Measurement reports for use in handover procedures
By allowing User Equipment to dynamically adjust measurement parameters and execution conditions using machine learning, the solution enhances handover efficiency and reduces Radio Link Failures in wireless networks, addressing the limitations of static parameters in existing conditional handover procedures.
Patent Information
- Application Number
- PCT/EP2023/062844
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-12
- Publication Date
- 2024-11-21
AI Technical Summary
Conditional handover procedures in wireless networks face challenges due to static measurement parameters, leading to Radio Link Failures (RLF) when mobile User Equipment (UE) moves between cells, as these parameters cannot be dynamically adjusted to adapt to changing conditions.
The UE is enabled to generate and transmit measurement reports that include dynamic adjustments of tunable parameters, such as measurement objects and reporting configurations, using machine learning models to determine optimal values, allowing for adaptive measurement configurations and execution conditions during handovers.
This approach reduces the likelihood of RLF by enabling dynamic adjustment of measurement parameters, improving handover efficiency and reducing power consumption by optimizing the measurement and reporting processes.
Smart Images

Figure EP2023062844_21112024_PF_FP_ABST
Abstract
Description
[0001] TITLE
[0002] MEASUREMENT REPORTS FOR USE IN HANDOVER PROCEDURES
[0003] TECHNOLOGICAL FIELD
[0004] Examples of the disclosure relate to measurement reports for use in handover procedures. Some relate to measurement reports for use in handover procedures where a User Equipment has control over at least some of the measurements that are performed and reported.
[0005] BACKGROUND
[0006] Conditional handover based mobility schemes can be used to handover a User Equipment from a source network node (such as a gNB) to a target network node when an execution condition is satisfied. The UE can be configured by the network to perform measurements to assist the network in determining candidate target cells and implementing the handover procedure.
[0007] BRIEF SUMMARY
[0008] According to various, but not necessarily all, examples of the disclosure there is provided a User Equipment comprising: means for generating a measurement report wherein the measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the User Equipment to obtain the measurement results; and means for transmitting the measurement report.
[0009] The User Equipment may comprise means for receiving an indication of one or more tunable parameters that represent parameters of the measurements that can be adjusted. The User Equipment may comprise means for determining a new value for one or more of the tunable parameters represented in the received indication.
[0010] The User Equipment may comprise means for using a machine learning model to determine one or more of the new values for one or more of the tunable parameters.
[0011] The User Equipment may comprise means for transmitting an estimated measurement configuration to enable a network check of one or more of the new values for one or more of the tunable parameters.
[0012] The tunable parameters may comprise at least one of: a measurement object; a reporting configuration.
[0013] The measurement object may comprise any one or more of: Synchronization Signal Block Absolute Radio Frequency Channel Number; Sub Carrier Spacing; Synchronization Signal Block Measurement Timing Configuration; Synchronization Signal Block / Channel State Information - Reference Signal blocks to average; Measurement Object offset; Reference Signal Configuration; Reference Signal Consolidation Threshold and number of Reference Signal to consolidate; Quality Configuration Index.
[0014] The reporting configuration may comprise any one or more of: choice of periodical or event triggered reporting; to additionally also report Cell Global Identity; to additionally also report System Frame Number and Frame Timing Difference; A3 / A5 offsets; Time to Trigger; Hysteresis; Reference Signal type to be reported; Reporting intervals; Reporting amounts; Maximum number of cells to report; Whether to include beam measurements; Location information; Measurements from other sensors; Interference reporting parameters.
[0015] The User Equipment may comprise means for determining a recommendation of a tunable execution condition that is to be applied during execution of a handover and means for transmitting the recommendation of the tunable execution condition. The User Equipment may comprise means for transmitting an indication of an execution condition that has been used by the User Equipment during the execution of a handover.
[0016] The indication of the execution condition that has been used by the User Equipment may be transmitted in a handover complete message.
[0017] The measurement report may be used during a preparation phase of a conditional handover procedure.
[0018] According to various, but not necessarily all, examples of the disclosure there may be provided a method comprising: generating a measurement report wherein the measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the User Equipment to obtain the measurement results; and transmitting the measurement report.
[0019] According to various, but not necessarily all, examples of the disclosure there may be provided a computer program comprising instructions which, when executed by a User Equipment cause the User Equipment to perform: generating a measurement report wherein the measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the User Equipment to obtain the measurement results; and transmitting the measurement report.
[0020] According to various, but not necessarily all, examples of the disclosure there may be provided a Network Entity comprising: means for receiving a measurement report from a User Equipment wherein the measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the User Equipment to obtain the measurement results; and means for using information from the measurement report to perform handover. The Network Entity may comprise means for transmitting an indication of one or more tunable parameters that represent parameters of the measurements that can be adjusted to the User Equipment.
[0021] The Network Entity may comprise means for receiving an estimated measurement configuration to enable a network check of one or more of the new values for one or more of the tunable parameters.
[0022] The Network Entity may comprise means for receiving a recommendation of a tunable execution condition that is to be applied during execution of a handover; and means for using the recommendation of the tunable execution condition to execute a handover.
[0023] The Network Entity may comprise means for receiving an indication of an execution condition that has been used by the User Equipment during the execution of a handover.
[0024] The indication of the execution condition that has been used by the User Equipment may be transmitted in a handover complete message.
[0025] The Network Entity may comprise means for storing at least one of versions of one or more tunable parameters that have been used by the User Equipment to perform measurements and tunable execution conditions that have been used to execute a handover; and means for using the stored versions of one or more tunable parameters that have been used by the User Equipment to perform measurements and / or tunable execution conditions that have been used to execute a handover and / or for training a machine learning model.
[0026] The measurement report may be used during a preparation phase of a conditional handover procedure.
[0027] According to various, but not necessarily all, examples of the disclosure there may be provided a method comprising: receiving a measurement report from a User Equipment wherein the measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the User Equipment to obtain the measurement results; and using information from the measurement report to perform handover.
[0028] According to various, but not necessarily all, examples of the disclosure there may be provided a computer program comprising instructions which, when executed by a Network Entity cause the Network Entity to perform: receiving a measurement report from a User Equipment wherein the measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the User Equipment to obtain the measurement results; and using information from the measurement report to perform handover.
[0029] According to various, but not necessarily all, examples of the disclosure there may be provided a User Equipment comprising: means for determining a recommendation of a tunable execution condition that is to be applied during execution of a handover; and means for transmitting the recommendation of the tunable execution condition to enable execution conditions of a network to be updated.
[0030] The User Equipment may comprise means for receiving an indication of one or more tunable parameters that represent parameters of the measurements that can be adjusted and determining the recommendation of the tunable execution condition based on one or more measurements made using parameters that have been adjusted in accordance with the indication.
[0031] The User Equipment may comprise means for using a machine learning model to determine one or more of the recommendations for the tunable execution condition.
[0032] The User Equipment may comprise means for generating a measurement report wherein the measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the User Equipment to obtain the measurement results; and means for transmitting the measurement report. The User Equipment may comprise means for transmitting an estimated measurement configuration to enable a network check of one or more of the new values for one or more of the tunable parameters.
[0033] The tunable parameters may comprise at least one of: a measurement object; a reporting configuration.
[0034] The measurement object may comprise any one or more of: Synchronization Signal Block Absolute Radio Frequency Channel Number; Sub Carrier Spacing; Synchronization Signal Block Measurement Timing Configuration; Synchronization Signal Block / Channel State Information - Reference Signal blocks to average; Measurement Object offset; Reference Signal Configuration; Reference Signal Consolidation Threshold and number of Reference Signal to consolidate; Quality Configuration Index.
[0035] The reporting configuration may comprise any one or more of: choice of periodical or event triggered reporting; to additionally also report Cell Global Identity; to additionally also report System Frame Number and Frame Timing Difference; A3 / A5 offsets; Time to Trigger; Hysteresis; Reference Signal type to be reported; Reporting intervals; Reporting amounts; Maximum number of cells to report; Whether to include beam measurements; Location information; Measurements from other sensors; Interference reporting parameters.
[0036] The User Equipment may comprise means for transmitting an indication of an execution condition that has been used by the User Equipment during the execution of a handover.
[0037] The indication of the execution condition that has been used by the User Equipment may be transmitted in a handover complete message.
[0038] According to various, but not necessarily all, examples of the disclosure there is provided a method comprising: determining a recommendation of a tunable execution condition that is to be applied during execution of a handover; and transmitting the recommendation of the tunable execution condition to enable execution conditions of a network to be updated.
[0039] According to various, but not necessarily all, examples of the disclosure there is provided a computer program comprising instructions which, when executed by a User Equipment cause the User Equipment to perform: determining a recommendation of a tunable execution condition that is to be applied during execution of a handover; and transmitting the recommendation of the tunable execution condition to enable execution conditions of a network to be updated.
[0040] According to various, but not necessarily all, examples of the disclosure there is provided a Network Entity comprising: means for receiving a recommendation of a tunable execution condition that is to be applied during execution of a handover; and means for using the recommendation of the tunable execution condition to execute a handover.
