Phase discontinuity prediction

Abstract

Examples of the present disclosure relate to phase discontinuity prediction. A UE can indicate a capability of the UE for phase discontinuity prediction to a network node, and receive a configuration for phase discontinuity prediction result reporting from the network node. The configuration can include at least a reporting indication method and one or more reporting conditions. The UE can perform phase discontinuity prediction, and determine whether to report a result of the phase discontinuity prediction based on the received configuration.

Description

Technical Field

[0001] Examples disclosed herein relate to phase discontinuity prediction. Some examples involve phase discontinuity prediction performed using machine learning models. Background Technology

[0002] Joint Channel Estimation (JCE) for the Physical Uplink Shared Channel (PUSCH) can be used to enhance uplink (UL) coverage for both data and control channels. For JCE to be possible, cross-slot phase continuity for JCE must be maintained on the User Equipment (UE) side. Summary of the Invention

[0003] According to various, but not necessarily all, examples of this disclosure, a user equipment (UE) is provided, including: At least one processor; and At least one memory stores instructions that, when executed by at least one processor, cause the UE to execute at least the following: Indicate the UE's ability to predict phase discontinuities to network nodes; The configuration for receiving phase discontinuity prediction results reports from network nodes includes at least a reporting indication method and one or more reporting conditions. Perform phase discontinuity prediction; and Based on the received configuration, determine whether to report the results of the phase discontinuity prediction.

[0004] Phase discontinuity prediction can be performed using machine learning models.

[0005] One or more reporting conditions may include one or more thresholds for the probability of phase discontinuities. Different thresholds may be associated with different use cases.

[0006] The configuration can be received via at least one of the following: radio resource control signaling; and downlink control information.

[0007] Phase discontinuity prediction can involve one of the following: the probability of a single event causing a phase discontinuity; and the probability of multiple events causing a cumulative phase discontinuity.

[0008] The reporting indication method may include one of the following: a bit indicating whether the reporting condition is met; a value indicating the probability that one or more events cause a phase discontinuity; a value indicating the result of the phase discontinuity prediction; and an indication of the duration for which the phase discontinuity meets the reporting condition.

[0009] The memory and computer program can also be configured to receive indications of event parameters, as well as one or more thresholds for the probability of phase discontinuities associated with the event parameters.

[0010] One or more reporting conditions received from the network node may include: a first reporting condition for a first scenario and a second reporting condition for a second scenario.

[0011] Based on various, but not necessarily all, examples of this disclosure, a method may be provided, including: Indicate the UE's ability to predict phase discontinuities to network nodes; Receive configuration from network nodes for reporting phase discontinuity prediction results, the configuration including at least a reporting indication method and one or more reporting conditions; Perform phase discontinuity prediction; and Based on the received configuration, determine whether to report the results of the phase discontinuity prediction.

[0012] Based on various, but not necessarily all, examples of this disclosure, a computer program may be provided, including computer program instructions, for causing a UE to perform at least the following operations or for performing at least the following operations: Indicate the UE's ability to predict phase discontinuities to network nodes; Receive configuration from network nodes for reporting phase discontinuity prediction results, the configuration including at least a reporting indication method and one or more reporting conditions; Perform phase discontinuity prediction; and Based on the received configuration, determine whether to report the results of the phase discontinuity prediction.

[0013] Based on various, but not necessarily all, examples of this disclosure, a network node may be provided, including: At least one processor; and At least one memory stores instructions that, when executed by at least one processor, cause a network node to execute at least the following: The ability to receive predictions about phase discontinuities from the UE; Send a configuration to the UE for reporting phase discontinuity prediction results, the configuration including at least a reporting indication method and one or more reporting conditions; and The UE receives a report indicating the results of the phase discontinuity prediction, where the report is based on configuration.

[0014] One or more reporting criteria may include one or more thresholds for calculating the probability of phase discontinuity. Different thresholds are associated with different use case scenarios.

[0015] The configuration can be sent via at least one of the following: radio resource control signaling; and downlink control information.

[0016] Phase discontinuity prediction can involve one of the following: the probability of a single event causing a phase discontinuity; and the probability of multiple events causing a cumulative phase discontinuity.

[0017] The reporting indication method may include one of the following: a bit indicating whether the reporting condition is met; a value indicating the probability that one or more events cause a phase discontinuity; a value indicating the result of the phase discontinuity prediction; and an indication of the duration for which the phase discontinuity meets the reporting condition.

[0018] The processor and memory can also be arranged to enable the network node to perform: determining the probability that one or more events cause a phase discontinuity based on the value of the received indication of the phase discontinuity prediction result.

[0019] The processor and memory can also be configured to enable network nodes to perform at least one of the following: adjust one or more reporting conditions; or disable the reporting of phase discontinuity predictions.

[0020] Based on various, but not necessarily all, examples of this disclosure, a method may be provided, including: The ability to receive predictions about phase discontinuities from the UE; Send a configuration to the UE for reporting phase discontinuity prediction results, the configuration including at least a reporting indication method and one or more reporting conditions; and The UE receives a report indicating the results of the phase discontinuity prediction, where the report is based on configuration.

[0021] Based on various, but not necessarily all, examples of this disclosure, a computer program may be provided, including computer program instructions, for causing a UE to perform at least the following operations or for performing at least the following operations: The ability to receive predictions about phase discontinuities from the UE; Send a configuration to the UE for reporting phase discontinuity prediction results, the configuration including at least a reporting indication method and one or more reporting conditions; and The UE receives a report indicating the results of the phase discontinuity prediction, where the report is based on configuration.

[0022] According to various, but not all, embodiments, an apparatus is provided, comprising: At least one processor; and At least one memory; At least one memory stores instructions that, when executed by at least one processor, cause the device to perform at least a portion of one or more methods described herein.

[0023] According to various, but not necessarily all, embodiments, an apparatus is provided including components for performing at least a portion of one or more methods described herein. The description of functions and / or actions should also be considered as disclosing any components suitable for performing such functions and / or actions. The functions and / or actions described herein can be performed using any suitable method and in any suitable manner.

[0024] Examples claimed in the appended claims are provided according to various, but not necessarily all, embodiments.

[0025] Although the examples and optional features disclosed above are described separately, it should be understood that they are included within this disclosure in all possible combinations and permutations. It should be understood that the various examples of this disclosure may include any or all of the features described with respect to other examples of this disclosure, and vice versa. Furthermore, it should be understood that any one or more or all features, in any combination, may be implemented / included / executable by means, methods, and / or instructions as needed and appropriately. The description of a function should also be considered as disclosing any components suitable for performing that function. Attached Figure Description

[0026] Some examples will now be described with reference to the accompanying drawings, in which:

[0027] Figure 1 An example network is shown;

[0028] Figure 2 An example of OCC is shown;

[0029] Figure 3A and 3B Example methods are shown;

[0030] Figure 4 An example signaling procedure is shown;

[0031] Figure 5 An example RL model is shown;

[0032] Figure 6 The method using RL models is shown; and

[0033] Figure 7 An example controller is shown.

