Data logging for UE measurement reporting

Abstract

According to an example aspect of the present invention, there is provided an apparatus configured to select a set of user equipments, UEs, the set comprising a part and not all of UEs configurable by the apparatus, provide to the UEs of the set a measurement configuration which defines at least one measurement start condition, at least one measurement stop condition and at least one measurement reporting condition, the at least one reporting condition comprising at least one mobility problem-based trigger and the at least one measurement configuration defining a measurement to be conducted in more than one cell, and receive measurement reports from the UEs of the set, the measurement reports comprising data logged based on the provided measurement configuration.

Description

DATA LOGGING FOR UE MEASUREMENT REPORTINGFIELD

[0001] The present disclosure relates to data logging, such as for training of machine learning solutions.BACKGROUND

[0002] In cellular wireless communication, user terminals, known as user equipments, UE, roam within a coverage area of the communication network from cell to cell. As a UE moves from a coverage area of one cell toward a coverage area of another cell, a handover, also known as a handoff, may be caused to take place to switch the UE to be served by the other cell and maintain its connectivity with the network, NW. Handovers may take place using different mechanisms depending on the used radio-access technology, RAT, and optionally also depending on a type of connection the UE has with the network.

[0003] Handover errors may lead to degradation of quality in communication sessions, wherefore optimizing handovers is of interest in cellular communication. For example, handovers may be configured so that a communication link to the other cell is established before a communication link with the previous cell is relinquished.SUMMARY

[0004] According to some aspects, there is provided the subject-matter of the independent claims. Some embodiments are defined in the dependent claims. The scope of protection sought for various embodiments of the invention is set out by the independent claims. The embodiments, examples and features, if any, described in this specification that do not fall under the scope of the independent claims are to be interpreted as examples useful for understanding various embodiments of the invention.

[0005] According to a first aspect of the present disclosure, there is provided an apparatus comprising at least one processing core and at least one memory storing instructionsthat, when executed by the at least one processing core, cause the apparatus at least to select a set of user equipments, UEs, the set comprising a part and not all of UEs configurable by the apparatus, provide to the UEs of the set a measurement configuration which defines at least one measurement start condition, at least one measurement stop condition and at least one measurement reporting condition, the at least one reporting condition comprising at least one mobility problem-based trigger and the at least one measurement configuration defining a measurement to be conducted in more than one cell, and receive measurement reports from the UEs of the set, the measurement reports comprising data logged based on the provided measurement configuration.

[0006] According to a second aspect of the present disclosure, there is provided an apparatus comprising at least one processing core and at least one memory storing instructions that, when executed by the at least one processing core, cause the apparatus at least to receive, from a network, a measurement configuration which defines at least one measurement start condition, at least one measurement stop condition and at least one measurement reporting condition, the at least one reporting condition comprising at least one mobility problem-based trigger and the at least one measurement configuration defining a measurement to be conducted in more than one cell, perform a measurement based on the measurement configuration, and send, responsive to determining that a reporting condition from among the at least one reporting condition is fulfilled, a measurement report to the network, the measurement report comprising data logged based on the provided measurement configuration.

[0007] According to a third aspect of the present disclosure, there is provided a method comprising selecting, by an apparatus, a set of user equipments, UEs, the set comprising a part and not all of UEs configurable by the apparatus, providing to the UEs of the set a measurement configuration which defines at least one measurement start condition, at least one measurement stop condition and at least one measurement reporting condition, the at least one reporting condition comprising at least one mobility problem-based trigger and the at least one measurement configuration defining a measurement to be conducted in more than one cell, and receiving measurement reports from the UEs of the set, the measurement reports comprising data logged based on the provided measurement configuration.

[0008] According to a fourth aspect of the present disclosure, there is provided a method comprising receiving, from a network, a measurement configuration which defines at least one measurement start condition, at least one measurement stop condition and at least onemeasurement reporting condition, the at least one reporting condition comprising at least one mobility problem-based trigger and the at least one measurement configuration defining a measurement to be conducted in more than one cell, performing a measurement based on the measurement configuration, and sending, responsive to determining that a reporting condition from among the at least one reporting condition is fulfilled, a measurement report to the network, the measurement report comprising data logged based on the provided measurement configuration.

[0009] According to a fifth aspect of the present disclosure, there is provided an apparatus comprising means for defining a set of user equipments, UEs, the set comprising a part and not all of UEs configurable by the apparatus, providing to the UEs of the set a measurement configuration which defines at least one measurement start condition, at least one measurement stop condition and at least one measurement reporting condition, the at least one reporting condition comprising at least one mobility problem-based trigger and the at least one measurement configuration defining a measurement to be conducted in more than one cell, and receiving measurement reports from the UEs of the set, the measurement reports comprising data logged based on the provided measurement configuration.

[0010] According to a sixth aspect of the present disclosure, there is provided an apparatus comprising means for receiving, from a network, a measurement configuration which defines at least one measurement start condition, at least one measurement stop condition and at least one measurement reporting condition, the at least one reporting condition comprising at least one mobility problem-based trigger and the at least one measurement configuration defining a measurement to be conducted in more than one cell, performing a measurement based on the measurement configuration, and sending, responsive to determining that a reporting condition from among the at least one reporting condition is fulfilled, a measurement report to the network, the measurement report comprising data logged based on the provided measurement configuration.

[0011] According to a seventh aspect of the present disclosure, there is provided a non- transitory computer readable medium having stored thereon a set of computer readable instructions that, when executed by at least one processor, cause an apparatus to at least select a set of user equipments, UEs, the set comprising a part and not all of UEs configurable by the apparatus, provide to the UEs of the set a measurement configuration which defines at least one measurement start condition, at least one measurement stop condition and at least onemeasurement reporting condition, the at least one reporting condition comprising at least one mobility problem-based trigger and the at least one measurement configuration defining a measurement to be conducted in more than one cell, and receive measurement reports from the UEs of the set, the measurement reports comprising data logged based on the provided measurement configuration.