[0041] The Network Entity may comprise means for transmitting an indication of one or more tunable parameters that represent parameters of the measurements that can be adjusted and receiving the recommendation of the tunable execution conditions in response.
[0042] The Network Entity may comprise means for receiving a measurement report wherein the measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the User Equipment to obtain the measurement results; and means for using information from the measurement report to perform handover.
[0043] The Network Entity may comprise means for receiving an estimated measurement configuration and performing a network check of one or more of the new values for one or more of the parameters. The Network Entity may comprise means for receiving an indication of an execution condition that has been used by the User Equipment during the execution of a handover.
[0044] The indication of the execution condition that has been used by the User Equipment may be transmitted in a handover complete message.
[0045] According to various, but not necessarily all, examples of the disclosure there is provided a method comprising: receiving a recommendation of a tunable execution condition that is to be applied during execution of a handover; and using the recommendation of the tunable execution condition to execute a handover.
[0046] According to various, but not necessarily all, examples of the disclosure there is provided a computer program comprising instructions which, when executed by a Network Entity cause the Network Entity to perform: receiving a recommendation of a tunable execution condition that is to be applied during execution of a handover; and using the recommendation of the tunable execution condition to execute a handover.
[0047] While the above examples of the disclosure and optional features are described separately, it is to be understood that their provision in all possible combinations and permutations is contained within the disclosure. It is to be understood that various examples of the disclosure can comprise any or all of the features described in respect of other examples of the disclosure, and vice versa. Also, it is to be appreciated that any one or more or all of the features, in any combination, may be implemented by / comprised in / performable by an apparatus, a method, and / or computer program instructions as desired, and as appropriate.
[0048] BRIEF DESCRIPTION
[0049] Some examples will now be described with reference to the accompanying drawings in which:
[0050] FIG. 1 shows an example network; FIGS. 2A and 2B show example methods;
[0051] FIGS. 3A and 3B show example methods;
[0052] FIG. 4 shows an example signaling chart;
[0053] FIG. 5 shows an example use case scenario;
[0054] FIG. 6 shows an example ML model structure;
[0055] FIGS. 7A and 7B show an example ML model input sample matrix and output vector;
[0056] FIG. 8 shows a relation between an input sample and an output vector; and
[0057] FIG. 9 shows an example controller.
[0058] The figures are not necessarily to scale. Certain features and views of the figures can be shown schematically or exaggerated in scale in the interest of clarity and conciseness. For example, the dimensions of some elements in the figures can be exaggerated relative to other elements to aid explication. Corresponding reference numerals are used in the figures to designate corresponding features. For clarity, all reference numerals are not necessarily displayed in all figures.
[0059] DEFINITIONS
[0060] CGI Cell Global Identity
[0061] CHO Conditional Handover
[0062] CSI-RS Channel State Information - Reference Signal
[0063] E-UTRA Evolved Universal Mobile Telecommunications System (UMTS)
[0064] Terrestrial Radio Access gNB NR base station
[0065] HO Handover
[0066] LSTM Long Short-Term Memory
[0067] ML Machine Learning
[0068] MO Measurement Object
[0069] NR New Radio
[0070] O-RAN Open Radio Access Network
[0071] PCell Primary Cell (mobility anchor for the primary cell group in dual connectivity)
[0072] PSCell Primary and Secondary Cell (mobility anchor for the secondary cell group in dual connectivity)
[0073] RAN Radio Access Network RLF Radio Link Failure
[0074] RS Reference Signal
[0075] RSRP Reference Signal Received Power
[0076] SCS Sub Carrier Spacing
[0077] SFTD System Frame Number and Frame Timing Difference
[0078] SIM Subscriber Identity Module
[0079] SMTC SSB Measurement Timing Configuration
[0080] SSB ARFCN Synchronization Signal Block Absolute Radio Frequency Channel
[0081] Number
[0082] SS-RSRP Secondary Signal- RSRP
[0083] TTT Time to Trigger
[0084] UE User Equipment
[0085] DETAILED DESCRIPTION
[0086] Fig. 1 illustrates an example of a network 100 such as a 5G NR network. The network 100 comprises a plurality of terminal apparatus 110 and a plurality of network entities 120, 130. The network entities 120, 130 can comprise one or more node apparatus 120 that can be configured to communicate with the terminal apparatus 110. The network entities can also comprise one or more core network apparatus 130. The one or more core network apparatus 130 communicate with the node apparatus 120. In some examples the one or more core network apparatus 130 communicate with the terminal apparatus 110.
[0087] The one or more core network apparatus 130 can, in some examples, communicate with each other. The one or more node apparatus 120 can, in some examples, communicate with each other.
[0088] The network 100 can be a cellular network comprising a plurality of cells 122 each served by a node apparatus 120. In this example, the interface between the terminal apparatus 110 and a node apparatus 120 defining a cell 122 is a wireless interface 124.
[0089] The node apparatus 120 comprises one or more cellular radio transceivers. The terminal apparatus 110 comprises one or more cellular radio transceivers. In the example illustrated the cellular network 100 is a Third Generation Partnership Project (3GPP) network in which the terminal apparatus 110 are user equipment (UE) and the node apparatus 120 can be access nodes such as base stations (gNB). A 3GPP network is a communication network that applies at least one 3GPP standard. Other types of networks could be used in other examples.
[0090] The term ‘user equipment’ is used to designate mobile equipment comprising a smart card for authentication / encryption etc. such as a Subscriber Identity Module (SIM). In some examples the term ‘user equipment’ is used to designate mobile equipment comprising circuitry embedded as part of the user equipment for authentication / encryption such as software SIM.
[0091] The node apparatus 120 can be any suitable base station. A base station is an access node. It can be a network entity responsible for radio transmission and reception in one or more cells to or from the UE 110. The node apparatus 120 can be a network element in a Radio Access Network (RAN), an Open-Radio Access Network (O-RAN), a E-UTRA (Evolved Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access) network, or any other suitable type of network.
[0092] The core network apparatus 130 can be part of a core network. The core network apparatus 130 can be configured to manage functions relating to connectivity for the UEs 110. For example, the core network apparatus 130 can be configured to manage functions such as connectivity, mobility, authentication, authorization and / or other suitable functions.
[0093] In the example of Fig. 1 the core network apparatus 130 is shown as a single entity. In some examples the core network apparatus 130 could be distributed across a plurality of entities. For example, the core network apparatus 130 could be cloud based or distributed in any other suitable manner.
[0094] The network 100 can be a 4G or 5G network, for example. It can for example be a New Radio (NR) network that uses gNB or eNB as access nodes 120. New Radio is one term used by 3GPP to refer to 5G technology. In such cases the node apparatus 120 can comprise base stations (gNBs) 120 configured to provide user plane and control plane protocol terminations towards the UE 110 and / or to perform any other suitable functions. The gNBs 120 are interconnected with each other by means of any suitable interface 126. The gNBs are also connected by means of the N2 interface 128 to the core network apparatus 130. Other types of networks and interfaces could be used in other examples. Other types of networks could comprise next generation mobile and communication network, for example, a 6G network.
[0095] Conditional handover procedures can be used to handover a UE 110 from a Source gNB 120 to a target gNB 120 when an execution condition is satisfied. The UE 110 can be configured to perform measurements to determine if an execution condition is satisfied. Measurement parameters such as objects to be measured, the reporting configurations for the measurements and the execution conditions can all be set by the gNB 120. These can be static parameters in that they do not change over time. The parameters that have been sent by the gNB 120 cannot be adapted by the UE 110.
[0096] These static parameters can lead to problems. For example, a mobile UE 110 can encounter an anomalous situation while it is moving between cells. This can be due to improper or suboptimal measurement parameters. This can lead to Radio Link Failure (RLF) or a recovery action (such as, CHO fallback to a target cell ignoring the execution condition) which could be avoided. For instance, a UE 110, could be able to avoid source PCell (Primary Cell) or PSCell (primary and Secondary Cell) RLF by adapting the configuration of one or more of the measurement parameters.
[0097] Examples of the disclosure address this issue by enabling dynamic adjustment of one or more of the measurement parameters. The measurement parameters for which dynamic adjustment can be enabled can comprise measurement objects, reporting configuration, execution conditions, or any other suitable parameters.
[0098] Figs. 2A and 2B show example methods that could be implemented in examples of the disclosure. The method of Fig. 2A could be implemented by a UE 110. The method of Fig. 2B is a corresponding method that could be implemented by a network entity such as a gNB 120. The respective methods can be performed as part of a conditional handover. The respective methods can be performed as part of a conditional handover that is assisted by machine learning. The method of Fig. 2A comprises, at block 200, generating a measurement report. The measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the UE 110 to obtain the measurement results.
[0099] The measurement report can be used during a preparation phase of a conditional handover procedure.
[0100] To enable the measurement report to be generated, the UE 110 can be configured to receive an indication of one or more tunable parameters that represent parameters of the measurements that can be adjusted. The indication can be received from a gNB 120. The indication can provide the UE 110 with control to dynamically adjust one or more of the measurement parameters that have previously been set by the gNB 120. In some examples the indication can provide the UE 110 with control to dynamically adjust an execution condition for triggering a handover. The handover could be triggered suing an execution phase of a CHO.