[0034] The accompanying drawings are not necessarily drawn to scale. For clarity and simplicity, some features and views in the drawings may be shown schematically or at scale. For example, the dimensions of some elements in the drawings may be enlarged relative to other elements to aid illustration. Appropriate reference numerals are used in the drawings to designate the corresponding features. For clarity, not all reference numerals are shown in all drawings. definition

[0035] AI (Artificial Intelligence)

[0036] BW bandwidth

[0037] CP-OFDM Cyclic Prefix - OFDM

[0038] DCI Downlink Control Information

[0039] DFT-S-OFDM Discrete Fourier Transform Spread Spectrum OFDM

[0040] DL downlink

[0041] DMRS demodulation reference signal

[0042] GNSS Global Navigation Satellite System

[0043] HARQ-ACK Hybrid Automatic Repeat Request - Acknowledgement

[0044] HW Hardware

[0045] JCE Joint Channel Estimation

[0046] KPIs (Key Performance Indicators)

[0047] MAC-CE Media Access Control - Control Elements

[0048] ML Machine Learning

[0049] NTN non-terrestrial networks

[0050] OCC Orthogonal Cover Code

[0051] OFDM (Orthogonal Frequency Division Multiplexing)

[0052] OLPC Open-Loop Power Control

[0053] PA power amplifier

[0054] PC power control

[0055] PD phase discontinuity

[0056] PUCCH (Physical Uplink Control Channel)

[0057] PUSCH Physical Uplink Shared Channel

[0058] RF (Radio Frequency)

[0059] RL (Reinforcement Learning)

[0060] RRC (Radio Resource Control)

[0061] TA scheduled in advance

[0062] UCB Upper Confidence Boundary

[0063] UE User Equipment Detailed Implementation

[0064] Figure 1 An example of a communication network 100 to which the examples of this disclosure can be applied is shown. Communication network 100 is a cellular communication network. Communication network 100 includes a network access node 102. Network access node 102 provides one or more cells 104. Cell 104 can define the coverage area or service area of ​​the corresponding network access node 102.

[0065] Network access node 102 can provide radio access to a communication network for one or more user equipment (UE) devices 106. This radio access may include downlink communication from network access node 102 to UE 106 and uplink communication from UE 106 to network access node 102. Examples of uplink channels include a physical uplink control channel for transmitting control information and a physical uplink shared channel for transmitting data to network access node 102. Examples of downlink channels include a physical downlink control channel for transmitting control information and a physical downlink shared channel for transmitting data to UE 106.

[0066] There may be multiple UEs 106 in network 100. Each UE 106 may be served by the same or different network access nodes 102.

[0067] If the communication network 100 contains multiple network access nodes 102, these network access nodes 102 can be interconnected via interfaces. The LTE specification refers to such interfaces as X2 interfaces. The interface between an LTE node and a 5G node, or between two 5G nodes, can be called an Xn interface.

[0068] Network access node 102 can also connect to the core network 108 of communication network 100 via another interface. Core network 108 may contain core network nodes. The LTE specification designates the core network as an evolved packet core (EPC), and the core network may include entities such as mobility management entities and gateway nodes. The MME can handle the mobility of terminal devices within a tracking area covering multiple cells and handle signaling connections between terminal devices such as UE 106 and core network 108. Gateway nodes can handle data routing within core network 108 and to / from terminal devices such as UE 106. The 5G specification designates the core network as a 5G core network. A 5G core network may include, for example, access and mobility management functions, user plane functions / gateways, and other functions. The AMF can handle non-access stratum (NAS) signaling termination, NAS encryption and integrity protection, registration management, connection management, mobility management, access authentication and authorization, and security context management. UPF nodes can support, for example, packet routing and forwarding, packet inspection, and quality of service (QoS) processing. In other types of networks, other types of entities can be provided within the core network 108.

[0069] In such Figure 1 In networks such as network 100 shown, Joint Channel Estimation (JCE) for the Physical Uplink Shared Channel (PUSCH) can be used to enhance uplink coverage for both data and control channels. JCE works by bundling demodulation reference signals across different time slots (continuous or discontinuous), which improves channel estimation accuracy at network node 102. This is particularly true for the Physical Uplink Control Channel (PUCCH) / PUSCH of UE 106 located at the cell edge.

[0070] For JCE to proceed, cross-timeslot phase continuity must be maintained at the user equipment side to compensate for time-varying variations in the UE 106's radio frequency (RF) circuitry. Phase continuity must be guaranteed at UE 106 for the JCE operation at network node 102 to produce the desired results. Network node 102 performs JCE operations blindly regarding phase continuity; that is, network node 102 is unaware of the phase continuity status at UE 106 when performing JCE operations.

[0071] Phase changes at the transmitter (i.e., UE 106) cause rotation of the frequency domain samples received at the receiver (i.e., network node 102). In this context, network node 102 lacks a mechanism to detect whether this rotation is occurring. From the perspective of network node 102, the time-varying phase of the signal transmitted by UE 106, and the resulting phase continuity or discontinuity, may depend on predictable and unpredictable events or aspects. These events or aspects include, but are not limited to: Known events for network node 102: These are events in which it can be predicted whether the event will cause phase discontinuity. Example events include transmit precoder phase, network-assisted timing adjustments, frequency resource allocation, transmit waveform changes (CP-OFDM<->DFT-s-OFDM), and DL timing monitoring. Unknown events at network node 102: These refer to events where it is impossible to predict whether a particular event will cause phase discontinuity. Example events include the actual transmit power at UE 106 (open-loop power control, OLPC), UE-related timing adjustments, impairments, and unexpected events occurring during the RF phase of UE 106.

[0072] Given the very specific requirements that will exist in this regard, predictable events are expected to be handled without issue within the context of the JCE. However, the examples in this disclosure provide a mechanism for handling unpredictable events that may prevent the UE 106 from maintaining phase continuity.

[0073] Similarly, in such Figure 1 In networks such as Network 100 shown, multiplexing based on orthogonal coverage codes (OCC) can be used to increase the capacity of Network 100. This is particularly suitable for UE 106, which is located near the cell edge and benefits from duplication.

[0074] Figure 2 The principle of OCC is illustrated. In this example, two UEs transmit two PUSCH repetitions on the same time-frequency resource. For these transmissions, the two UEs apply different OCCs to their transmitted signals. In this case, it is assumed that the transmitted signals remain unchanged across the repetitions. Applying different OCCs allows the receiver of network node 102 to receive (i.e., demodulate and decode) the signal from each UE without interference from the signal from the other UE.