[0012] According to an eighth aspect of the present disclosure, there is provided a non- transitory computer readable medium having stored thereon a set of computer readable instructions that, when executed by at least one processor, cause an apparatus to at least receive, from a network, a measurement configuration which defines at least one measurement start condition, at least one measurement stop condition and at least one measurement reporting condition, the at least one reporting condition comprising at least one mobility problem-based trigger and the at least one measurement configuration defining a measurement to be conducted in more than one cell, perform a measurement based on the measurement configuration, and send, responsive to determining that a reporting condition from among the at least one reporting condition is fulfilled, a measurement report to the network, the measurement report comprising data logged based on the provided measurement configuration.BRIEF DESCRIPTION OF THE DRAWINGS

[0013] FIGURE 1 illustrates an example system in accordance with at least some embodiments of the present invention;

[0014] FIGURE 2A illustrates signal strengths in accordance with at least some embodiments of the present invention;

[0015] FIGURE 2B illustrates signal strengths in accordance with at least some embodiments of the present invention;

[0016] FIGURE 3 illustrates an example apparatus capable of supporting at least some embodiments of the present invention;

[0017] FIGURE 4 illustrates signalling in accordance with at least some embodiments of the present invention;

[0018] FIGURE 5 is a signalling diagram involving a too-late handover in accordance with at least some embodiments of the present invention,

[0019] FIGURE 6 is a flow graph of a method in accordance with at least some embodiments of the present invention, and

[0020] FIGURE 7 is a flow graph of a method in accordance with at least some embodiments of the present invention.EMBODIMENTS

[0021] Methods are herein described which enable advantageously collecting measurement data concerning real-life events where mobility processes do not function as intended. Such data may be used to compile training data for a geographically localized machine learning, ML, solution which is thereby configured to select appropriate time instants to trigger handovers such that mobility process problems will occur less frequently than without using the ML solution.

[0022] FIGURE 1 illustrates an example system in accordance with at least some embodiments of the present invention. This system includes base stations 130, 135 in communication with UEs, such as UE 110. The base stations and the UE are apparatuses. A radio link connects base station 130 with UE 110. The radio link may be bidirectional, comprising an uplink, UL, to convey information from UE 110 toward base station 130, and a downlink, DL, to convey information from the base station 130 toward UE 110. A cellular communication system may comprise hundreds or thousands of base stations, of which only two are illustrated in FIGURE 1 for the sake of clarity of the illustration. The base stations may be distributed in that they comprise a centralized unit, CU, and one or more distributed unit, DU. A base station is an example of a base node.

[0023] Base station 130 is further coupled communicatively with core network node 140, which may comprise, for example, a mobility management entity, MME, or access and mobility management function, AMF. The core network node 140 may be coupled with further core network nodes, and with a network 150, which may comprise the Internet or a corporate network, for example. The system may communicate with further networks via network 150. Examples of the further core network nodes, which are not illustrated in FIGURE 1 for the sake of clarity, include gateways and subscriber information repositories. Core network nodes may be virtualized in the sense that they may run as software modules on computing substrates, such that more than one virtualized network node may run on a same physical computingsubstrate. The network may be configured to function in accordance with a suitable cellular standard such as long term evolution, LTE, fifth generation, 5G, which is also known as New Radio, NR, or sixth generation, 6G standards as defined by the the 3rdgeneration partnership project, 3GPP.

[0024] Base station 130 controls, in the example of FIGURE 1 cells 130A and 130B, of which UE 110 is in the situation illustrated in FIGURE 1 attached with cell 130A, and base station 135 controls, in the example of FIGURE 1, cells 135A and 135B. The number of cells, or beams, may be in excess of what is illustrated in FIGURE 1. It is also possible that a base station has a single cell or beam. While illustrated as sector-shaped, cells of a same base station may be omnidirectional and operate on different frequencies, for example. A mobility event may comprise a switch from one beam to another beam of the same cell, or a switch from one cell to another cell. To support mobility procedures, UEs, including UE 110, are configured to conduct radio measurements to measure signal strengths of adjacent beams and / or cells, and report results of these measurements to the network, which may then take a decision concerning a mobility event, such as a beam change or a cell switch.

[0025] When a signal strength of a serving cell declines while a signal strength of a neighbouring cell increases, the network may consider a handover to the neighbouring cell to safeguard a functioning connection with the UE. Base stations of the system may be connected with each other using an inter-base station interface, such as an X2 interface, for example, to facilitate handover signalling. Such an inter-base station interface is not included in FIGURE 1 to protect clarity of the illustration.

[0026] FIGURE 2A illustrates signal strengths in accordance with at least some embodiments of the present invention. On the horizontal axis is distance, proceeding from the left to the right from a base station controlling a first, serving, cell toward a base station controlling a second, neighbouring, cell. The vertical axis corresponds to a signal strength from the base stations, respectively, as measured by a UE, in terms of reference signal received power, RSRP. The curve marked with square markers corresponds to a signal from the first cell, and the curve marked with circle markers corresponds to a signal from the second cell.

[0027] As is clear from the figure, at a point which roughly corresponds to the cell edge, the signal from the second cell becomes stronger than the signal from the first cell, and the UE, proceeding toward the base station controlling the second cell, should be handed over to that cell. In some RATs, such as 3GPP RATs, the network is configured to decide on handovers,while in other RATs the UE itself may decide on handovers. The UE may provide mobility measurement reports to the NW to help the NW decide on handovers. Such reports may include information on signal strengths from the serving and neighbouring cells, as measured by the UE. Such HO-related measurement reports are distinct from measurement reports of conditional measurements discussed herein in terms of compiling training data.

[0028] In actual networks, the behaviour of signal strengths is more complex than is illustrated in the idealized FIGURE 2A. In detail, topographical terrain features, buildings and other objects affect propagation of electromagnetic waves in ways that make the cell edge have a more complicated shape than simply e.g. circular or hexagonal, and moreover the cell edge may be affected by time- varying effects, such as traffic patterns. It may occur that an exclave of coverage area of a first cell is enclosed within a coverage area of a second cell (an enclave) or the exclave may be surrounded by coverage areas of more than one cell other than the first cell.