[0101] When the UE 110 has received such an indication, the UE 110 can then determine a new value for one or more of the tunable parameters represented in the received indication. Any suitable means or processes can be used to determine the new values for the tunable parameters. In some examples a machine learning model can be used to determine one or more of the new values for one or more of the tunable parameters.
[0102] The new values of the measurement parameters can then be used by the UE 110 to perform the measurements. The measurement reports therefore not only contain the measurement result but also a version of the tunable parameters that have been used to obtain the results.
[0103] At block 202 the method comprises transmitting the measurement report. The measurement report can be transmitted to a gNB 120 to enable information in the measurement report to be used to execute a handover.
[0104] In some examples the method can also comprise transmitting an estimated measurement configuration to enable a network check of one or more of the new values for one or more of the tunable parameters. The estimated measurement configuration can comprise an indication of the measurement parameters that are to be used. The network check can determine if the new values are within a permitted range or threshold.
[0105] The tunable parameters that can be adjusted can comprise at least one of: a measurement object, a reporting configuration, an execution condition, or any other suitable parameter.
[0106] The measurement object could comprise any one or more of: Synchronization Signal Block Absolute Radio Frequency Channel Number (SSB ARFCN), Sub Carrier Spacing (SCS), Synchronization Signal Block Measurement Timing Configuration (SMTC), Synchronization Signal Block (SSB) / Channel State Information - Reference Signal (CSI-RS) blocks to average, Measurement Object (MO) offset; Reference Signal (RS) Configuration; RS Consolidation Threshold and number of RS to consolidate, Quality Configuration Index, or any other suitable objects.
[0107] The reporting configuration could comprise any one or more of: choice of periodical or event triggered reporting; to additionally also report Cell Global Identity (CGI); to additionally also report System Frame Number and Frame Timing Difference (SFTD); A3 / A5 offsets, Time to Trigger (TTT), Hysteresis, RS type to be reported, Reporting intervals, Reporting amounts, Maximum number of cells to report, Whether to include beam measurements, Location information, Measurements from other sensors, Interference reporting parameters, or any other suitable configurations.
[0108] In some examples the UE 110 can be configured to determine a recommendation of a tunable execution condition that is to be applied during execution of a handover. The UE 110 can use the new versions of the tunable parameters to make measurements to determine the recommendation of the tunable execution condition. The UE 110 can also be configured to transmit the recommendation of the tunable execution condition. The recommendation of the tunable execution condition can be transmitted to the gNB 120 so that the recommendation of the tunable execution condition can be used to execute a handover and / or to update the execution conditions of the network. The recommendation of the tunable execution condition can be a tunable execution condition that has been used by the UE 110 during the execution of a handover. In such cases the UE 110 can therefore be configured to transmit an indication of an execution condition that has been used by the UE 110 during the execution of a handover. The indication of the execution condition that has been used by the UE 110 can be transmitted in a handover complete message or any other suitable message.
[0109] The method of Fig. 2B corresponds to the method of Fig. 2A. The method of Fig. 2B can be implemented by a gNB 120 that is in communication with a UE 110 that is implementing the method of Fig. 2A. The method of Fig. 2B comprises, at block 204, receiving a measurement report from a UE 110. The measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the UE 110 to obtain the measurement results.
[0110] The measurement report can be used during a preparation phase of a conditional handover procedure.
[0111] In order to enable the UE 110 to generate the measurement report, the gNB 120 can be configured to transmit an indication of one or more tunable parameters that represent parameters of the measurements that can be adjusted. The indication can be transmitted to the UE 110 that performs the measurements. The indication can provide the UE 110 with control to dynamically adjust one or more of the measurement parameters that have previously been set by the gNB 120.
[0112] When the UE 110 has received such an indication, the UE 110 can then determine a new value for one or more of the tunable parameters represented in the received indication. Any suitable means or processes can be used to determine the new values for the tunable parameters. In some examples a machine learning model can be used to determine one or more of the new values for one or more of the tunable parameters.
[0113] The new values of the measurement parameters can then be used by the UE 110 to perform the measurements. The measurement report therefore not only contains the measurement results but also a version of the tunable parameters that have been used to obtain the results. The method comprises, at block 206, using information from the measurement report to perform handover.
[0114] In some examples the method can comprise receiving an estimated measurement configuration to enable a network check of one or more of the new values for one or more of the tunable parameters. The estimated measurement configuration can comprise an indication of the measurement parameters that have been recommended by the UE 110. The network check can determine if the new values are within a permitted range or threshold.
[0115] The gNB 120 can also be configured to receive a recommendation of a tunable execution condition that is to be applied during execution of a handover. The gNB can also be configured to use the recommendation of the tunable execution condition to execute a handover. In some examples the recommendation of the tunable execution condition could be stored by the network and / or used to update or train machine learning models for the network.
[0116] The recommendation of the tunable execution condition can be a tunable execution condition that has been used by the UE 110 during the execution of a handover. In such cases the gNB 120 can therefore be configured to receive an indication of an execution condition that has been used by the UE 110 during the execution of a handover. The indication of the execution condition that has been used by the UE 110 can be received in a handover complete message or any other suitable message.
[0117] In some examples the gNB 120 can be configured to store versions of one or more tunable parameters that have been used by the UE 110 to perform measurements. For instance, the gNB 120 can be configured to extract the indications of the versions of one or more tunable parameters that have been used by the UE 110 to obtain the measurement result and enable this information to be stored. This information can be stored so that it can be used in the execution of handovers. For instance, it can be used for training or updating machine learning models that are used to assist handovers. This information can be stored in a network database or any other suitable location. In some examples the gNB 120 can be configured to store the tunable execution conditions that have been used to execute a handover. The stored tunable execution conditions can be used to execute a handover. For instance, the recommended execution conditions can be used for training or updating machine learning models that are used to assist handovers. The execution conditions can be stored in a network database or in any other suitable location.
[0118] Figs. 3A and 3B show example methods that could be implemented in examples of the disclosure. The method of Fig. 3A could be implemented by a UE 110. The method of Fig. 3B is a corresponding method that could be implemented by a network entity such as a gNB 120. The respective methods can be performed as part of a conditional handover. The respective methods can be performed as part of a conditional handover that is assisted by machine learning.
[0119] The method of Fig. 3A comprises, at block 300, determining a recommendation of a tunable execution condition that is to be applied during execution of a handover.
[0120] To enable the tunable execution condition to be recommended, the UE 110 can be configured to receive an indication of one or more tunable parameters that represent parameters of the measurements that can be adjusted. The indication can be received from a gNB 120. The indication can provide the UE 110 with control to dynamically adjust one or more of the measurement parameters and / or execution conditions that have previously been set by the gNB 120. The indication can provide the UE 110 with control to dynamically adjust an execution condition for triggering a handover.
[0121] When the UE 110 has received such an indication the UE 110 can then determine a new value for one or more of the tunable parameters represented in the received indication and use the new values of the measurement parameters to perform the measurements. The UE 110 can also recommend a tunable execution parameter based on the tuned parameters and / or the measurements made using the new parameters.
[0122] In some examples the recommendation of the tunable execution condition can comprise an execution condition that has been used by the UE 110 during the execution of a handover. In such cases an indication of the execution condition that has been used by the UE 110 can be transmitted in a handover complete message or any other suitable message.
[0123] At block 302 the method comprises transmitting the recommendation of the tunable execution condition to enable execution conditions of a network to be updated. For instance, the tunable execution condition could be used to execute handovers, could be stored in a network database for future use, could be used for training or updating a machine learning program and / or for any other suitable purpose.
[0124] In some examples a machine learning model can be used to determine one or more of the recommendations for the tunable execution condition.
[0125] The UE 110 can also be configured to generate a measurement report wherein the measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the UE 110 to obtain the measurement results. The UE 110 can be configured to transmit the measurement report. The measurement report can be transmitted to the gNB 120.
[0126] In some examples the UE 110 can also be configured to transmit an estimated measurement configuration to enable a network check of one or more of the new values for one or more of the tunable parameters.
[0127] The tunable parameters can comprise at least one of: a measurement object, a reporting configuration, an execution condition, or any other suitable parameter.
[0128] The measurement object could comprise any one or more of: Synchronization Signal Block Absolute Radio Frequency Channel Number (SSB ARFCN), Sub Carrier Spacing (SCS), Synchronization Signal Block Measurement Timing Configuration (SMTC), Synchronization Signal Block (SSB) / Channel State Information - Reference Signal (CSI-RS) blocks to average, Measurement Object (MO) offset; Reference Signal (RS) Configuration; RS Consolidation Threshold and number of RS to consolidate, Quality Configuration Index or any other suitable objects.