[0075] exist Figure 2 In the example shown, the first UE1 applies OCC [1, 1], while the second UE2 applies OCC [1, -1]. The first UE1 has signal x1, and the second UE2 has signal x2.

[0076] Figure 2 The transmission is shown to be repeated twice. In the first transmission 200_1, the PUSCH 202_1 of the first UE1 includes x1 (+1), and the second UE2's PUSCH 202_2 includes x2 (+1). In the second transmission 200_2, the PUSCH 202_1 of the first UE1 includes x1 (+1), the second UE2's PUSCH 202_2 includes x2 (+1).

[0077] The following equations mathematically illustrate its working principle. In these equations, x1 and x2 represent the signals transmitted by UE1 and UE2 in the two repetitions, respectively. y1 and y2 represent the total signals received by the receiver of network node 102 in the first and second repetitions, respectively.

[0078] In these equations, network node 102 retrieves the signal from UE2 by cross-correlating the two received signals y1 and y2 with the OCC used by UE2 (i.e., [1, -1]), without interference from the signal from UE1. To generate the digital cross-correlation, a suitable operation is the "sum of products" at time "zero," as shown in equation (1). Accordingly, applying the result corresponding to the OCC of UE1 (i.e., [+1, +1]) is shown in equation (2), where the result yields the signal x1 initially transmitted by UE1.

[0079] For simplicity, the above example does not consider channel impairments and additive noise. It is important to note that channel impairments always affect the signal received at network node 102. Therefore, for the OCC solution to work effectively in practice, the channel response across repetitions should not change. Channel response includes not only the physical channel response but also the response of the UE RF circuitry. An important aspect of the UE RF circuitry response changing over time is called phase continuity. Therefore, phase continuity is a necessary requirement for UE 106 performing PUSCH repetitions with OCC and for JCE. That is, UE 106 is mandated to maintain phase continuity across PUSCH repetitions with OCC. If UE 106 fails to maintain phase continuity across PUSCH repetitions with OCC, not only will its own performance degrade, but it will also significantly interfere with other multiplexed UEs of UE 106, resulting in a degraded system performance.

[0080] In TS 38.214 Clause 6.1.7, a list of UE operations that cause phase discontinuities in PUSCH transmissions across PUSCH repetition type A is defined as events (as listed in Table 1 below). Therefore, these events will cause problems in certain scenarios (e.g., OCC operations) because they will prevent the network node 102 receiver from coherently combining PUSCH repetitions and removing interference from one UE 106 while decoding other multiplexed UEs 106. Table 1

[0081] It is important to note that uplink timing advance (TA) adjustments are mentioned in this list because they cause phase continuity issues at user equipment 106. However, even if not mentioned in this list, power control (PC) adjustments across PUSCH repetitions can also cause phase and power consistency issues. These two events are particularly relevant for non-terrestrial network (NTN) UEs, as NTN UEs are required to perform autonomous TA and PC updates during operation. These updates are based on Global Navigation Satellite System (GNSS) position updates. These updates enable synchronization at network node 102. Such autonomous TA and PC updates can occur at any time within a PUSCH repetition, and user equipment 106 needs to properly handle these events to maintain phase continuity across repetitions.

[0082] The degree of phase discontinuity caused by the event, and consequently the impact of the event on network performance, may depend on factors at user equipment 106, such as temperature, PA gain state, the nature of the event itself, or any other suitable factor. The same event may cause negligible phase discontinuities in the first set of conditions, but may cause non-negligible phase discontinuities in the second set of conditions.

[0083] The examples of this disclosure provide a mechanism that can be used to improve performance when events occur during transmission. The examples of this disclosure are able to predict whether an event will produce a non-negligible phase discontinuity and notify network nodes accordingly. A phase discontinuity can be considered non-negligible if predetermined conditions are met. These conditions can be thresholds related to the impact on performance or any other suitable criteria.

[0084] Figure 3A and 3B Example methods that can be used in the implementation of this disclosure are shown. Figure 3A The example method can be implemented by UE 106 or any other suitable device. Figure 3B An example can be implemented by network node 102. Network node 102 can be an access node, such as a gNB or any other suitable type of network node. Figure 3B The method corresponds to Figure 3A The method, because of execution Figure 3B The network node 102 of the method can be used for execution Figure 3A The method provides user equipment 106 with access to network 100.

[0085] The method implemented by UE 106 includes, at block 300, instructing network node 102 on UE 106's ability to predict phase discontinuities. For example, UE 106 may indicate that UE 106 has an ML model or any other suitable means that can be used to predict phase discontinuities in relevant events and situations.

[0086] At box 302, user equipment 106 receives configuration from network node 102. This configuration is used for reporting phase discontinuity prediction results. The configuration includes at least one reporting instruction method. That is, the configuration can indicate how phase discontinuity prediction results should be reported. The configuration may also include one or more reporting conditions.

[0087] In some examples, one or more reporting conditions may include one or more thresholds for the probability of phase discontinuities. Different thresholds may be associated with different use cases or scenarios.

[0088] Configuration can be received via any suitable means. For example, it can be received via radio resource control signaling, downlink control information (DCI), or other suitable means.

[0089] At box 304, UE 106 performs phase discontinuity prediction. Phase discontinuity prediction can be performed using a machine learning model or any other suitable means.

[0090] In some examples, phase discontinuity prediction may involve the probability that a single event causes a phase discontinuity. In other examples, phase discontinuity prediction may involve the probability that multiple events cause a cumulative phase discontinuity.

[0091] The predicted duration of phase discontinuity can include the duration of a time slot. In some examples, this duration can be indicated, and it can be associated with one or more scene configurations. Scene configurations can be associated with OCC configurations or any other suitable factors. This duration can be indicated implicitly or explicitly.

[0092] At box 306, user equipment 106 determines whether to report the phase discontinuity prediction result. This determination is based on the received configuration. If the configured reporting conditions are met, the phase discontinuity prediction result should be reported according to the reporting instruction method. If the configured reporting conditions are not met, the phase discontinuity prediction result is not reported.

[0093] In some examples, reporting conditions may include a threshold for calculating the probability of a predicted phase discontinuity. For instance, if the probability of a predicted phase discontinuity being non-negligible is higher than the threshold, the reporting conditions may require reporting the phase discontinuity prediction. Conversely, if the probability of a predicted phase discontinuity being non-negligible is lower than the threshold, the reporting conditions may require not reporting the phase discontinuity prediction. This allows network node 102 to be notified when a phase discontinuity that may affect system performance is anticipated.

