network node (16) of any of Claims 41 and 42, wherein the processing circuitry is configured to configure the WD (22) with at least one of a prediction periodicity, a number of predictions and a prediction window.

49. The network node (16) of Claim 43, wherein the prediction periodicity is an integer multiple of a channel state information reporting periodicity.

50. The network node (16) of any of Claims 41-44, wherein the processing circuitry (68) is configured to receiving from the WD (22) a set of at least one time at which the time domain predictions are above a threshold.