[0129] The reporting configuration could comprises any one or more of: choice of periodical or event triggered reporting; to additionally also report Cell Global Identity (CGI); to additionally also report System Frame Number and Frame Timing Difference (SFTD); A3 / A5 offsets, Time to Trigger (TTT), Hysteresis, RS type to be reported, Reporting intervals, Reporting amounts, Maximum number of cells to report, Whether to include beam measurements, Location information, Measurements from other sensors, Interference reporting parameters or any other suitable configurations.
[0130] The method of Fig. 3B corresponds to the method of Fig. 3A. The method of Fig. 3B can be implemented by a gNB 120 that is in communication with a UE 110 that is implementing the method of Fig. 3A. The method of Fig. 3B comprises, at block 304, receiving a recommendation of a tunable execution condition that is to be applied during execution of a handover.
[0131] To enable the tunable execution condition to be recommended, the gNB 120 can be configured to transmit an indication of one or more tunable parameters that represent parameters of the measurements that can be adjusted to the UE 110. The indication can provide the UE 110 with control to dynamically adjust one or more of the measurement parameters and / or execution conditions that have previously been set by the gNB 120. The indication can provide the UE 110 with control to dynamically adjust an execution condition for triggering a handover.
[0132] When the UE 110 has received such an indication the UE 110 can then determine a new value for one or more of the tunable parameters represented in the received indication and use the new values of the measurement parameters to perform the measurements. The UE 110 can also recommend a tunable execution parameter based on the tuned parameters and / or the measurements made using the new parameters. The recommendation of the tunable execution condition can be received in response to the indication of the tunable parameters.
[0133] In some examples the recommendation of the tunable execution condition can comprise an execution condition that has been used by the UE 110 during the execution of a handover. In such cases an indication of the execution condition that has been used by the UE 110 can be received in a handover complete message or any other suitable message. At block 306 the method comprises using the recommendation of the tunable execution condition to execute a handover. The recommendation of the tunable execution condition can also be used to update execution conditions of a network. For instance, the tunable execution condition could be used to execute handovers, could be stored in a network database for future use, could be used for training or updating a machine learning program and / or for any other suitable purpose.
[0134] The gNB 120 can also be configured to receive a measurement report wherein the measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the UE 110 to obtain the measurement results. The gNB 120 can the use information from the measurement report to perform handover.
[0135] In some examples the gNB 120 can also be configured to receive an estimated measurement configuration and perform a network check of one or more of the new values for one or more of the parameters.
[0136] Fig. 4 shows an example signaling chart that can be used to implement examples of the disclosure.
[0137] At block 400 the gNB 120 is aware of the capability of the UE 110. In this example the gNB 120 knows that the UE 110 has capability to adjust one or more parameters for handover. The gNB 120 can know the type of parameters that the UE 110 has the capability to adjust. The UE 110 can be configured to adjust one or more of, measurement objects, reporting configurations, execution conditions.
[0138] The UE 110 can use Machine Learning (ML) models or any other suitable processes or means to adjust the parameters. The UE 110 can use Machine Learning (ML) models or any other suitable processes or means to optimize, or substantially optimize, the parameters.
[0139] The parameters that can be adjusted by the UE 110 can comprise any parameters that are used during handover. In some examples the parameters that can be adjusted can comprise measurement parameters that relate to the measurements that are performed by the UE 110. The measurement parameters can comprise parameters that are used to perform and / or report the measurements. The measurement parameters can comprise measurement objects, reporting configurations, or any other suitable parameters. In some examples the parameters that can be adjusted can comprise an execution condition that defines when a handover is to be triggered. The parameters that can be adjusted can be referred to as tunable parameters.
[0140] The measurement objects could comprise any one or more of: Synchronization Signal Block Absolute Radio Frequency Channel Number (SSB ARFCN), Sub Carrier Spacing (SCS), Synchronization Signal Block Measurement Timing Configuration (SMTC), Synchronization Signal Block (SSB) / Channel State Information - Reference Signal (CSI-RS) blocks to average, Measurement Object (MO) offset; Reference Signal (RS) Configuration; RS Consolidation Threshold and number of RS to consolidate, Quality Configuration Index or any other suitable objects.
[0141] The reporting configurations can comprise choice of periodic or event triggered reporting; to additionally also report Cell Global Identity (CGI); to additionally also report System Frame Number and Frame Timing Difference (SFTD); A3 / A5 offsets, Time to Trigger (TTT), Hysteresis, RS type to be reported, Reporting intervals, Reporting amounts, Maximum number of cells to report, Whether to include beam measurements, Location information, Measurements from other sensors, Interference reporting parameters, or any other suitable configurations.
[0142] At block 402 the gNB 120 sets initial parameters for the handover. The initial parameters can comprise can comprise any parameters that are used during handover. The initial parameters can comprise measurement objects, reporting configurations, execution conditions, or any other suitable parameters. The initial parameters can be fetched by the gNB 120 by retrieving data from a network database 430.
[0143] In examples of the disclosure one or more of the initial parameters that are set by the gNB 120 can be adjusted by the UE 110. At block 404 the gNB 120 sends a measurement configuration message to the UE 110. The measurement configuration can comprise an indication of one or more tunable parameters. The tunable parameters are parameters that have been set by the gNB 120 that the UE 110 has freedom to adjust. The indication of the tunable parameters provides the UE 110 with control to dynamically adjust one or more of the tunable parameters.
[0144] The tunable parameters can be indicated in any suitable manner. In some examples the measObjectNR and ReportConfigNR can be marked to indicate that a particular parameter is tunable. The measObjectNR and ReportConfigNR can be marked with ASN.1 fields as a flag or could be marked in any other suitable manner. In some examples a range or ranges for one or more of the tunable parameters could also be indicated. This could indicate a permissible range within which the UE 110 can adjust the indicated parameter.
[0145] For instance, if the tunable parameters comprise a Measurement Object (MO) offset then an example range for the MO offset could be from -2 dB to + 2 dB in steps of 0.5 dB. If the tunable parameters comprise the TTT the range for the number of SSB / CSI- RS blocks to average could be from 1 to 3 and the TTT value could be a tuple of {80, 100, 120} msec. Other ranges and types of tunable parameters could be used in other examples.
[0146] The gNB 120 can select which parameters are tunable. For instance, the gNB 120 can select one or more parameters that are known to influence the way in which the target cell is selected for measurement and reported for a handover to that target cell. The parameters that are known to influence the way in which the target cell is selected for measurement and reported for a handover to that target cell can be determined from radio network performance tools or other network planning tools.
[0147] In some examples the gNB 120 can select parameters to be tunable to ensure that RLF is avoided before handover to a target gNB 102 has been completed. In such cases the parameters that are selected to be tunable could comprise timers or constants such as T310. If the UE 110 sets a larger value for such parameters this could cause RLF but if the UE 110 sets a smaller value this might avoid the RLF.
[0148] In some examples the tunable parameters can comprise the frequencies (cells) that are to be measured by the UE 110. For instance, the gNB 120 can initially set the measObjectNR SSB ARFCN to frequencies f 1 , f2, f3 and f4 but can include an indication that this list of frequencies can be tuned by the UE 110. The UE 110 can tune the list of frequencies by removing, modifying or adding frequencies to the list. As an example, a UE 110 could remove f2 from the list and add f5. This tuning of the list of frequencies could be made based on the trajectory of the UE 110. The tuning could be made based on the recommendations of an ML model or any other suitable model. As another example the UE 110 might choose to remove frequencies from the list. For example, the UE 110 could tune the list of frequencies by removing f2 and f3. These frequencies could be considered low priority due to power saving actions or for any other suitable reasons.
[0149] At block 406 the UE 110 tunes one or more of the tunable parameters. The tunable parameters can be measurement parameters or any other suitable type of parameters. The UE 110 can tune the tunable parameters by feeding the measurement configuration received at block 406 into an ML model or any other suitable model. The UE 110 can also use other information as inputs to the ML model. The other information used as inputs could comprise local data such as sensor information, GPS data, user activity patterns, battery level, or any other suitable information or data derived from such information.
[0150] The UE 110 can then obtain recommendation values for the tunable parameters as outputs from the ML model. These can be the values of the measurement parameters that it is recommend to use to perform and report the measurements.
[0151] At block 408 the UE 110 transmits an estimated measurement configuration and measurement reporting configuration to the gNB 120. The estimated measurement configuration can comprise an indication of the versions of the tunable parameters that have been recommended for use.
[0152] At block 410 the gNB verifies the parameters that have been recommended. The gNB 120 can perform a consistency check or any other suitable type of check. For instance, the gNB 120 can verify that the parameters that have been tuned are still within a range as set by the gNB 120. The gNB 120 can ensure that the UE 110 has not made an error in setting a parameter value out of a given range. This can be ensured by the gNB 120 checking and authorizing the parameter change as indicated by the UE 110 in the estimated measurement configuration. Once the recommended parameters have been verified, the gNB 120 can then use them to execute handover. At block 412 the gNB 120 can transmit another measurement configuration message to the UE 110. The other measurement configuration message indicates whether the recommended parameters have been verified. The another measurement configuration message can comprise the verified recommended parameters.