[0029] FIGURE 2B illustrates signal strengths in accordance with at least some embodiments of the present invention. This figure, which has a more realistic scenario than FIGURE 2A, illustrates RSRP and measurement logging phases. Unlike FIGURE 2A, in FIGURE 2B the horizontal axis is time, rather than linear distance. As the RSRPs change, the UE of FIGURE 2B moves, for example toward the base station controlling the second cell, wherefore the basic shapes of the RSRP curves are similar as in the previous figure, albeit more complex.

[0030] The highlighted pattern indicates the serving cell, which is changed in a handover process in point (2) of the figure. Further, the UE of FIGURE 2B is configured with a measurement configuration which defines at least one measurement start condition, at least one measurement stop condition and at least one measurement reporting condition. Here the measurement start condition is expressed in terms of a power offset between the signals, that is, when the signals are closer in power than a threshold, the measurement is started in phase (1). After the handover (2) the measurement is stopped in phase (3), for example responsive to a measurement stop condition such as another offset, or a time elapsed from the successful handover. Once a reporting condition is met (4), the logged measurement is reported to the network. During the measurement, from phase (1) to phase (3), the UE performs measurements which may be defined in the measurement configuration, or alternatively they may be default properties. Examples of properties measured during a measurement period, from phase (1) tophase (3), include signal strength or quality values of nearby cells, such as signal strength or quality values of the strongest nearby cells. As is evident from the figure, the measurement is conducted in more than one cell.

[0031] The signal strength may be measures in terms of RSRP or received signal strength indication, RSSI, for example. The measurement configuration may further define, that in addition to logging signal strength measurements, the measurement comprises logging location information of the UE as it moves during the measurement interval. Overall by logged measurement it is meant measurements conducted by the UE, such that the UE stores results of the measurements in its memory, until it reports these results to the network in a measurement report which comprises the measurement results, at least in part, or data derived from the measurement results. The measurement reports may be sent to a core network node via a base station, or the measurement reports may be sent to the serving base station such that they are addressed to this base station and the base station is enabled to act on the measurement reports without forwarding them to a core network.

[0032] Machine learning, ML, models may be trained to enhance success rates of handovers. In detail, a ML model may be trained with training data localized to a cell pair or to a cell neighbourhood, such that the training data has a geographic scope similar to the geographic scope of phenomena affecting the success or failure of handovers in the cell pair or the cell neighbourhood. The training data may be generated from measurement reports obtained from UEs operating in the cell neighbourhood. In particular, the training data may comprise at least a part of the measurement results reported in the measurement reports, for example processed to a suitable format for training the ML model. The training data may comprise measurement results from logged measurements which are conducted in more than one cell, such as in FIGURE 2B, where a handover takes place, or must have taken place, during the measurement period. In particular, the training data used by e.g. a base station in training a ML solution may comprise measurement data collected in a cell controlled by the base station and in each one of the neighbouring cells of the cell controlled by the base station. The target cell of the handover, or a cell where the UE re-establishes connectivity after HO failure, may forward a copy of the measurement report to a source cell of the handover to enable the source cell to become aware of events experienced by UEs shortly after they’ve left the source cell. Training a local ML model to capture the local unique patterns of the radio environment within each cell coverage area benefits from not only data local to the cell itself but also data from neighbour cells.

[0033] The thus localized ML model may be trained to select a future HO point, or a future threshold for received signal power levels, using a history of signal measurements as input to the ML model. For example, the input to the model may be one or more HO-related measurement report from a UE. Moreover, at training time the future received signal levels themselves will work as ground truth or may be used in the process of selecting an optimal HO point as ground truth for the ML model output. In both cases, the knowledge of the future received signal levels is a useful factor in the process of training a predictive HO ML model. The sharing of measurement reports by the base stations participating in handovers enhances the predictive power of ML models trained using such data, since the data includes data both preceding and following the actual HO. Consequently, and to enable local ML model training, both base stations should have access to future, or historical measurements just before and after the HO execution time. The ML solution used may be a supervised deep-learning solution, such as a long-short term memory, LSTM, recurrent neural network, RNN. Another alternatives include a multi-class classifier or dense NW, or unsupervised learning techniques such as (deep) reinforcement learning, RL.

[0034] The training of the ML solution may take place in a base station which controls a cell in which the HO time instants will be used, or in another network node to which the measurement reports, or training data obtained from the measurement reports, may be provided from the base station and from which the base station may subsequently receive the trained ML solution in return. Examples of such network nodes include core network nodes and operations, administration and maintenance, 0AM, nodes.

[0035] For improved results, the training data should include data collected during mobility problems, such as failures or unintended events. The occurrence of failures in wireless communication networks is inevitable and collecting proper training data to mitigate their effects is a non-trivial task. Examples of such mobility problems include the following.

[0036] Firstly, the case of no or incomplete signalling towards UE. In some cases of HO failure, such as too-late failure, the handover process may start too late or not even start, which makes it impossible to signal to the UE to start logged measurements as a response to HO start. Depending on the type of handover procedure (e.g., baseline, conditional HO, dual active stack HO), this situation may occur when the UE fails to detect a suitable target cell / beam, or the target cell is congested, resulting in longer than expected cell preparation time.

[0037] Secondly, an unclarity concerning the problematic situation or the affected UE. In other instances, it may not be evident which UE(s) or under which conditions the problem(s) occurred. This lack of clarity in identifying the problem’s root cause can make it difficult to find an effective solution and associate the proper training set to identify or mitigate similar situations in the future.

[0038] Thirdly, the cases of unnecessary HOs, radio link failures, RLFs, and random access channel, RACH, failures. A series of unnecessary HOs, also known as ping-pong HOs, are considered mobility problems, elimination of which is desired. The training data for enabling avoidance of these cases is not limited to a single HO or single HO attempt and may involves multiple cells or base stations, may require dedicated measurement configurations. Also, UEs may experience failures related to HO procedures either before the HO procedure (e.g., expiry of timer T310 in 3GPP RATs) or during HO (e.g., RACH failure). After these failures, UEs may have to go through radio resource control, RRC, connection reestablishment or revert to idle mode. Even when reverting to idle mode, it is still useful to collect training samples during all the procedure up to moving to idle mode, to facilitate the trained ML model to decrease the frequency of occurrence of such failure events in the future.