[0094] If the prediction of a phase discontinuity is determined to be correct, the prediction result is reported according to the reporting conditions. In some examples, the reporting indication method may include bits indicating whether the reporting conditions are met. For example, a bit value of 1 may indicate that the probability of a non-negligible predicted phase discontinuity is higher than a threshold, and a bit value of 0 may indicate that the probability of a non-negligible predicted phase discontinuity is lower than a threshold.

[0095] In some examples, the reporting indication method may include a value indicating the outcome of the phase discontinuity prediction. This could be a value indicating the magnitude of the phase discontinuity prediction. Network nodes can then use this value to determine whether the phase discontinuity is negligible or non-negligible. In other examples, the reporting indication method may include a value indicating the probability that one or more events cause a non-negligible phase discontinuity (i.e., a phase discontinuity above a given threshold). The probability of a non-negligible phase discontinuity can be determined based on the phase discontinuity and the threshold.

[0096] In some examples, the reporting indication method may include an indication of a clean duration for which phase discontinuities are less than a threshold. This can notify the network that any phase discontinuity is a negligible clean duration. The threshold may be configured by network node 102 or dynamically signaled. In some examples, the reporting condition may include an indication of the maximum clean duration that UE 106 should report.

[0097] In some examples, the configuration may include multiple different reporting conditions. Different reporting conditions can be applied to different scenarios. For example, a first reporting condition may be used for a first scenario, and a second reporting condition may be used for a second scenario. In this case, UE 106 can determine which reporting conditions to use based on the determined scenario.

[0098] In some examples, UE 106 may also receive an indication of event parameters and one or more thresholds for the probability of phase discontinuities associated with the event parameters. This allows different phase discontinuity thresholds to be associated with different events.

[0099] Figure 3B A method that can be implemented by network node 102 is shown. Network node 102 can be used with implementations Figure 3A The method corresponds to UE 106 because it implements Figure 3A The method of UE 106 can be used to execute Figure 3B The method involves network node 102 sending an indication of predictive capability.

[0100] At block 310, the method includes receiving from UE 106 the ability of UE 106 to predict phase discontinuities. For example, UE 106 may notify network node 102 that UE 106 has an ML model or any other suitable means that can be used to predict phase discontinuities in relevant events and situations.

[0101] At box 312, network node 102 sends a configuration to user equipment 106. This network configuration is used for reporting phase discontinuity prediction results. The configuration includes at least one reporting instruction method. That is, the configuration can indicate how phase discontinuity prediction results should be reported. The configuration may also include one or more reporting conditions.

[0102] The reporting conditions can include a threshold for calculating the probability of a predicted phase discontinuity. For example, if the probability that a predicted phase discontinuity is non-negligible is higher than the threshold, the reporting conditions can require reporting the phase discontinuity prediction. Conversely, if the probability that a predicted phase discontinuity is non-negligible is lower than the threshold, the reporting conditions can require not reporting the phase discontinuity prediction. This allows network node 102 to be notified when a phase discontinuity that may affect system performance is anticipated.

[0103] Configuration can be sent via any suitable means. For example, it can be sent via Radio Resource Control (RRC) signaling, or via Downlink Control Information (DCI), or via other suitable means.

[0104] At box 314, network node 102 receives a report from UE 106. The received report indicates the result of phase discontinuity prediction. This report is configuration-based. That is, whether to send a report can be determined based on the reporting conditions in the configuration. Furthermore, the reporting indication method used in the report is determined by the configured reporting indication method.

[0105] In some examples, the reporting indication method may include bits indicating whether the reporting conditions are met. For example, a bit value of 1 may indicate that the probability that the predicted phase discontinuity is non-negligible is higher than a threshold, and a bit value of 0 may indicate that the probability that the predicted phase discontinuity is non-negligible is lower than a threshold.

[0106] In some examples, the reporting indication method may include a value indicating the outcome of the phase discontinuity prediction. This could be a value indicating the magnitude of the phase discontinuity prediction. Network node 102 can then use this value to determine whether the phase discontinuity is negligible or non-negligible. In other examples, the reporting indication method may include a value indicating the probability that one or more events cause a non-negligible phase discontinuity (i.e., a phase discontinuity above a given threshold). The probability of a non-negligible phase discontinuity can be determined based on the phase discontinuity and the threshold.

[0107] In some examples, the reporting indication method may include an indication of the clean duration for which a phase discontinuity satisfies the reporting criteria. For example, this could be a clean duration for which the phase discontinuity is below a threshold. This can notify the network that any phase discontinuity is a negligible clean duration. This threshold may be configured by network node 102 or dynamically signaled. In some examples, the reporting criteria may include an indication of the maximum clean duration that UE 106 needs to report.

[0108] In some examples, phase discontinuity prediction may involve the probability that a single event causes a phase discontinuity. In other examples, phase discontinuity prediction may involve the probability that multiple events cause a cumulative phase discontinuity.

[0109] If network node 102 receives an indication that the phase discontinuity prediction is higher than a threshold, or if network node 102 determines that the phase discontinuity prediction is higher than a threshold, network node 102 may take one or more appropriate actions. For example, network node 102 may adjust one or more configured reporting conditions, or may disable the reporting of phase discontinuity predictions.

[0110] Therefore, the examples in this disclosure enable user equipment 106 to perform phase discontinuity prediction and report it to network node 102. This prior knowledge of the level of phase discontinuity can help network node 102 avoid performance degradation. In cases such as OCC, this also helps protect the performance of other user equipment 106 and the system.

[0111] Figure 4 Example signaling procedures that may be used in some examples in this disclosure are shown.

[0112] In block 400, UE 106 indicates to network node 102 its ability to predict phase discontinuities. This could be an indication that UE 106 has machine learning capabilities or any other suitable type of capability.

[0113] In block 402, network node 102 requests support from UE 106 for predicting phase discontinuities. Network node 102 can enable prediction at UE 106. Network node 102 can send a configuration indicating reporting conditions and preferred reporting indication methods. For example, network node 102 can indicate that it wishes to use a single bit as the reporting indication method. The network node can indicate a threshold for the probability of phase discontinuities. For example, the threshold could be 0.9. Other suitable values ​​can be used in other examples.

[0114] In block 404, network node 102 can provide UE 106 with thresholds for phase discontinuity prediction and reporting. In some use cases, network node 102 can send a list of one or more thresholds to UE 106, depending on the scenario defined by network node 102. These thresholds can be configured by network node 102 via RRC.