[0153] In some cases the verification of the parameters at block 410 might not be performed. In such cases the UE 110 can proceed directly with measurements using the recommended parameters without waiting for the verification. In such cases the UE 110 can send the estimated measurement configuration to the gNB 120 but the gNB 120 can just store the recommended parameters rather than perform the verification.
[0154] The gNB 120 can choose to perform a handover using the recommended parameters, or the verified versions of the recommended parameters as appropriate.
[0155] At block 414 the UE 110 performs measurements using the tuned parameters. Once the measurements have been performed the UE 110 generates a measurement report. The measurement report comprises measurement results and an indication of the versions of the tunable parameters that have been used by the UE 110 to obtain the measurement results. The versions of the tunable parameters can comprise an indication of the values or ranges that have been used for the respective parameters for performing and / or reporting the measurements or could comprise any other suitable information. . One or more measurement reports indicating different versions of the tunable parameters can be sent.
[0156] At block 416 the measurement report is sent from the UE 110 to the gNB 120.
[0157] At block 418 the gNB 120 prepares Conditional Handover (CHO) and execution conditions. These can be based on the measurement report that is received by the gNB 120 at block 416. At block 420 a handover command is sent from the gNB 120 to the UE 110 this can be sent after the CHO configuration and execution condition have been prepared. In some examples the UE 110 can tune the execution condition at block 422. Tuning the execution condition can comprise altering the time for L3 filtering and / or tuning the TTT value in the execution condition configuration or setting a different timer value used to detect source RLF. For example, timer T310 can be set to a lower value. The tuning of the execution condition can allow the execution condition to be optimized, or substantially optimized, or improved, based on the recommendation of the ML model or any other models.
[0158] If the UE 110 tunes the execution condition so that the execution condition used by the UE 110 is different to the execution condition in the handover command sent at block 420 than the UE 110 will a recommendation for an execution condition to the gNB 120. For instance, this could be marked as an extended version. An indication of the version of the execution condition that has been used can be stored.
[0159] At block 424 the UE 110 sends a handover complete message to the gNB 120. The handover complete message provides the network with a handover report. The handover report comprises an indication of the version of the execution condition that has been used.
[0160] At block 426 the gNB 120 can tag any tuned parameters. The tuned parameters can comprise any measurement parameters or execution conditions that have been used for handover and that differ from the initial parameters. The initial parameters can be the parameters as set by the gNB 120 at block 402.
[0161] At block 428 the gNB 120 stores data indicating the tuned parameters. The gNB 120 can store data by uploading data to a network database 430. The network database 430 can be located in any suitable location within the network.
[0162] Any suitable data can be uploaded to the network database 430. In some examples, the data could comprise the measurement parameters such as the measurement object and the reporting configuration, the execution condition, the measurement results, the handover report and / or any other suitable information. In some examples, additional information can be uploaded to the network database. The additional information can comprise information relating to the situation or conditions of the UE 110 or any other suitable information. The additional information can comprise UE 110 location, UE 110 trajectory and / or any other suitable information.
[0163] The data stored in the network database 430 can be used for training an ML model or any other suitable type of model. The ML model can be used by the network to improve the setting of the initial parameters for handover. For instance, the data stored in the network database 430 could be used to build an ML model that is specific to a cell or gNB 120 for selecting the initial parameters that are set at block 402.
[0164] Examples of the disclosure therefore provide a UE 110 with control to dynamically adjust values that are used for measurement parameters or execution conditions. This can enable the UE 110 to select improved values which can help the UE 110 to avoid RLF. The data collected by the UE 110 can also be stored at the network and used to train the network so as to improve the setting of the initial parameters for future handovers.
[0165] Fig. 5 shows an example use case scenario for examples of the disclosure. In the example of Fig. 5 the tunable parameters comprise the number of cells (frequencies) that is to be measured by the UE 110 and reported to the serving gNB 120. Different cells use different frequencies and so an indication of the number of cells inherently provides an indication of the number of frequencies to be measured. Other tunable parameters could be used in other examples.
[0166] In the example of Fig. 5, four gNBs 120 and the corresponding cells 122 are shown.
[0167] The arrow 501 indicates that Uplink / Downlink signals are exchanged between the UE 110 and the third gNB 120_3. The third gNB 120_3 is the serving gNB. The other gNBs 120_1 , 120_2, 120_4 are target gNBs 120 that can be considered for handover.
[0168] The UE 110 is moving in a trajectory as indicated by the arrow 503. The UE 110 is moving out of the cell 120_3 of the serving gNB 120_3 and a target gNB 120 needs to be selected for handover.
[0169] In this example, the serving gNB 120_3 can indicate a list of cells (frequencies) that the UE 110 is to measure. The serving gNB 120_3 can indicate the cells that are to be measured in an RRCconfiguration / RRCreconfiguration message or in any other suitable type of message. In the simple example of Fig. 5 the serving gNB 120_3 will indicate to the UE 110 that cells 122_1 , 122_2 and 122_4 are to be measured for a Handover (HO) decision.
[0170] The gNB 120_3 can also indicate that the list of cells that are to be measured is tunable. That is the gNB 120_3 can provide the UE 110 with control to change the cells 122 that are to be measured and reported.
[0171] The UE 110 can therefore generate a recommendation of the cells 122 that are to be measured. The recommendation can comprise an optimal list of cells 122. The UE 110 can use its own local information and ML models, or other types of models, to generate the recommendation of the cells 122. For example, the UE 110 can use local information such as context, trajectory, detected cells 122 and any other suitable information, as inputs to an ML model that can then be used to generate the recommendation of the cells 122 that are to be measured.
[0172] In the example of Fig. 5, this can enable non-useful cells to be removed from the list. In this particular example, the UE 110 is also moving out of the second cell 122_2 and so this cell could be removed from the list as being non-useful.
[0173] The UE 110 can therefore tune the parameters set by the gNB 120_3 by removing the second cell 122_2 from the list. The UE 110 can therefore perform measurements for the first cell 122_1 and the fourth cell 122_4 and report these back to the serving gNB 120_3. The measurement report can indicate that the list of cells was updated and indicate which cells have been added or removed from the list.
[0174] In this case, the tuning of the parameters reduces the number of cells 122 that need to be measured. This can reduce power usage at for the UE 110 in performing the measurements and reduces the radio resources that are needed for reporting the measurements. This tuning of the parameters therefore provides for a more efficient handover.
[0175] The example use case shown in Fig. 5 is a simple example for the purposes of explaining the principles of the examples of the disclosure. In real implementations of the disclosure the number of cells 122 to considered could be much larger and the environment could be more complex with buildings and moving objects affecting signal paths.
[0176] In the example of Fig. 5, the UE 110 has tuned the list of cells 122 by removing cells from the list. In other examples the UE 110 could also add cells 122 to the list. The new cells 122 could be added based on the trajectory of the UE 110, the cells that the UE 110 can measure, and any other suitable factors.
[0177] In some examples, an ML model can be used by a UE 110 to tune the parameters. As an example an ML model can be used by a UE to predict the best, or minimum, cells 122 that are to be measured and reported. The ML model can take into account the detected energy levels for the respective cells 122, the list of cells 122 indicated as an MO by the gNB 120, and / or any other relevant factors. Other ML models could be used to tune other parameters.
[0178] In this example:
[0179] • D is the list of cells 122 detected by the UE 110
[0180] • S is the list of suggested cells 122 within the MO from the gNB 120
[0181] • A' = D n S , is the list of suggested cells 120 that are detectable by the UE 110
[0182] • A = D u A' , is the list of cells 120 that suggested and detectable and non-suggested but detectable
[0183] The max number M > 1 of cells 122 to be used will be checked, if
[0184] |A| == M
[0185] Where, M is a boundary number set by the serving gNB 123_3 as part of the MO to limit the tuning of the parameters by the UE 110.
[0186] This means that the size of | A | must be equal to M, then:
[0187] • If | A| > M, then UE 110 selects the most M detectable (simple energy level detection) out of A • If | A| < M, then gNB 120_3 will fill the missing reported cells information by None values such as very low unique values (for instance, - 330 dBm in case of RSRP measurements).
[0188] This therefore provides A with M cells. These can be used as inputs to an ML model that will perform the tuning operation. In this case the tuning operation comprises selecting suitable cells.
[0189] The ML model that is used can be configured to provide statistically independent output probabilities for each cell in A. Each output shows the probability of how important it is to perform full measurement for a given cell and report the measurement to the gNB 120. In some examples a multi label classification model can be used as the ML model.
[0190] Fig. 6 shows an example ML model structure that could be used to implement examples of the disclosure. In this case the ML model structure comprises a neural network. Other types of ML models could be used in other examples. The example ML model could be implemented by a UE 110 and used to tune parameters for use in handovers, or could be used for any other suitable purpose.
[0191] The neural network shown in Fig. 6 comprises an input layer 600, multiple long shortterm memory (LSTM) layer 602 and an output layer 604.