[0039] Fourthly, the case of the UE winding up in a cell other than the target or source cell of a handover. This is a wrong cell, WC, failure, and indicates the network selected an incorrect target cell and such an occurrence should be avoided as it entails an impact to connection quality.

[0040] To adequately address the above-described kinds of mobility problems, it may be useful to begin collecting logged measurement data already prior to a start of a HO procedure and to associate the data so collected with a subsequent handover, begun e.g. by an RRCreconfig message when the RAT is a 3GPP RAT.

[0041] When preparing the training data, data from mobility problem events may be included in the training data with an increased weight, such that mobility problems are represented in the training data with a higher incidence than the actual occurrence incidence of mobility problems. For example, if 4% of HOs from a cell fail, the training data may include 7% measurement data quantity collected during failed HOs and only 93% of successful-HO measurement data quantity. This provides the beneficial effect, that the ML solution will be more attuned to avoidance of mobility problems, which cause service quality degradation.

[0042] Since most handovers, in typical networks 95 - 98 percent of handovers, do not involve mobility problems, collecting training data which also includes cases of mobility problems, is of interest in order to obtain the technical benefit of enhanced HO quality when the trained ML solution is used to select the HO time and, optionally, also the HO target cell.

[0043] To compile training data collection for ML which includes data involving mobility problems, the following may be done.

[0044] A base station, or other network node responsible for collecting the data, selects UEs into a set of UEs, the set comprising a part and not all of UEs configurable by the apparatus. For example, the set may comprise only a part, and not all, of the UEs that the base station may configure with conditional measurement configurations. For example, the definition of the set may comprise including in the set UEs which fulfil certain conditions, such as one or more conditions from the following list: having a battery power level meeting a battery threshold, having a signal power which fulfils a power criterion, having a mobility state which fulfils a movement criterion, is further from the base station than a distance criterion, and is heading toward a predetermined geographical area. The predetermined geographical area may be one where mobility failures have been detected in the past with a higher frequency than in other nearby areas. The battery threshold may comprise that the UE has at least a certain percentage of maximum battery power remaining. The power criterion may comprise that the UE has an RSRP of the base station less than a certain level, indicating likelier HO to another cell. The movement criterion may comprise that the UE moves slower than a predefined speed. The distance criterion may comprise that the UE is closer than a threshold distance to the cell edge, also indicating enhanced likelihood of a handover in the near future.

[0045] The base station or other network node responsible for collecting the data, will further provide to each one of the UEs of the set a measurement configuration which defines at least one measurement start condition, at least one measurement stop condition and at least one measurement reporting condition, the reporting condition comprising at least one mobility problem-based trigger and the measurement configuration defining a measurement conducted in more than one cell. The measurement configuration need not be the same for each UE of the set. If a UE in the set becomes unreachable, or for another reason, it need not be provided a measurement configuration, effectively it may be thus excluded from the set. The mobility problem-based trigger may comprise that the reporting is triggered only if a mobility problem is encountered during the measurement period, that is after its start and before its end. Examplesof mobility problems are provided herein above. The mobility problem-based trigger may also mean that in the absence of mobility problems, the data logged during the measurement is discarded by the UE. The measurement conducted in more than one cell entails that the measurement is not stopped when the serving cell changes.

[0046] The measurement start condition may be based on one of already available events (e.g., A3 or A4 in 3GPP RATs) or a new event or condition, such as entering a certain geographical area or an RSRP offset between signals from serving and / or neighboring cells. The measurement start condition may be defined based on specified ones from among the neighboring cells of the serving cell, or a UE state, such as RACH or detected RLF.

[0047] The measurement stop condition, which enables UE to stop the logging procedure, may depend on the serving cell or the UE state, for example. For example, the measurement stop condition may comprise that logging ends after a time period configured in the measurement configuration has elapsed after a serving cell change. The measurement reporting condition(s) may comprise triggers for the UE to discard the logged data if it does not meet the given conditions, for example, if the HO does not encounter problems.

[0048] The base station, or the other network node, may further receive measurement reports from the UEs of the set, the measurement reports comprising data logged based on the provided measurement configuration. The base station or the node may then derive the training data based on these measurement reports. Subsequently, the base station may use the trained ML model to select optimized time instants for UEs it serves, and trigger handovers of these UEs at the selected optimized time instant. In some cases, the ML model will also select a target cell, and the base station will trigger the handover to this selected target cell at the time instant selected by the ML model.

[0049] The base station may be further configured to determine whether the optimized time instants for HO selected using the trained ML model meet a predetermined quality criterion, and responsive to the predetermined quality criterion not being met, the base station may trigger re-training of the machine learning model. The re-training may be based on new measurement reports, to account for changes in the landscape nearby the base station.

[0050] Whether for initial training or re-training, the base station may be configured to cease the provision of the measurement configurations to UEs of the set responsive to a determination that a sufficient number of measurement reports have been received. Forexample, the base station may be configured to collect a predetermined number of measurement reports which reflect mobility problems, such as a hundred or 150 such reports, for example.

[0051] When the network node other than the base station performs the training of the ML model, the base station is configured to provide the received measurement reports to this network node, to receive from the network node a trained machine learning model and to use the trained machine learning model select optimized time instants for handovers in a cell controlled by the apparatus.

[0052] Further concerning the selection of the UEs to the set of UEs for measurement configuration, it is useful to focus especially on failures in which the HO procedure is not even started, since in too-late failures, for example, the UE cannot be selected during the HO procedure for data collection.

[0053] In these cases, the UEs need to be selected to the set before the (expected) start of HO procedure to cover cases like too-late failures. However, the network cannot blindly select all the UEs to participate in the data collections since it is not efficient nor practical for all the UEs to measure and report, not all the UEs experience the problem, and the network may need data collected only from a group of UEs based on their capability, model, and vendor. The serving base station may select the UE may be based on criteria including but not limiting to: the UE vendor or model type, the UEs capabilities, e.g., Multi-Panel UE, MPUE, Multi- TRP, or legacy UE. A prediction of the mobility or behavior of the UEs may be used to select the UEs as may other relevant characteristics. Certain UE models may be more prone to HO failures than others.