[0115] In some examples, multiple threshold tables can be pre-configured. These multiple threshold tables can be defined in the specification or in any other suitable manner. Each table can be associated with different scenarios. For example, a first threshold table can be defined for OCC operation, and this table can include multiple thresholds associated with different OCC characteristics or sizes. Other tables can be used for other scenarios. The thresholds in the tables can have any suitable level of granularity. In an example where multiple available threshold tables are available, network node 102 can provide an indication in block 404 of which pre-configured table UE 106 should use.

[0116] In block 406, network node 102 may indicate parameters that will be used for phase discontinuity prediction. For example, network node 102 may indicate one or more event parameters or any other suitable information. As an example, network node 102 may instruct UE 106 to adjust its timing advance (TA) starting from a specific time slot n (i.e., when an event will occur at the beginning of time slot n). This can be indicated via a Media Access Control-Control Element (MAC-CE) or any other suitable signaling. UE 106 can use the indicated TA as an input for phase discontinuity prediction.

[0117] In some examples, network node 102 can determine the scenarios in which phase discontinuity prediction is required. For example, it can determine whether the phase discontinuity is associated with an OCC scenario and / or OCC characteristics, or whether it applies to any other scenario. Based on this determination, network node 102 can determine the thresholds or probabilities of phase discontinuities to be applied by user equipment 102 for phase discontinuities. In block 406, network node 102 can send these thresholds to UE 106.

[0118] In block 410, the UE performs predictions of phase discontinuities. Prediction can be performed using a machine learning model or any other suitable means. UE 106 can collect all necessary inputs to enable prediction. For example, UE 106 can collect inputs used by a machine learning model.

[0119] The predicted output can be the probability of a phase discontinuity. Other outputs can be used in other examples.

[0120] In block 412, UE 106 determines whether to report the result of the phase discontinuity prediction. UE 106 can make this determination using reporting conditions and thresholds indicated by network node 102. For example, the threshold for reporting phase discontinuities could be a probability value of 0.9. Therefore, if the predicted probability of a phase discontinuity is higher than 0.9, UE 106 will report this to network node 102. Conversely, if the predicted probability of a phase discontinuity is lower than 0.9, UE 106 will not report this to network node 102.

[0121] If UE 106 determines that a result needs to be reported, then in block 414, the UE reports the result of the phase discontinuity prediction to network node 102. Any suitable reporting indication method can be used. For example, the result can be reported as a single bit indicating whether the probability of the predicted phase discontinuity is higher or lower than a threshold. In other examples, a probability value or any other suitable indication of the result can be sent.

[0122] The result can be reported using any appropriate signaling. In some examples, the result can be reported as part of a Hybrid Automatic Repeat Request-Acknowledgement (HARQ-ACK) feedback, or as part of an earlier transmission prior to the event.

[0123] If UE 106 determines that it does not need to report the result, then UE 106 will not send a report in block 414. For example, if the predicted phase discontinuity is negligible or below a threshold, there is no need to report it to network node 102.

[0124] In block 416, network node 102 can respond to the reported results. For example, if a non-negligible phase discontinuity is predicted, network node 102 can discard the UE 106 in the scheduling of OCC operations, or it can take additional processing steps to protect network performance.

[0125] In the examples disclosed herein, a machine learning model can be used to perform phase discontinuity prediction. This machine learning model can contain multiple defined processing steps and can resemble processing instructions associated with regular program code. The difference between regular program code and a machine learning model is that the instructions in regular program code are more explicitly defined at the time of programming. The instructions of a machine learning model are defined by combining a set of predefined processing blocks (e.g., convolution, data normalization, other operators), where the model's weights are unknown at the time of model definition. The weights of the machine learning model are optimized by feeding the model a large amount of input and reference data, and then the model weights converge, thereby training the machine learning model to solve a given task. In this example, the task is to predict whether an event will cause a non-negligible phase discontinuity. In the examples disclosed herein, when using a machine learning model, the machine learning model can be fixed and can correspond to a set of processing instructions.

[0126] In the examples disclosed herein, the machine learning model may reside in UE 106. This machine learning model may be trained to provide the predicted phase discontinuity as output. This could be a value indicating the magnitude of the phase discontinuity, an indication of whether the phase discontinuity is above or below a threshold, or any other suitable output.

[0127] The inputs provided to the machine learning model can include any inputs related to factors that may affect phase discontinuities. For example, the inputs to the machine learning model can include event parameters, such as TA parameters indicated by network node 102, UE HW temperature, signal BW, RF circuit state (hardware components may deviate from their calibration state over time, thus introducing phase discontinuities), historical curves of PA gain (historical curves may affect nonlinearity at the current time), or any other relevant factors.

[0128] Machine learning models can be trained to provide appropriate outputs related to phase discontinuity predictions. The type of output provided by a machine learning model may depend on the scenario and use case.

[0129] In some examples, the output of the machine learning model may be the calculated probability that one or more events cause a phase discontinuity. The probability that one or more events cause a phase discontinuity can be calculated based on a comparison of the predicted phase discontinuity with a threshold phase discontinuity. If the predicted phase shift after the event is greater than the threshold, then one or more events can be considered to have caused a phase discontinuity.

[0130] Threshold phase discontinuities can be configured by network nodes or defined in the specification. For example, threshold phase discontinuities can be indicated as a reporting condition in the configuration of network node 102. In this case, the threshold can be a fixed threshold. In other examples, threshold phase discontinuities can be dynamically indicated to UE 106 via DCI once the machine learning model is enabled. In such examples, threshold phase discontinuities may depend on the use case. For example, a stricter threshold can be assigned for OCC scenarios, while a more lenient threshold can be used for DMRS bundled scenarios.

[0131] In some examples, a threshold can be provided to UE 106 for comparison with the probability of a phase discontinuity. Based on this comparison, UE 106 can then signal a single bit 0 / 1 as a result. Using a single bit to report phase discontinuities reduces signaling overhead compared to the example where UE 106 can signal a probability. However, using a single bit to report phase discontinuities also reduces any flexibility for network node 102 to interpret the received probability by comparing it with other factors available only to network node 102.

[0132] Threshold phase discontinuity can be configured by the network node or defined in the specification. For example, the threshold phase discontinuity can be indicated as a reporting condition in the configuration of network node 102. In this case, the threshold can be a fixed threshold. In other examples, the threshold phase discontinuity can be dynamically indicated to UE 106 via DCI once the machine learning model is enabled. In such examples, the threshold phase discontinuity may depend on the use case. Network node 102 can adjust the threshold based on monitoring of machine learning model performance, parameter updates, or any other relevant factors. For example, in the case of OCC, a higher threshold can be used if the OCC size is 2 than in a scenario with an OCC size of 4.