[0192] The input layer 600 is configured to receive an input. The LSTM layers 602 follow the input layer 600. In this example the LSTM layers 602 are hidden and fully connected. The neural network can comprise any number of LSTM layers 602. In some examples the number of LSTM layers 602 can be one of the parameters that can be tuned. The number of LSTM layers 602 can be tuned, based at least in part, on the complexity of the input data.
[0193] The output layer 604 follows the LTSM layers 602. The output layer 604 has an output dimension which is equal to the number of targeted cells to be predicted (M in the described use case). The output layer 604 also has sigmoid as the activation function and binary cross entropy as the loss function. Figs. 7A and 7B show an example ML model input sample matrix and output vector These could be the input and output for the neural network of Fig. 6 or for any other suitable ML model.
[0194] An appropriate input is important for training ML models. The input has to be selected so that it contributes to the learning of the ML model.
[0195] In the use case example described herein, the UE 110 will perform a preliminary measurement for the cells in A for a predefined number of samples (time period). The input will consist of input samples of Secondary Signal- RSRP (SS-RSRP) or CSI-RS RSRP as shown in Fig. 7A.
[0196] In the example of Fig. 7A the input for the ML model comprises a matrix of RSRP values where the rows represent the different cells and the columns represent the different time instances.
[0197] Fig. 7B shows an example output vector for the ML model. The output vector comprises a probability value for the respective cells 122. The probability value provides an indication of whether a cell is needed.
[0198] Example values an input matrix and output vector could be:
[0199] StepO Stepl Step2 Predicted Output Vector cellOr
[0200] -100 -99 -98 0.80 celll -80 -81 -82 0.95 cell2 L-lll -112 -111 0.3
[0201] In this example, there are three different measurements for three different cells 122 at three different time instances. Other numbers of cells and time instances could be used in other examples. The measurements comprise RSRP values. Other measurements could be used in other examples.
[0202] In this example the predicted output vector indicates there is an 80% probability that cell 0 is needed, there is a 95% probability that cell 1 is needed and there is only a 30% probability that cell 2 is needed. Therefore, it can be inferred that only two of the cells (cell 0 and cell 1) are predicted to contribute to the HO decision. In this case it can be recommended to measure and report cell 0 and cell 1 while saving energy and resources by ignoring cell 2.
[0203] The labelling of the input data part of the process for the training of the ML. There are multiple ways that the input samples can be labelled. These can comprise: Assuming an offline training with all full history time series data (history measurements from all cells) is available, then for each sample input [Stepi, ... StepN], future samples in the time series can be considered. This could be for K steps , where K >N. That is, StepN+1 to StepK are considered. The mean signal levels of the cells over the period from StepN+1 to StepK can then be computed and sorted from high to low mean signal levels. The M cells with highest mean signal levels can be picked. These can be assigned a 1 (100%) as a label and the remaining cells will be assigned 0 as a label.
[0204] Referring back to the example of Fig. 5 the UE 110 is connected to the serving gNB120_3 but is headed towards gNB 120_1 and gNB 120_4. In this case the labels for the respective gNBs 120 would be
[0205] [gNB1 , gNB2, gNB3, gNB4] = [1 , 0, 1 , 1],
[0206] In this case, gNB 120_2 is not important for future handover because the trajectory of the UE 110 is moving away from gNB 120_2. Therefore, the label for gNB 120_2 is set to zero. In this case, gNB 120_3 is the serving cell and so the UE 110 must keep measuring this cell and so gNB3 is assigned the label 1. The remaining gNB 120_1 and 120_4 are important for the future decision of HO and so they are both assigned label 1. In this case training using historical measurements from gNB 120_1 , gNB 120_2, gNB 120_3 and gNB 120_4 with the calculated ground truth labels can train an ML model so that if a UE 110 trajectory is similar to the scenario in Fig. 5 the network can predict that gNB 120_1 and gNB 120_4 are the optimal cells to measure and report.
[0207] This can therefore enable the historical data collected by the UE 110 and gNB 120 in handovers using tuned parameters to be stored and used to train ML models to improve future handovers. Fig. 8 shows a relation between an input sample and an output vector that could be used in examples of the disclosure.
[0208] In the use case example described herein, the UE 110 can receive a message, such as a MeasConfig message, with MO indicating the list of preferred cells to measure. These can be indicated as tunable using a flag or any other suitable indication.
[0209] The UE 110 will prepare the A list of cells 122 as described above and perform a preliminary measurement for the cells in A and for a predefined number of samples (time period). The input 800 for the ML model 802 therefore comprises input samples of SS-RSRP or CSI-RS RSRP.
[0210] In this case the ML model 802 can be trained to obtain the probabilities that cells 122 are useful or not useful. The output 804 of the ML model 802 shown in Fig. 8 therefore comprises a list of probabilities. This can be provided as a vector output or in any other suitable format. ML models trained for other purpose could be used for other use cases.
[0211] As an example, to illustrate multi-label classification it can be assumed that there are 6 cells and the ground truth (labels) should be either 0 (Not measured) or 1 (Measured) for respective cells 122. If a cell 122 is known to be useful cell to measure and report its information then it will be assigned label 1 , otherwise the cell is assigned label 0. In this example, if it is found that cell 1 and 4 out of the 6 cells are not useful for mobility objective decisions then they can be ignored in future. Therefore in this model Ytrue for input RSRP from 6 cells will be [0 1 1 0 1 1] where celU and Cell4 are ignored. By using this a model will start predicting which set of useful cells are associated with our input sample and which cells 122 should be ignored.
[0212] In this case number of neurons in the output layer is equal to the number of total cells. Therefore, in this case the number of neurons on the output layer is 6 because there are 6 cells.
[0213] A neural network, or other type of ML model, can therefore provide an output vector which contains a 0 or 1 for each cell 122. A 0 assigned to a cell 122 indicates that the cell 122 is not useful for handover and can be turned OFF. A 1 assigned to a cell 122 indicates that the cell 122 is for handover and can be turned ON.
[0214] Examples of the disclosure can use Sigmoid in the output layer with binary_crossentropy as loss function, so each neuron in the output layer will give a probability for each cell independently in the output vector. Therefore, in the example with six cells, using Ytrue [0 1 1 0 1 1 ] for an input sample X indicates that only cells 2,3,5 and 6 are seen to be useful to measure and report. If the ML model has been trained well then the prediction output of the model Ypredicted could be:
[0215] [0.1 0.8 0.85 0.15 0.7 0.98],
[0216] This indicates that there is a high probability that cells 1 and 4 are not useful and that there is a high probability that cells 2, 3, 5, 6 are useful.
[0217] This output also indicates that cell 6 will be the most useful to measure because it has a very high probability value of 0.98.
[0218] The ML models can be trained for other predictions in other examples. For instance, an ML model could be trained for execution in a UE 110 so as to enable the UE 110 to recommend a A3 / A5 event offset, TTT or hysteresis values or other suitable values. Such ML models could be different from ML models trained to perform the recommendation of the cells / frequencies that the UE 110 measures. The UE 110 can be configured to combine the results from multiple ML models to set the measObjectNR and ReportingConfigNR as well as tune the ExecutionConfig based on recommendations from multiple ML models.
[0219] Fig. 9 illustrates an example of a controller 900. The controller 900 could be provided within an apparatus such as a UE 110 or a node apparatus such as a gNB 120. Implementation of a controller 900 may be as controller circuitry. The controller 900 may be implemented in hardware alone, have certain aspects in software including firmware alone or can be a combination of hardware and software (including firmware). The controller 900 can be configured to control functions of an apparatus comprising the controller 900. The controller 900 can be configured to cause apparatus to perform functions in accordance with examples of the disclosure. As illustrated in Fig. 9, the controller 900 can be implemented using instructions that enable hardware functionality, for example, by using executable instructions of a computer program 906 in a general-purpose or special-purpose processor 902 that may be stored on a computer readable storage medium (disk, memory etc.) to be executed by such a processor 902.
[0220] The processor 902 is configured to read from and write to the memory 904. The processor 902 may also comprise an output interface via which data and / or commands are output by the processor 902 and an input interface via which data and / or commands are input to the processor 902.
[0221] The memory 904 stores a computer program 906 comprising computer program instructions (computer program code) that controls the operation of the apparatus when loaded into the processor 902. The computer program instructions, of the computer program 906, provide the logic and routines that enables the apparatus to perform the methods illustrated in the Figs. The processor 902 by reading the memory 904 is able to load and execute the computer program 906.
[0222] In some examples where the controller 900 is provided within a UE 110 the controller 900 therefore comprises: at least one processor 902; and at least one memory 904 storing instructions that, when executed by the at least one processor 902, cause a UE 110 at least to perform: generating 200 a measurement report wherein the measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the UE 110 to obtain the measurement results; and transmitting 202 the measurement report.
[0223] In some examples where the controller 900 is provided within a node apparatus such as a gNB 120 the controller 900 therefore comprises: at least one processor 902; and at least one memory 904 storing instructions that, when executed by the at least one processor 902, cause a UE 110 at least to perform: receiving 204 a measurement report from a UE 110 wherein the measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the UE 110 to obtain the measurement results; and using 206 information from the measurement report to perform handover.