[0054] The base station, or the other network node, may be configured to update the measurement configuration already provided to a UE in the set.

[0055] The measurement start and stop triggers may each include one of the following: the serving cell signal quality becomes better than absolute threshold, the serving cell signal quality becomes worse than absolute threshold, a neighbor cell signal quality becomes offset better than serving cell, neighbor cell signal quality becomes better than absolute threshold, serving cell signal quality becomes worse than absolute thresholdl and neighbor becomes better than absolute threshold2, neighbor becomes offset better than supplementary cell, beingserved by a specific beam, a number of beam switches during an interval to be higher than threshold, and a drop or change of a secondary cell in case of dual connectivity.

[0056] The measurement configuration may comprise information describing the details of what to be measured, the granularity of the measurement, in addition to the stopping condition. For example, the UE may be configured to measure the serving cell RSRP every tl [ms] if the serving cell is gNB 1 , and / or measure detectable cells during RRCreestablishment every t2 [ms]. In general, the conditional measurement indicates jointly the following issues: What to be measured / logged, e.g., serving cell(s) / beam(s) and / or visible (detectable) cell(s) / beam(s) and / or neighbor cell(s) / beam(s), Under different conditions, e.g., if serving cell(s) / beam(s) is and / or does not match the given ID, if T304 is running, if the UE is in RRCrestablishment, Using different configuration, e.g. periodicity, Ll-rsrp or / and L3-rsrp, or L3 filter coefficient, DRX, Stopping Condition: e.g., t3 [s] after successful connection to a given cell, t4 [s] after expiry of T310 or t4 [s] after beam recovery failure.

[0057] Concerning reporting of the logged measurement, after measurement is performed, the UEs report them efficiently back to the network. Reporting all the logged measurement is not desirable, hence, the network may provide a reporting trigger as part of the configuration. The reporting condition may request the UE to report only if one or multiple events has happened during the data collections. Examples of possible reporting triggers include successful HO, one or multiple consecutive handovers during the predefined interval, RACH attempt, RACH failure (i.e., T304 expiry in 3GPP RAT), cell reselections, baseline or condition HO failure and RLF (either T310 or beam recovery failure in 3GPP RAT) shortly after a successful HO. Reporting may be configured to take place only if the candidate beam / cell / gNB / nodes are involved, and / or only if the measurement length is longer than the threshold.

[0058] FIGURE 3 illustrates an example apparatus capable of supporting at least some embodiments of the present invention. Illustrated is device 300, which may comprise, for example, a mobile communication device such as, in applicable parts, base station 130 or UE 110 of FIGURE 1. Comprised in device 300 is processor 310, which may comprise, for example, a single- or multi-core processor wherein a single-core processor comprises one processing core and a multi-core processor comprises more than one processing core. Processor 310 may comprise, in general, a control device. Processor 310 may comprise more than one processor. When processor 310 comprises more than one processor, device 300 may be adistributed device wherein processing of tasks takes place in more than one physical unit. Processor 310 may be a control device. A processing core may comprise, for example, a Cortex- A8 processing core manufactured by ARM Holdings or a Zen processing core designed by Advanced Micro Devices Corporation. A processing core or processor may be, or may comprise, at least one qubit. Processor 310 may comprise at least one Qualcomm Snapdragon and / or Intel Atom processor. Processor 310 may comprise at least one application- specific integrated circuit, ASIC. Processor 310 may comprise at least one field-programmable gate array, FPGA. Processor 310, optionally together with memory and computer instructions, may be means for performing method steps in device 300, such as defining, providing, receiving, performing and sending. Processor 310 may be configured, at least in part by computer instructions, to perform actions.

[0059] A processor may comprise circuitry, or be constituted as circuitry or circuitries, the circuitry or circuitries being configured to perform phases of methods in accordance with embodiments described herein. As used in this application, the term “circuitry” may refer to one or more or all of the following: (a) hardware-only circuit implementations, such as implementations in only analogue and / or digital circuitry, and (b) combinations of hardware circuits and software, such as, as applicable: (i) a combination of analogue and / or digital hardware circuit(s) with software / firmware and (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 UE or a base station, to perform various functions) and (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.

[0060] 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 (or multiple processors) or portion of 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 or processor integrated circuit for a mobile device or a similar integrated circuit in server, a cellular network device, or other computing or network device.

[0061] Device 300 may comprise memory 320. Memory 320 may comprise randomaccess memory and / or permanent memory. Memory 320 may comprise at least one RAM chip. Memory 320 may be a computer readable medium. Memory 320 may comprise solid-state, magnetic, optical and / or holographic memory, for example. Memory 320 may be at least in part accessible to processor 310. Memory 320 may be at least in part comprised in processor 310. Memory 320 may be means for storing information. Memory 320 may comprise computer instructions that processor 310 is configured to execute. When computer instructions configured to cause processor 310 to perform certain actions are stored in memory 320, and device 300 overall is configured to run under the direction of processor 310 using computer instructions from memory 320, processor 310 and / or its at least one processing core may be considered to be configured to perform said certain actions. Memory 320 may be at least in part external to device 300 but accessible to device 300. Memory 320 may be transitory or non- transitory. The term “non-transitory”, as used herein, is a limitation of the medium itself (that is, tangible, not a signal) as opposed to a limitation on data storage persistency (for example, RAM vs. ROM).

[0062] Device 300 may comprise a transmitter 330. Device 300 may comprise a receiver 340. Transmitter 330 and receiver 340 may be configured to transmit and receive, respectively, information in accordance with at least one cellular or non-cellular standard. Transmitter 330 may comprise more than one transmitter. Receiver 340 may comprise more than one receiver. Transmitter 330 and / or receiver 340 may be configured to operate in accordance with wideband code division multiple access, WCDMA, 5G, long term evolution, LTE, wireless local area network, WLAN, Ethernet and / or worldwide interoperability for microwave access, WiMAX, standards, for example.

[0063] Device 300 may comprise a near-field communication, NFC, transceiver 350. NFC transceiver 350 may support at least one NFC technology, such as NFC, Bluetooth, Wibree or similar technologies.