[0133] In some examples, the output of the machine learning model can be a predicted value of the phase discontinuity. This can be reported directly to network node 102. This can also be reported directly to network node 102 by UE 106 without any processing by UE 106. For example, UE 106 does not need to determine whether the predicted phase discontinuity is higher or lower than a threshold. Reporting the predicted value of the phase discontinuity may increase signaling overhead, but it provides more information to network node 102 and may reduce feedback and signaling from network node 102. This additional information allows network node 102 to interpret the phase discontinuity in conjunction with other factors available only to network node 102. Furthermore, network node 102 can correct the phase discontinuity and restore link performance at the receiver.

[0134] In some examples, the machine learning model can predict phase discontinuities for individual events. If multiple events occur within a transmission, UE 106 can use the machine learning model to predict each event within that transmission. UE 106 can then perform an additional step to determine the cumulative phase discontinuity for the multiple events, or the cumulative probability of a non-negligible phase discontinuity occurring (i.e., the probability that at least one event will result in a non-negligible phase discontinuity). In other examples, the machine learning model can be configured to predict phase discontinuities for multiple events. The predictions for multiple events can be reported to network node 102 according to relevant reporting conditions.

[0135] When the prediction of phase discontinuities needs to consider multiple events, a prediction window can be indicated by the network node. The prediction window can be indicated explicitly or implicitly. It can be indicated via Radio Resource Control (RRC) signaling or DCI. In this case, UE 106 can send a single bit indicating the cumulative probability of phase discontinuities within the prediction window. In the OCC example, the prediction window can be based on the OCC period. In this case, once the OCC configuration is applied, UE 106 can determine the prediction window without the network node 102 explicitly signaling this information.

[0136] In some cases, machine learning models may not indicate the predicted phase discontinuity or its probability, but instead predict a clean duration within which the phase discontinuity is predicted to be below a threshold. That is, the machine learning model will predict a time period in which there is no significant phase discontinuity. The output of the machine learning model will be based on the probability that the phase discontinuity is less than the threshold within that duration.

[0137] Machine learning models can be trained using any suitable process. In some examples, the machine learning model can be developed on a server based on data collected from UE 106. Training data can be collected from UE 106 because UE 106 has a comprehensive understanding and statistics of the required input and actual output phase discontinuities at the time the event occurs. Therefore, feedback from network node 102 may not be needed in this case. In other examples, training data can be based on feedback from network node 102. If the training data is based on feedback from network node 102, then the training of the machine learning model can take into account the actual performance impact of any phase discontinuities. Based on this, if the performance degradation exceeds a threshold, the phase discontinuity is considered destructive (label 0). The measurement of performance degradation is performed by network node 102, and feedback is provided to the training entity in the form of 0 / 1. This type of training is scenario-dependent and KPI-related (related to the final performance).

[0138] This provides two types of training and development for machine learning models. The first type is a KPI-aware machine learning model. For this type of machine learning model, feedback from network node 102 regarding the performance impact of phase discontinuities is used. The machine learning model can then be trained to protect the performance measured by network node 102. The second type is a UE-centric machine learning model. For this type of machine learning model, no feedback from network node 102 is required, as the machine learning model is only trained to predict phase discontinuity values. The management of the predicted phase discontinuity values ​​is controlled by UE 106 and / or network node 102 during the inference phase.

[0139] Figure 5 An example machine learning model 500 is shown, which can be used in some examples. In this case, machine learning model 500 is a reinforcement learning model. Other types of models can be used in other examples.

[0140] The machine learning model 500 includes an agent 502 and an environment 504. Agent 502 is a decision-making entity that interacts with the environment 504. It is configured to observe the state of the environment 504, select actions, and receive feedback in the form of rewards or punishments. In the example disclosed, agent 502 may reside at UE 106 for the inference phase, while the training of model 500 may be performed offline.

[0141] Environment 504 represents an external system that interacts with agent 502. In this implementation, environment 504 represents a network and its dynamics. The environment may include the activities of UE 105, the hardware behavior of UE 106, network conditions, and any other relevant factors.

[0142] State 506 is a representation of environment 504 at a specific point in time. State 506 captures all the relevant information required for agent 502 to make decisions. In the examples of this disclosure, the state may include factors such as UE HW characteristics, signal bandwidth (BW), historical curves of PA gain, event parameter values, and / or any other suitable information. State 506 is provided to agent 502 as input.

[0143] Action 508 is a choice made by agent 502 to influence environment 504. Actions can be provided as outputs of agent 502. The set of possible actions available to agent 502 depends on the specific environment 504. In the examples disclosed herein, possible actions can be selected from an available set corresponding to different levels of phase discontinuity.

[0144] Reward 510 is the feedback signal provided to agent 502 by environment 504 after taking action 508 in a specific state. Reward 510 represents the immediate gain or cost associated with action 508. In this problem, the reward or penalty may include the degree of good or bad between the estimated phase discontinuity and the actual phase discontinuity:

[0145] Where f is a function, such as the Sigmoid function used to scale the independent variable in order to balance the effects of estimation error.

[0146] Figure 6 This demonstrates a method using machine learning models (e.g.) Figure 5 The method shown is the RL model. Figure 6 The example in the example uses a flow of an RL contextual gambling machine model based on the confidence upper bound (UCB) algorithm. Any suitable ML model and corresponding algorithm can be used.

[0147] In block 600, agent 502 initializes the algorithm-related parameters. These parameters may include the exploration parameter α, the regularization parameter λ, and the action count N for each action. a =0, eigenvector X a and parameter vector θ a The parameters used depend on the algorithm used and any other relevant factors.

[0148] In block 602, agent 502 receives state 506. State 506 may include event parameters and local inputs. State 506 is received at time t. Agent 502 uses the received state to construct a context vector x. t .

[0149] In block 604, agent 502 calculates the estimated reward, uncertainty (confidence interval), and UCB for each action available to agent 502. a,t Then the agent selects the one with the highest UCB. a,t action a t .

[0150] In block 606, UE 106 evaluates the actual phase discontinuity and calculates relevant indicators used to calculate the reward.

[0151] In block 608, agent 502 receives these indicators. In some examples, the indicators may be the actual value of the phase discontinuity or any other suitable information.

[0152] In block 610, agent 502 calculates the action a for the selected action. t Reward r tAnd update the parameters used for the selected action. Updating the parameters can include updating the feature matrix X. a θ a N a Update.

[0153] Agent 502 also caches the observed rewards for the selected action.

[0154] Figure 7 An example controller 700 is shown. The controller 700 may be located within user equipment 106 or network node 102, or any other suitable entity. The implementation of the controller 700 may be controller circuitry. The controller 700 may be implemented solely in hardware, some aspects may be implemented solely in software (including firmware), or it may be a combination of hardware and software (including firmware). The controller 700 may be provided as means for implementing this disclosure, or may be provided as part of means for implementing this disclosure.