[0224] In some examples where the controller 900 is provided within a UE 110 the controller 900 therefore comprises: at least one processor 902; and at least one memory 904 storing instructions that, when executed by the at least one processor 902, cause a UE 110 at least to perform: determining 300 a recommendation of a tunable execution condition that is to be applied during execution of a handover; and transmitting 302 the recommendation of the tunable execution condition to enable execution conditions of a network to be updated.
[0225] In some examples where the controller 900 is provided within a node apparatus such as a gNB 120 the controller 900 therefore comprises: at least one processor 902; and at least one memory 904 storing instructions that, when executed by the at least one processor 902, cause a UE 110 at least to perform: receiving 304 a recommendation of a tunable execution condition that is to be applied during execution of a handover; and using 306 the recommendation of the tunable execution condition to execute a handover.
[0226] The computer program 906 may arrive at the UE 110 via any suitable delivery mechanism 908. The delivery mechanism 908 may be, for example, a machine- readable medium, a computer-readable medium, a non-transitory computer-readable storage medium, a computer program product, a memory device, a record medium such as a Compact Disc Read-Only Memory (CD-ROM) or a Digital Versatile Disc (DVD) or a solid-state memory, an article of manufacture that comprises or tangibly embodies the computer program 906. The delivery mechanism may be a signal configured to reliably transfer the computer program 906. The apparatus may propagate or transmit the computer program 906 as a computer data signal.
[0227] The computer program 906 can comprise computer program instructions for causing a UE 110 to perform at least the following or for performing at least the following: generating 200 a measurement report wherein the measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the UE 110 to obtain the measurement results; and transmitting 202 the measurement report.
[0228] The computer program 906 can comprise computer program instructions for causing a node apparatus such as a gNB 120 to perform at least the following or for performing at least the following: receiving 204 a measurement report from a UE 110 wherein the measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the UE 110 to obtain the measurement results; and using 206 information from the measurement report to perform handover.
[0229] The computer program 906 can comprise computer program instructions for causing a UE 110 to perform at least the following or for performing at least the following: determining 300 a recommendation of a tunable execution condition that is to be applied during execution of a handover; and transmitting 302 the recommendation of the tunable execution condition to enable execution conditions of a network to be updated.
[0230] The computer program 906 can comprise computer program instructions for causing a node apparatus such as a gNB 120 to perform at least the following or for performing at least the following: receiving 304 a recommendation of a tunable execution condition that is to be applied during execution of a handover; and using 306 the recommendation of the tunable execution condition to execute a handover.
[0231] The computer program instructions may be comprised in a computer program, a non- transitory computer readable medium, a computer program product, a machine- readable medium. In some but not necessarily all examples, the computer program instructions may be distributed over more than one computer program. Although the memory 904 is illustrated as a single component / circuitry it may be implemented as one or more separate components / circuitry some or all of which may be integrated / removable and / or may provide permanent / semi-permanent / dynamic / cached storage.
[0232] Although the processor 902 is illustrated as a single component / circuitry it may be implemented as one or more separate components / circuitry some or all of which may be integrated / removable. The processor 902 may be a single core or multi-core processor.
[0233] References to ‘computer-readable storage medium’, ‘computer program product’, ‘tangibly embodied computer program’ etc. or a ‘controller’, ‘computer’, ‘processor’ etc. should be understood to encompass not only computers having different architectures such as single / multi- processor architectures and sequential (Von Neumann) / parallel architectures but also specialized circuits such as field-programmable gate arrays (FPGA), application specific circuits (ASIC), signal processing devices and other processing circuitry. References to computer program, instructions, code etc. should be understood to encompass software for a programmable processor or firmware such as, for example, the programmable content of a hardware device whether instructions for a processor, or configuration settings for a fixed-function device, gate array or programmable logic device etc.
[0234] As used in this application, the term ‘circuitry’ may refer to one or more or all of the following:
[0235] (a) hardware-only circuitry implementations (such as implementations in only analog and / or digital circuitry) and
[0236] (b) combinations of hardware circuits and software, such as (as applicable):
[0237] (i) a combination of analog and / or digital hardware circuit(s) with software / firmware and
[0238] (ii) any portions of hardware processor(s) with software (including digital signal processor(s)), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions and
[0239] (c) hardware circuit(s) and or processor(s), such as a microprocessor(s) or a portion of a microprocessor(s), that requires software (e.g. firmware) for operation, but the software may not be present when it is not needed for operation. This definition of circuitry applies to all uses of this term in this application, including in any claims. As a further example, as used in this application, the term circuitry also covers an implementation of merely a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example and if applicable to the particular claim element, a baseband integrated circuit for a mobile device or a similar integrated circuit in a server, a cellular network device, or other computing or network device.
[0240] The stages illustrated in The Figs can represent steps in a method and / or sections of code in the computer program 906. The illustration of a particular order to the blocks does not necessarily imply that there is a required or preferred order for the blocks and the order and arrangement of the block may be varied. Furthermore, it can be possible for some blocks to be omitted.
[0241] The term ‘comprise’ is used in this document with an inclusive not an exclusive meaning. That is any reference to X comprising Y indicates that X may comprise only one Y or may comprise more than one Y. If it is intended to use ‘comprise’ with an exclusive meaning then it will be made clear in the context by referring to “comprising only one...” or by using “consisting”.
[0242] In this description, the wording ‘connect’, ‘couple’ and ‘communication’ and their derivatives mean operationally connected / coupled / in communication. It should be appreciated that any number or combination of intervening components can exist (including no intervening components), i.e., so as to provide direct or indirect connection / coupling / communication. Any such intervening components can include hardware and / or software components.
[0243] As used herein, the term "determine / determining" (and grammatical variants thereof) can include, not least: calculating, computing, processing, deriving, measuring, investigating, identifying, looking up (for example, looking up in a table, a database or another data structure), ascertaining and the like. Also, "determining" can include receiving (for example, receiving information), accessing (for example, accessing data in a memory), obtaining and the like. Also, " determine / determining" can include resolving, selecting, choosing, establishing, and the like. In this description, reference has been made to various examples. The description of features or functions in relation to an example indicates that those features or functions are present in that example. The use of the term ‘example’ or ‘for example’ or ‘can’ or ‘may’ in the text denotes, whether explicitly stated or not, that such features or functions are present in at least the described example, whether described as an example or not, and that they can be, but are not necessarily, present in some of or all other examples. Thus ‘example’, ‘for example’, ‘can’ or ‘may’ refers to a particular instance in a class of examples. A property of the instance can be a property of only that instance or a property of the class or a property of a sub-class of the class that includes some but not all of the instances in the class. It is therefore implicitly disclosed that a feature described with reference to one example but not with reference to another example, can where possible be used in that other example as part of a working combination but does not necessarily have to be used in that other example.
[0244] Although examples have been described in the preceding paragraphs with reference to various examples, it should be appreciated that modifications to the examples given can be made without departing from the scope of the claims.
[0245] Features described in the preceding description may be used in combinations other than the combinations explicitly described above.
[0246] Although functions have been described with reference to certain features, those functions may be performable by other features whether described or not.
[0247] Although features have been described with reference to certain examples, those features may also be present in other examples whether described or not.
[0248] The term ‘a’, ‘an’ or ‘the’ is used in this document with an inclusive not an exclusive meaning. That is any reference to X comprising a / an / the Y indicates that X may comprise only one Y or may comprise more than one Y unless the context clearly indicates the contrary. If it is intended to use ‘a’, ‘an’ or ‘the’ with an exclusive meaning then it will be made clear in the context. In some circumstances the use of ‘at least one’ or ‘one or more’ may be used to emphasis an inclusive meaning but the absence of these terms should not be taken to infer any exclusive meaning. The presence of a feature (or combination of features) in a claim is a reference to that feature or (combination of features) itself and also to features that achieve substantially the same technical effect (equivalent features). The equivalent features include, for example, features that are variants and achieve substantially the same result in substantially the same way. The equivalent features include, for example, features that perform substantially the same function, in substantially the same way to achieve substantially the same result.
[0249] In this description, reference has been made to various examples using adjectives or adjectival phrases to describe characteristics of the examples. Such a description of a characteristic in relation to an example indicates that the characteristic is present in some examples exactly as described and is present in other examples substantially as described.
[0250] The above description describes some examples of the present disclosure however those of ordinary skill in the art will be aware of possible alternative structures and method features which offer equivalent functionality to the specific examples of such structures and features described herein above and which for the sake of brevity and clarity have been omitted from the above description. Nonetheless, the above description should be read as implicitly including reference to such alternative structures and method features which provide equivalent functionality unless such alternative structures or method features are explicitly excluded in the above description of the examples of the present disclosure.
[0251] Whilst endeavoring in the foregoing specification to draw attention to those features believed to be of importance it should be understood that the Applicant may seek protection via the claims in respect of any patentable feature or combination of features hereinbefore referred to and / or shown in the drawings whether or not emphasis has been placed thereon. l / we claim:
Claims
CLAIMS1. A User Equipment comprising: means for generating a measurement report wherein the measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the User Equipment to obtain the measurement results; and means for transmitting the measurement report.