[0064] Device 300 may comprise user interface, UI, 360. UI 360 may comprise at least one of a display, a keyboard, a touchscreen, a vibrator arranged to signal to a user by causing device 300 to vibrate, a speaker or a microphone. A user may be able to operate device 300 via UI 360, for example to accept incoming telephone calls, to originate telephone calls or video calls.

[0065] Device 300 may comprise or be arranged to accept a user identity module 370. User identity module 370 may comprise, for example, a subscriber identity module, SIM, card installable in device 300. A user identity module 370 may comprise information identifying a subscription of a user of device 300. A user identity module 370 may comprise cryptographic information usable to verify the identity of a user of device 300.

[0066] Processor 310 may be furnished with a transmitter arranged to output information from processor 310, via electrical leads internal to device 300, to other devices comprised in device 300. Such a transmitter may comprise a serial bus transmitter arranged to, for example, output information via at least one electrical lead to memory 320 for storage therein. Alternatively to a serial bus, the transmitter may comprise a parallel bus transmitter. Likewise processor 310 may comprise a receiver arranged to receive information in processor 310, via electrical leads internal to device 300, from other devices comprised in device 300. Such a receiver may comprise a serial bus receiver arranged to, for example, receive information via at least one electrical lead from receiver 340 for processing in processor 310. Alternatively to a serial bus, the receiver may comprise a parallel bus receiver.

[0067] Device 300 may comprise further devices not illustrated in FIGURE 3. For example, where device 300 comprises a smartphone, it may comprise at least one digital camera. In some embodiments, device 300 lacks at least one device described above. For example, some devices 300 may lack a NFC transceiver 350 and / or user identity module 370.

[0068] Processor 310, memory 320, transmitter 330, receiver 340, NFC transceiver 350, UI 360 and / or user identity module 370 may be interconnected by electrical leads internal to device 300 in a multitude of different ways. For example, each of the aforementioned devices may be separately connected to a master bus internal to device 300, to allow for the devices to exchange information. However, as the skilled person will appreciate, this is only one example and various ways of interconnecting at least two of the aforementioned devices may be used without departing from the scope of the present invention.

[0069] FIGURE 4 illustrates signalling in accordance with at least some embodiments of the present invention. On the vertical axes are disposed, on the left, base station 130 of FIGURE 1, and on the right, UE 110 of FIGURE 1. Time advances from the top toward the bottom.

[0070] In phase 410, base station 130 defines the set of UEs, which in this example includes UE 110. The base station provides, in phase 420, a measurement configuration to UE 110, which takes the measurement configuration into use. Phase 430 represents UE 110 determining that a measurement start condition in the measurement configuration has been met, causing measurement 440 to begin. The curved bracket in the figure represents the span of the measurement in time. During measurement 440, a mobility problem occurs at point 435. In phase 450, UE 110 determines that a measurement stop condition of the measurement configuration has been met, and subsequently, responsive to determining that a measurement reporting condition of the measurement configuration has been met, UE 110 provides a measurement report to base station 130, phase 460, this report comprising logged measurement data of measurement 440, including measurements conducted in more than one cell. In some cases, the reporting is only triggered in case the measurements include measurements conducted in at least three cells. Once the base station is in possession of a sufficient number of such measurement reports, it may prepare the training data based on these reports, train the ML model and start using the thus trained ML model in selecting HO time instants and, in some cases, also HO target cells. HOs will then be conducted, as guided by the base station, on the basis of the selected HO time instants.

[0071] In the following, a signalling process will be described which involves a successful handover in a 3GPP network:• Step 1 : The network provides or updates a measurement configuration to the UE. The network may also, or alternatively, provide a conditional measurement configuration to the UE. The network may provide / update the conditional measurements in while configuring a normal measurement configuration or in a separate message. The conditional measurement configuration may be independent from another measurement configuration, where such configuration is present.• Step 2: Responsive to the measurement start condition being met, the UE starts measuring and logging,• Step 3: Upon meeting the measurement report condition for HO, UE sends the HO measurement condition. This report sent in this step is not the conditional report for training data collection, but a reporting phase forming part of a HO procedure.• Steps 4-9: A normal handover procedure including handover decision (4), handover request from source cell (5), admission control in the target cell (6), handover request acknowledge from target to source cell (7), sending RRCreconfig from source cell to the UE (8) and starting buffering data in source cell (9).• Step 10: UE detach from the serving cell, starts a T304 timer. Since the conditions are changed, UE checks if any updates are needed to be applied to the measurements during this phase,• Steps 11 - 15: early status transfer from source cell to target cell (11), SN status transfer from source cell to target cell (12), user data forwarding from source to target cell (13), buffering user data in target cell (14) and RAN handover completion (15).• Step 16: UE successfully connects to the target cell. Since the conditions are changed, UE checks if any updates are needed to be applied to the measurements during this phase,• Step 17-26: The singling among different network nodes to complete the handover and switch the path to new cell. Handover success from target to source cell (17), SN status transfer from source to target cell (18), user data to target cell (19) and to core NW from the target cell (20), path switch request from target cell to AMF (21), path switch in UPF (22), end marker from UPF to source cell and thence to target cell (23), user data between target cell and UPF (24), patch switch ack from AMF to target cell (25) and UE context release from target cell to source cell (26)• Step 27 : Upon receiving the indication of successful HO, the source cell may decide to not release the UE context until it receives the measurement reports.• Step 28 : UE checks the measurement report condition, and prepare the logged report,• Step 29: UE indicates to the target cell that it has logged measurement ready to be reported.• Step 30: The target cell request the report on the logged measurement,• Step 31 : UE provides the logged reports• Step 32: The target cell forward the logged report to the source cell (which has configured the UE)

[0072] Steps 27 - 32 are hereby disclosed also separately from steps 1 - 16.

[0073] FIGURE 5 is a signalling diagram involving a too-late handover in accordance with at least some embodiments of the present invention. The vertical axes correspond to UE 110 on the left, and source base station 130 and target base station 135 on the right.