[0155] like Figure 7 As shown, the controller 700 can be implemented using instructions capable of implementing hardware functions, for example, by using executable instructions of a computer program 706 in a general-purpose or special-purpose processor 702, the program can be stored on a machine-readable storage medium (disk, memory, etc.) and executed by the processor 702.

[0156] Processor 702 is configured to read data from memory 704 and write data to it. Processor 702 may also include an output interface and an input interface, wherein processor 702 outputs data and / or commands via the output interface and data and / or commands are input to processor 702 via the input interface.

[0157] Memory 704 stores instructions, programs 706, or code that, when loaded into processor 702, control the operation of the device. The instructions, programs 706, or code provide the logic and routines that enable the device to perform the methods shown in the figures. Processor 702 can load and execute the instructions, programs 706, or code by reading from memory 704.

[0158] In some examples, when controller 700 is located within user equipment 106, the controller therefore includes components for the following operations: Instruct network node 102 on the ability of 300 UEs 106 to predict phase discontinuities; Receive configuration from network node 102 for reporting phase discontinuity prediction results, the configuration including at least a reporting indication method and one or more reporting conditions; Perform 304 phase discontinuity prediction; and Based on the received configuration, determine whether 306 should report the results of the phase discontinuity prediction.

[0159] In some examples, when controller 700 is provided within network node 102, the controller therefore includes components for the following operations: Receive from UE 106 310 the ability of UE 106 to predict phase discontinuities; Send configuration 312 to UE 106 for reporting phase discontinuity prediction results, the configuration including at least a reporting indication method and one or more reporting conditions; and Receive a report from UE 106 indicating the results of a phase discontinuity prediction, wherein the report is based on the configuration.

[0160] Instructions, program 706, or code can reach the device via any suitable delivery mechanism 708. Delivery mechanism 708 can be, for example, a machine-readable medium, a computer-readable medium, a non-transitory computer-readable storage medium, a computer program product, a storage device, a recording medium (such as a read-only optical disc (CD-ROM) or digital versatile optical disc (DVD) or solid-state storage), or an article of manufacture that includes or tangibly embodies the computer program 706. The delivery mechanism can be a signal configured to reliably transmit the computer program 706. The device can propagate or transmit the computer program 706 as a computer data signal.

[0161] The term “non-transitory” as used in this article refers to a limitation on the medium itself (i.e., tangible, not signal), rather than a limitation on the persistence of data storage (e.g., RAM vs. ROM).

[0162] Computer program 706 may include computer program instructions for causing UE 106 to perform at least the following operations: Instruct network node 102 on the ability of 300 UEs 106 to predict phase discontinuities; Receive 302 configuration from network node 102 for reporting phase discontinuity prediction results, the configuration including at least a reporting indication method and one or more reporting conditions; Perform 304 phase discontinuity prediction; and Based on the received configuration, determine whether 306 should report the results of the phase discontinuity prediction.

[0163] Computer program 706 may include computer program instructions for causing network node 102 to perform at least the following operations: Receive from UE 106 310 the ability of UE 106 to predict phase discontinuities; Send configuration 312 to UE 106 for reporting phase discontinuity prediction results, the configuration including at least a reporting indication method and one or more reporting conditions; and Receive a report from UE 106 indicating the results of the phase discontinuity prediction, where the report is based on the configuration.

[0164] Computer program instructions may be included in computer programs, non-transitory computer-readable media, computer program products, and machine-readable media. In some, but not all, examples, computer program instructions may be distributed across multiple computer programs.

[0165] Although memory 704 is illustrated as a single component / circuit system, it can be implemented as one or more independent components / circuits, some or all of which may be integrated / removable and / or provide permanent / semi-permanent / dynamic / cached storage.

[0166] Although processor 702 is illustrated as a single component / circuit system, it can be implemented as one or more independent components / circuits, some or all of which may be integrated / removable. Processor 702 can be a single-core or multi-core processor.

[0167] References to “computer-readable storage medium,” “computer program product,” “tangible computer program,” or “controller,” “computer,” “processor,” etc., should be understood to encompass not only computers with different architectures (such as single / multiprocessor architectures and sequential (von Neumann) / parallel architectures) but also special-purpose circuits, such as field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), signal processing devices, and other processing circuit systems, including quantum processing circuit systems. References to computer programs, instructions, code, etc., should be understood to encompass software used with programmable processors or firmware (e.g., programmable content of hardware devices, whether instructions for processors or configuration settings for fixed-function devices, gate arrays, or programmable logic devices, etc.).

[0168] As used in this application, the term "circuit system" may refer to one or more or all of the following: (a) Pure hardware circuit implementation (e.g., implementation in analog and / or digital circuit systems only), and (b) A combination of hardware circuitry and software, such as (if applicable): (i) A combination of (multiple) analog, digital, and / or quantum hardware circuits and software / firmware, and (ii) Any or all portions of a hardware processor (including multiple digital and / or quantum processors) combined with multiple software and memory, which work together to enable a device (e.g., a mobile device, computing device, or server) to perform various functions, and (c) Any or all parts of (multiple) hardware circuits (e.g., (multiple) microprocessors and / or (multiple) quantum processors) that require software (e.g. firmware) to function, but which may not exist when not needed to run.

[0169] The definition of "circuit system" applies to all uses of the term in this application, including in any claim. As a further example, as used in this application, the term "circuit system" also covers implementations of hardware circuitry or processors (or processors) or a portion thereof and their accompanying software and / or firmware. For example, if applicable to claim elements, the term "circuit system" also covers baseband integrated circuits or processor integrated circuits for use in mobile devices or servers, cellular network devices or other computing or networking devices.

[0170] The blocks shown in the diagram may represent steps in a method and / or code segments in computer program 706. The illustration of a specific order of blocks does not necessarily imply a necessary or preferred order; the order and arrangement of blocks can vary. Furthermore, some blocks may be omitted.

[0171] When describing a structural feature, it can be replaced by means of one or more functions that perform that structural feature, whether those functions are explicit or implicit descriptions.

[0172] According to one example of this disclosure, the device can be located in an electronic device, such as a mobile terminal. However, it should be understood that the mobile terminal is merely an illustrative example of an electronic device that can benefit from implementations of this disclosure, and therefore the scope of this disclosure should not be limited thereto. While in some implementation examples the device can be located in a mobile terminal, other types of electronic devices, such as, but not limited to, mobile communication devices, handheld portable electronic devices, wearable computing devices, portable digital assistants (PDAs), pagers, mobile computers, desktop computers, televisions, gaming devices, laptops, cameras, video recorders, GPS devices, and other types of electronic systems, can readily adopt the examples of this disclosure. Furthermore, regardless of whether the devices are intended to provide mobility, they can readily adopt the examples of this disclosure.