2. A User Equipment as claimed in claim 1 comprising means for receiving an indication of one or more tunable parameters that represent parameters of the measurements that can be adjusted.
3. A User Equipment as claimed in claim 2 comprising means for determining a new value for one or more of the tunable parameters represented in the received indication.
4. A User Equipment as claimed in claim 2 comprising means for using a machine learning model to determine one or more of the new values for one or more of the tunable parameters.
5. A User Equipment as claimed in any of claims 2 to 4 comprising means for transmitting an estimated measurement configuration to enable a network check of one or more of the new values for one or more of the tunable parameters.
6. A User Equipment as claimed in any preceding claim wherein the tunable parameters comprise at least one of: a measurement object; a reporting configuration.
7. A User Equipment as claimed in claim 6 wherein the measurement object comprises any one or more of: Synchronization Signal Block Absolute Radio Frequency Channel Number; Sub Carrier Spacing; Synchronization Signal Block Measurement Timing Configuration; Synchronization Signal Block / Channel State Information - Reference Signal blocks to average; Measurement Object offset;Reference Signal Configuration; Reference Signal Consolidation Threshold and number of Reference Signal to consolidate; Quality Configuration Index.
8. A User Equipment as claimed in any of claims 6 to 7 wherein the reporting configuration comprises any one or more of: choice of periodical or event triggered reporting; to additionally also report Cell Global Identity; to additionally also report System Frame Number and Frame Timing Difference; A3 / A5 offsets; Time to Trigger; Hysteresis; Reference Signal type to be reported; Reporting intervals; Reporting amounts; Maximum number of cells to report; Whether to include beam measurements; Location information; Measurements from other sensors; Interference reporting parameters.
9. A User Equipment as claimed in any preceding claim comprising means for determining a recommendation of a tunable execution condition that is to be applied during execution of a handover and means for transmitting the recommendation of the tunable execution condition.
10. A User Equipment as claimed in any preceding claim comprising means for transmitting an indication of an execution condition that has been used by the User Equipment during the execution of a handover.
11. A User Equipment as claimed in claim 10 wherein the indication of the execution condition that has been used by the User Equipment is transmitted in a handover complete message.
12. A User Equipment as claimed in any preceding claim wherein the measurement report is used during a preparation phase of a conditional handover procedure.
13. A method comprising: generating a measurement report wherein the measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the User Equipment to obtain the measurement results; and transmitting the measurement report.
14. A computer program comprising instructions which, when executed by a User Equipment cause the User Equipment to perform: generating a measurement report wherein the measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the User Equipment to obtain the measurement results; and transmitting the measurement report.
15. A Network Entity comprising: means for receiving a measurement report from a User Equipment wherein the measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the User Equipment to obtain the measurement results; and means for using information from the measurement report to perform handover.
16. A Network Entity as claimed in claim 15 comprising means for transmitting an indication of one or more tunable parameters that represent parameters of the measurements that can be adjusted to the User Equipment.
17. A Network Entity as claimed in any of claims 15 to 16 comprising means for receiving an estimated measurement configuration to enable a network check of one or more of the new values for one or more of the tunable parameters.
18. A Network Entity as claimed in any of claims 15 to 17 comprising means for receiving a recommendation of a tunable execution condition that is to be applied during execution of a handover; and means for using the recommendation of the tunable execution condition to execute a handover.
19. A Network Entity as claimed in any of claims 15 to 18 comprising means for receiving an indication of an execution condition that has been used by the User Equipment during the execution of a handover.
20. A Network Entity as claimed in claim 19 wherein the indication of the execution condition that has been used by the User Equipment is transmitted in a handover complete message.
21. A Network Entity as claimed in any of claims 15 to 20 comprising means for storing at least one of versions of one or more tunable parameters that have been used by the User Equipment to perform measurements and tunable execution conditions that have been used to execute a handover; and means for using the stored versions of one or more tunable parameters that have been used by the User Equipment to perform measurements and / or tunable execution conditions that have been used to execute a handover and / or for training a machine learning model.
22. A Network Entity as claimed in any of claims 15 to 21 wherein the measurement report is used during a preparation phase of a conditional handover procedure.
23. A method comprising: receiving a measurement report from a User Equipment wherein the measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the User Equipment to obtain the measurement results; and using information from the measurement report to perform handover.
24. A computer program comprising instructions which, when executed by a Network Entity cause the Network Entity to perform: receiving a measurement report from a User Equipment wherein the measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the User Equipment to obtain the measurement results; and using information from the measurement report to perform handover.
25. A User Equipment comprising: means for determining a recommendation of a tunable execution condition that is to be applied during execution of a handover; and means for transmitting the recommendation of the tunable execution condition to enable execution conditions of a network to be updated.
26. A User Equipment as claimed in claim 25 comprising means for receiving an indication of one or more tunable parameters that represent parameters of themeasurements that can be adjusted and determining the recommendation of the tunable execution condition based on one or more measurements made using parameters that have been adjusted in accordance with the indication.
27. A User Equipment as claimed in any of claims 25 to 26 comprising means for using a machine learning model to determine one or more of the recommendations for the tunable execution condition.
28. A User Equipment as claimed in any of claim 25 to 27 comprising means for generating a measurement report wherein the measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the User Equipment to obtain the measurement results; and means for transmitting the measurement report.
29. A User Equipment as claimed in claim 28 comprising means for transmitting an estimated measurement configuration to enable a network check of one or more of the new values for one or more of the tunable parameters.
30. A User Equipment as claimed in any of claims 25 to 29 wherein the tunable parameters comprise at least one of: a measurement object; a reporting configuration.
31. A User Equipment as claimed in claim 30 wherein the measurement object comprises any one or more of: Synchronization Signal Block Absolute Radio Frequency Channel Number; Sub Carrier Spacing; Synchronization Signal Block Measurement Timing Configuration; Synchronization Signal Block / Channel State Information - Reference Signal blocks to average; Measurement Object offset; Reference Signal Configuration; Reference Signal Consolidation Threshold and number of Reference Signal to consolidate; Quality Configuration Index.
32. A User Equipment as claimed in any of claims 30 to 31 wherein the reporting configuration comprises any one or more of: choice of periodical or event triggered reporting; to additionally also report Cell Global Identity; to additionally also report System Frame Number and Frame Timing Difference; A3 / A5 offsets; Time to Trigger;Hysteresis; Reference Signal type to be reported; Reporting intervals; Reporting amounts; Maximum number of cells to report; Whether to include beam measurements; Location information; Measurements from other sensors; Interference reporting parameters.
33. A User Equipment as claimed in any of claims 28 to 31 comprising means for transmitting an indication of an execution condition that has been used by the User Equipment during the execution of a handover.
34. A User Equipment as claimed in claim 33 wherein the indication of the execution condition that has been used by the User Equipment is transmitted in a handover complete message.
35. A method comprising: determining a recommendation of a tunable execution condition that is to be applied during execution of a handover; and transmitting the recommendation of the tunable execution condition to enable execution conditions of a network to be updated.
36. A computer program comprising instructions which, when executed by a User Equipment cause the User Equipment to perform: determining a recommendation of a tunable execution condition that is to be applied during execution of a handover; and transmitting the recommendation of the tunable execution condition to enable execution conditions of a network to be updated.
37. A Network Entity comprising: means for receiving a recommendation of a tunable execution condition that is to be applied during execution of a handover; and means for using the recommendation of the tunable execution condition to execute a handover.
38. A Network Entity as claimed in claim 37 comprising means for transmitting an indication of one or more tunable parameters that represent parameters of themeasurements that can be adjusted and receiving the recommendation of the tunable execution conditions in response.
39. A Network Entity as claimed in any of claims 37 to 38 comprising means for receiving a measurement report wherein the measurement report comprises measurement results and one or more indications of versions of one or more tunable parameters that have been used by the User Equipment to obtain the measurement results; and means for using information from the measurement report to perform handover.
40. A Network Entity as claimed in claim 39 comprising means for receiving an estimated measurement configuration and performing a network check of one or more of the new values for one or more of the parameters.
41. A Network Entity as claimed in any of claims 37 to 40 comprising means for receiving an indication of an execution condition that has been used by the User Equipment during the execution of a handover.
42. A Network Entity as claimed in claim 41 wherein the indication of the execution condition that has been used by the User Equipment is transmitted in a handover complete message.
43. A method comprising: receiving a recommendation of a tunable execution condition that is to be applied during execution of a handover; and using the recommendation of the tunable execution condition to execute a handover.
44. A computer program comprising instructions which, when executed by a Network Entity cause the Network Entity to perform: receiving a recommendation of a tunable execution condition that is to be applied during execution of a handover; and using the recommendation of the tunable execution condition to execute a handover.
Citation Information
Patent Citations
Coordination of energy metric reporting
WO2022229430A1
Wireless terminal, radio access network node, and methods therefor
WO2023079946A1