[0074] In phase 510, source base station 130 provides to UE 110 a measurement configuration for handover and a conditional measurement configuration for collecting data for training data to train the ML model. In phase 520, UE 110 determines that a measurement start condition is met, and UE 110 starts logging the conditional measurement for ML training. In phase 530 UE 110 transmits a HO-related measurement report concerning neighbour cell signal strengths to the source base station, which takes a HO decision in phase 540 based at least in part on the report of phase 530. In phase 550 the source 130 sends a HO request to target 135, which performs an admission control decision in phase 560 and returns a HO request ack 570 to source base station 130. After phase 570, a failure occurs in the form a too-late HO, wherein the UE proceeds into a coverage area of the target cell without being sent a HO command.

[0075] In phase 580, UE 110 updates the conditional measurement based on the conditions, for example, based on detecting that the failure has occurred, the number of measured and logged parameters may be increased in UE 110.

[0076] Phase 590 represents and exchange where UE 110 sends to target base station 135 an RRC connection re-establishment request, receives from to target base station 135 a RRC re-establishment message, and sends to target base station 135 a RRC re-establishment complete message. In other words, in phase 590 the RRC connection is re-established in a cell controlled by to target base station 135, which is a slower process than completing a handover to this cell.

[0077] In phase 5100 UE 110 determines that a reporting condition in the measurement configuration received in phase 510 is fulfilled, and UE 110 responsively indicates to target base station 135 in phase 5110 that it has a logged report. The logged report may be usable, as discussed herein above, in generation of training data. Target base station 135 requests UE 110 to provide the report in phase 5120, and UE 110 responsively provides the report with the logged measurement results in phase 5130.

[0078] FIGURE 6 is a flow graph of a method in accordance with at least some embodiments of the present invention. The phases of the illustrated method may be performed in base station 130, or in a control device configured to control the functioning thereof, when installed therein.

[0079] Phase 610 comprises selecting, by an apparatus, a set of user equipments, UEs, the set comprising a part and not all of UEs configurable by the apparatus. Phase 620 comprises providing to the UEs of the set a measurement configuration which defines at least one measurement start condition, at least one measurement stop condition and at least one measurement reporting condition, the reporting condition comprising at least one mobility problem-based trigger and the measurement configuration defining a measurement conducted in more than one cell. Phase 630 comprises receiving measurement reports from the UEs of the set, the measurement reports comprising data logged based on the provided measurement configuration.

[0080] FIGURE 7 is a flow graph of a method in accordance with at least some embodiments of the present invention The phases of the illustrated method may be performedin UE 110, or in a control device configured to control the functioning thereof, when installed therein.

[0081] Phase 710 comprises receiving, from a network, a measurement configuration which defines at least one measurement start condition, at least one measurement stop condition and at least one measurement reporting condition, the reporting condition comprising at least one mobility problem-based trigger and the measurement configuration defining a measurement conducted in more than one cell. Phase 720 comprises performing a measurement based on the measurement configuration. Finally, phase 730 comprises sending, responsive to determining that a reporting condition from among the at least one reporting condition is fulfilled, a measurement report to the network, the measurement report comprising data logged based on the provided measurement configuration.

[0082] It is to be understood that the embodiments of the invention disclosed are not limited to the particular structures, process steps, or materials disclosed herein, but are extended to equivalents thereof as would be recognized by those ordinarily skilled in the relevant arts. It should also be understood that terminology employed herein is used for the purpose of describing particular embodiments only and is not intended to be limiting.

[0083] Reference throughout this specification to one embodiment or an embodiment means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, appearances of the phrases “in one embodiment” or “in an embodiment” in various places throughout this specification are not necessarily all referring to the same embodiment. Where reference is made to a numerical value using a term such as, for example, about or substantially, the exact numerical value is also disclosed.

[0084] As used herein, a plurality of items, structural elements, compositional elements, and / or materials may be presented in a common list for convenience. However, these lists should be construed as though each member of the list is individually identified as a separate and unique member. Thus, no individual member of such list should be construed as a de facto equivalent of any other member of the same list solely based on their presentation in a common group without indications to the contrary. In addition, various embodiments and example of the present invention may be referred to herein along with alternatives for the various components thereof. It is understood that such embodiments, examples, and alternatives are not to be construed as de facto equivalents of one another, but are to be considered as separateand autonomous representations of the present invention.

[0085] Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the preceding description, numerous specific details are provided, such as examples of lengths, widths, shapes, etc., to provide a thorough understanding of embodiments of the invention. One skilled in the relevant art will recognize, however, that the invention can be practiced without one or more of the specific details, or with other methods, components, materials, etc. In other instances, well- known structures, materials, or operations are not shown or described in detail to avoid obscuring aspects of the invention.

[0086] While the forgoing examples are illustrative of the principles of the present invention in one or more particular applications, it will be apparent to those of ordinary skill in the art that numerous modifications in form, usage and details of implementation can be made without the exercise of inventive faculty, and without departing from the principles and concepts of the invention. Accordingly, it is not intended that the invention be limited, except as by the claims set forth below.

[0087] The verbs “to comprise” and “to include” are used in this document as open limitations that neither exclude nor require the existence of also un-recited features. The features recited in depending claims are mutually freely combinable unless otherwise explicitly stated. Furthermore, it is to be understood that the use of "a" or "an", that is, a singular form, throughout this document does not exclude a plurality.

[0088] As used herein, “at least one of the following: ” and “at least one of ” and similar wording, where the list of two or more elements are joined by “and” or “or”, mean at least any one of the elements, or at least any two or more of the elements, or at least all the elements.INDUSTRIAL APPLICABILITY

[0089] At least some embodiments of the present invention find industrial application in managing cellular networks.

Claims

CLAIMS:

1. An apparatus comprising at least one processing core and at least one memory storing instructions that, when executed by the at least one processing core, cause the apparatus at least to:- select a set of user equipments, UEs, the set comprising a part and not all of UEs configurable by the apparatus;- provide to the UEs of the set a measurement configuration which defines at least one measurement start condition, at least one measurement stop condition and at least one measurement reporting condition, the at least one reporting condition comprising at least one mobility problem-based trigger and the at least one measurement configuration defining a measurement to be conducted in more than one cell, and- receive measurement reports from the UEs of the set, the measurement reports comprising data logged based on the provided measurement configuration.