[0173] The term "include" as used in this document has an inclusive rather than exclusive meaning. That is, any reference to X including Y indicates that X may include only one Y or may include multiple Ys. If the intention to use "include" with an exclusive meaning is to specify in the context by referring to "includes only one..." or using "consisting of...".

[0174] In this specification, the terms “connection,” “coupling,” and “communication,” and their derivatives, mean operational connection / coupling / communication. It should be understood that any number or combination of intermediate components (including no intermediate components) may exist to provide direct or indirect connection / coupling / communication. Any such intermediate component may include hardware and / or software components.

[0175] As used herein, the term “determine / decide” (and its grammatical variations) may include, but is not limited to: calculation, operation, processing, derivation, measurement, investigation, identification, lookup (e.g., searching in a table, database, or other data structure), ascertainment, etc. Furthermore, “determine” may include receiving (e.g., receiving information), accessing (e.g., accessing data in memory), obtaining, etc. Additionally, “determine / decide” may include resolving, selecting, picking, establishing, etc.

[0176] Various examples are referenced in this specification. Descriptions of features or functions in examples indicate that such features or functions exist in that example. The use of the terms "example," "for example," "may," or "possibly" in the text, whether explicitly stated or not, indicates that such features or functions exist at least in the described example, whether or not they are described as examples, and that they may, but not necessarily, exist in some or all other examples. Therefore, "example," "for example," "may," or "possibly" refers to a specific instance within an example category. The attributes of that instance may be attributes of only that instance, or attributes of the category or a subcategory that includes some but not all instances within that category. Thus, it is implicitly disclosed that a feature described with reference to one example but not another may, where possible, be used as part of a working combination in that other example, but is not necessarily required to be used in that other example.

[0177] As used in this article, “at least one of the following:” and “at least one” and similar wording, where a list of two or more elements is connected by “and” or “or”, means at least any one element, or at least any two or more elements, or at least all elements.

[0178] Although examples have been described with reference to various examples in the preceding paragraphs, it should be understood that modifications may be made to the given examples without departing from the scope of the claims.

[0179] The features described above can be used in combinations other than those explicitly described above.

[0180] Although the functions have been described with reference to certain features, these functions can be performed by other features, whether or not they are described.

[0181] A description of features (e.g., means or components of means) configured to perform a function or used to perform a function should also be considered as disclosing a method for performing that function. For example, a description of means configured to perform one or more actions or used to perform one or more actions should also be considered as disclosing a method for performing the one or more actions using or not using the means.

[0182] Although the features have been described with reference to some examples, these features may also exist in other examples, whether or not they are described.

[0183] The terms “a,” “an,” or “that” as used in this document have an inclusive rather than exclusive meaning. That is, any statement that X contains one / an / that Y indicates that X may contain only one Y or more Ys, unless the context clearly indicates the opposite. If “a,” “an,” or “that” is intended to be used in an exclusive sense, it will be made clear in the context. In some cases, “at least one” or “one or more” may be used to emphasize the inclusive meaning, but the absence of these terms should not be inferred to have any exclusive meaning.

[0184] When a claim refers to a feature (or combination of features), it means the feature (or combination of features) itself, as well as features that achieve substantially the same technical effect (equivalent features). Equivalent features include, for example, those variant features that achieve substantially the same result in substantially the same manner. Equivalent features include, for example, those features that perform substantially the same function and achieve substantially the same result in substantially the same manner.

[0185] In this specification, references are made to various examples that use adjectives or adjective phrases to describe the example characteristics. Such a description of an example characteristic means that the characteristic exists exactly as described in some examples and substantially as described in other examples.

[0186] As used herein, the terms “the at least one” and “the one or more” mean “any one of the at least one” and “any one of the one or more”, respectively.

[0187] The foregoing description illustrates some examples of this disclosure; however, those skilled in the art will understand that alternative structural and methodological features may exist that provide equivalent functionality to the specific examples of such structures and features described above, and have been omitted from the foregoing description for the sake of brevity and clarity. Nevertheless, the foregoing description should be understood to implicitly include references to such alternative structural and methodological features that provide equivalent functionality, unless such alternative structural or methodological features are expressly excluded in the foregoing description of the examples of this disclosure.

[0188] Despite efforts made in the foregoing specification to draw attention to features deemed important, the applicant may seek protection by means of the claims for any patentable feature or combination of features shown in the foregoing and / or figures herein, whether or not they have been emphasized.

Claims

1. A user equipment (UE), comprising: At least one processor; as well as At least one memory stores instructions that, when executed by the at least one processor, cause the UE to perform at least the following operations: Indicate the UE's ability to predict phase discontinuities to the network node; The network node receives a configuration for reporting phase discontinuity prediction results, the configuration including at least a reporting indication method and one or more reporting conditions; Perform phase discontinuity prediction; as well as Based on the received configuration, determine whether to report the results of the phase discontinuity prediction.

2. The UE of claim 1, wherein the phase discontinuity prediction is performed using a machine learning model.

3. The UE according to claim 1 or 2, wherein the one or more reporting conditions include one or more thresholds for the probability of phase discontinuity.

4. The UE of claim 3, wherein different thresholds are associated with different use cases.

5. The UE according to claim 1 or 2, wherein the configuration is received via at least one of the following: Radio resource control signaling; and Downlink control information.

6. The UE according to claim 1 or 2, wherein the phase discontinuity prediction involves one of the following: The probability that a single event causes a phase discontinuity; and The probability that multiple events cause a cumulative phase discontinuity.

7. The UE according to claim 1 or 2, wherein the reporting indication method includes one of the following: Bits indicating whether the reporting conditions have been met; A value indicating the probability that one or more events cause a phase discontinuity; The value of the result indicating the phase discontinuity prediction; and The indication of the duration for which the phase discontinuity satisfies the reporting conditions.

8. The UE according to claim 1 or 2, wherein the memory and computer program are further configured to receive an indication of an event parameter and one or more thresholds for the probability of a phase discontinuity associated with the event parameter.

9. The UE according to claim 1 or 2, wherein the one or more reporting conditions received from the network node include: The first reporting condition is used for the first scenario, and the second reporting condition is used for the second scenario.

10. A network node, comprising: At least one processor; as well as At least one memory stores instructions that, when executed by the at least one processor, cause the network node to perform at least the following operations: The ability of the UE to receive predictions of phase discontinuities from the UE; Send the configuration for reporting phase discontinuity prediction results to the UE, the configuration including at least a reporting indication method and one or more reporting conditions; as well as The UE receives a report indicating the result of the phase discontinuity prediction, wherein the report is based on the configuration.

Images