2. The apparatus according to claim 1, further configured to use the measurement reports as training data in training of a machine learning model, the machine learning model being configured to select a time instant to trigger a handover, the training data further comprising data measured during successful mobility events.

3. The apparatus according to claim 2, further configured to use the trained machine learning model to select the optimized time instant for a first UE, and to trigger the handover of the first UE at the selected optimized time instant.

4. The apparatus according claim 3, further configured to determine whether the optimized time instant selected using the trained machine learning model meet a predetermined quality criterion, and responsive to the predetermined quality criterion not being met by the optimized time instants selected using the trained machine learning model, trigger re-training of the machine learning model.

5. The apparatus according to any of claims 1 - 4, further configured to cease the provision of the measurement configuration responsive to a determination that a sufficient number of measurement reports have been received.

6. The apparatus according to claim 1, further configured to provide the received measurement reports to a network node, to receive from the network node a trained machine learning model and to use the trained machine learning model select time instants for handovers in a cell controlled by the apparatus.

7. The apparatus according to any of claims 1 - 6, further configured to perform the defining of the set of UEs at least in part by including in the set UEs which fulfil one or more of the following: having a battery power level meeting a battery threshold, having a signal power which fulfils a power criterion, having a mobility state which fulfils a movement criterion, is further from the apparatus than a distance criterion, and is heading toward a predetermined geographical area.

8. The apparatus according to any of claims 1 - 7, wherein the at least one mobility problembased trigger comprises one or more trigger based on one or more of the following: a handover failure, a random access process failure, ping-pong handover behaviour, radio link failure and handover to wrong cell.

9. The apparatus according to any of claims 1 - 8, wherein the apparatus is a base station.

10. An apparatus comprising at least one processing core and at least one memory storing instructions that, when executed by the at least one processing core, cause the apparatus at least to:- receive, from a network, a measurement configuration which defines at least one measurement start condition, at least one measurement stop condition and at least one measurement reporting condition, the at least one reporting condition comprising at least one mobility problem-based trigger and the at least one measurement configuration defining a measurement to be conducted in more than one cell,- perform a measurement based on the measurement configuration, and- send, responsive to determining that a reporting condition from among the at least one reporting condition is fulfilled, a measurement report to the network, the measurement report comprising data logged based on the provided measurement configuration.

11. A method comprising:- selecting, by an apparatus, a set of user equipments, UEs, the set comprising a part and not all of UEs configurable by the apparatus;- providing to the UEs of the set a measurement configuration which defines at least one measurement start condition, at least one measurement stop condition and at least one measurement reporting condition, the at least one reporting condition comprising at least one mobility problem-based trigger and the at least one measurement configuration defining a measurement to be conducted in more than one cell, and- receiving measurement reports from the UEs of the set, the measurement reports comprising data logged based on the provided measurement configuration.

12. The method according to claim 11, further comprising using the measurement reports as training data in training of a machine learning model, the machine learning model being configured to select a time instant to trigger a handover, the training data further comprising data measured during successful mobility events.

13. The method according to claim 12, further comprising using the trained machine learning model to select the optimized time instant for a first UE, and triggering the handover of the first UE at the selected optimized time instant.

14. The method according claim 13, further comprising determining whether the optimized time instants selected using the trained machine learning model meet a predetermined quality criterion, and responsive to the predetermined quality criterion not being met by the optimized time instants selected using the trained machine learning model, triggering re-training of the machine learning model.

15. The method according to any of claims 11 - 14, further comprising ceasing the provision of the measurement configuration responsive to a determination that a sufficient number of measurement reports have been received.

16. The method according to claim 11, further comprising providing the received measurement reports to a network node, receiving from the network node a trained machine learning model and using the trained machine learning model select time instants for handovers in a cell controlled by the apparatus.

17. The method according to any of claims 11 - 16, further comprising performing the defining of the set of UEs at least in part by including in the set UEs which fulfil one or more of the following: having a battery power level meeting a battery threshold, having a signal power which fulfils a power criterion, having a mobility state which fulfils a movement criterion, is further from the apparatus than a distance criterion, and is heading toward a predetermined geographical area.

18. The method according to any of claims 11 - 17, wherein the at least one mobility problembased trigger comprises one or more trigger based on one or more of the following: a handover failure, a random access process failure, ping-pong handover behaviour, radio link failure and handover to wrong cell.

19. The method according to any of claims 11 - 18, wherein the method is performed by a base station.

20. A method comprising:- receiving, from a network, a measurement configuration which defines at least one measurement start condition, at least one measurement stop condition and at least one measurement reporting condition, the at least one reporting condition comprising at least one mobility problem-based trigger and the at least one measurement configuration defining a measurement to be conducted in more than one cell,- performing a measurement based on the measurement configuration, and- sending, responsive to determining that a reporting condition from among the at least one reporting condition is fulfilled, a measurement report to the network, the measurement report comprising data logged based on the provided measurement configuration.

21. A non-transitory computer readable medium having stored thereon a set of computer readable instructions that, when executed by at least one processor, cause an apparatus to at least:- select a set of user equipments, UEs, the set comprising a part and not all of UEs configurable by the apparatus;- provide to the UEs of the set a measurement configuration which defines at least one measurement start condition, at least one measurement stop condition and at least one measurement reporting condition, the at least one reporting condition comprising at least one mobility problem-based trigger and the at least one measurement configuration defining a measurement to be conducted in more than one cell, and- receive measurement reports from the UEs of the set, the measurement reports comprising data logged based on the provided measurement configuration.

22. A non-transitory computer readable medium having stored thereon a set of computer readable instructions that, when executed by at least one processor, cause an apparatus to at least:- receive, from a network, a measurement configuration which defines at least one measurement start condition, at least one measurement stop condition and at least one measurement reporting condition, the at least one reporting condition comprising at least one mobility problem-based trigger and the at least one measurement configuration defining a measurement to be conducted in more than one cell,- perform a measurement based on the measurement configuration, and- send, responsive to determining that a reporting condition from among the at least one reporting condition is fulfilled, a measurement report to the network, the measurement report comprising data logged based on the provided measurement configuration.

Images