Prediction of configurable system parameters using synthetic samples generated in compliance with fundamental domain requirement

Abstract

A method of generating a prediction of an operating parameter setting for an element in a system includes collecting (302) parameter data samples for a plurality of elements in the system. The parameter data samples include covariate parameters associated with the plurality of elements. The method further includes generating (304) synthetic data samples based on the parameter data samples for the plurality of elements. Generating the synthetic data samples includes, for a pair of parameter data samples, combining the pair of parameter data samples to form a synthetic data sample only if the synthetic data sample is consistent with a fundamental domain requirement associated with the plurality of elements A first model is trained (306) using the synthetic data samples to predict the operating parameter setting, and the operating parameter setting for the element is predicted (308) using the model. Related computer program products and systems are also disclosed.

Description

PREDICTION OF CONFIGURABLE SYSTEM PARAMETERS USING SYNTHETIC SAMPLES GENERATED IN COMPLIANCE WITH FUNDAMENTAL DOMAIN REQUIREMENTTECHNICAL FIELD

[0001] The present disclosure relates to system configuration, and in particular to systems and methods for determining operational parameters of wireless communication systems.BACKGROUND

[0002] In wireless communication systems, there are many configurable operational parameters of network equipment, such as base stations or antennas, that can be configured by a network operator. The settings chosen by the operator can affect the operation of the network equipment, which in turn can affect the operation of the overall network in terms of performance indicators such as efficiency, capacity, throughput, etc.

[0003] For example the electrical tilt of a base station antenna is a configurable operational parameter of the antenna. The electrical tilt of an antenna can affect network performance parameters such as coverage area and / or interference levels. Thus, determination of optimal tilt for an antenna is an important aspect of improving network performance. Selecting the appropriate or optimal tilt for an antenna can reduce interference, close gaps in the network coverage area, and / or increase the coverage area, which can improve the performance of a network and / or reduce the energy requirements of the network.

[0004] Figure 1 illustrates an antenna 100, which may, for example, be a towermounted antenna of a base station in a wireless communication network. The antenna 100 is characterized by a mechanical tilt which mechanically orients the antenna to point in a first downward direction 102 relative to horizontal. Using beamforming techniques, a main lobe of an antenna beam 110 generated by the antenna 100 can be directed to have an electrical tilt relative to the direction of orientation of the antenna 100. Thus, a total tilt of the antenna 100 relative to the horizontal direction is equal to the sum of the mechanical tilt and the electrical tilt of the antenna 100, which causes the antenna beam 110 to be directed in a second downward direction 104. As used herein, the term “antenna tilt angle,” “tilt angle” or simply “tilt” may refer to a total antenna tilt angle or only to an electrical tilt angle depending on the implementation.

[0005] Figure 2 illustrates elements of a wireless communication system including a first base station antenna 100A and a second base station antenna 100B . The first base stationantenna 100A has a first downward tilt angle that causes the first antenna 1OOA to have a first coverage area 200A. The second base station antenna 100B has a second downward tilt angle that causes the second antenna 100B to have a second coverage area 200B. The coverage area of an antenna is related to the total tilt of the antenna, which is in turn affected by the electrical tilt of the antenna. For example, typically, when the electrical tilt angle of an antenna is increased, the coverage area is typically decreased. It will be appreciated, however, that the coverage area of an antenna may be affected by many factors, including the topography of the area in which the antenna is located and the presence or absence of scattering structures, such as buildings, towers, etc., near the antenna. Thus, two antennas with identical tilt angles may have different coverage areas.

[0006] In the example illustrated in Figure 2, because the first antenna 100A and the second antenna 100B are in proximity to each other, the coverage areas 200A, 200B of the respective first antenna 100A and second antenna 100B may overlap within an area 210. Within the area of overlap 210, signals transmitted / received by the first antenna 100A may interfere with signals transmitted / received by the second antenna 100B, and vice-versa. Accordingly, selecting an electrical tilt for an antenna may have an effect on a level of interference between neighboring base stations, which in turn affects the overall level of interference within the wireless communication system. The level of interference within the communication system can impact performance aspects of the wireless communication system, such as the efficiency, capacity and / or throughput of the system.

[0007] A tilt angle recommendation for an antenna is traditionally generated as a part of a network planning process with the help of network planning software and subject matter expert input. However, there is interest in developing a more sophisticated approach for antenna tilt angle optimization.

[0008] This problem has been addressed from different perspectives. Two major classes of approaches are self-planning and self-optimization. Self-planning relies on a system model to find the best antenna settings in terms of chosen network performance measures. Once a system model is available, a suitable optimization algorithm (such as brute-force enumeration, simulated annealing, evolutionary algorithm, etc.) is used to find the optimum tilt. Self-optimization methods for tilt prediction does not use a system model, but rather makes use of live measurements to adjust tilts following simple control rules.

[0009] Later, other approaches have been proposed based on, for example, Bayesian and other optimization techniques. More recently Reinforcement Learning (RL) and Safe RL(SRL) have been proposed, as well as and techniques based on graph neural networks, have been proposed.

[0010] Many control-based approaches presume that multiple tilt adjustments can be performed in a live network. However, because tilt adjustment is a cost sensitive procedure, such approaches may be prohibitive in practice and hence may limit the application and / or scalability of such approaches.

[0011] Both complex simulation (e.g., simulation based optimal tilt search) and long iterative solution-based approaches (e.g., RL based optimal tilt search) are computation intensive. This leads to certain challenges. For example, it may be difficult to scale up a tilt prediction process for thousands of sites on an ongoing basis. Additionally, performing iterative tuning of antenna tilt angles on a live network may be impractical because frequent interventions / changes in a live network may degrade network performance.

[0012] Such existing approaches may be not suitable for tilt prediction for sites that are yet to be launched. When a group of cells are launched for the first time, there is no prior performance data to use as model inputs. In such a scenario, application of existing approaches to provide reasonable tilt prediction may be limited because running a simulation or iterative process without prior data is difficult and more prone to high prediction error.SUMMARY

[0013] A method of generating a prediction of an operating parameter setting for an element in a system according to some embodiments includes collecting (302) parameter data samples for a plurality of elements in the system, wherein the parameter data samples include covariate parameters associated with the plurality of elements, generating (304) synthetic data samples based on the parameter data samples for the plurality of elements, wherein generating the synthetic data samples includes, for a pair of parameter data samples, combining the pair of parameter data samples to form a synthetic data sample only if the synthetic data sample is consistent with a fundamental domain requirement associated with the plurality of elements, training (306) a first model using the synthetic data samples to predict the operating parameter setting, and predicting (308) the operating parameter setting for the element using the model.

[0014] The method may further include adjusting the operating parameter setting of the element in accordance with the predicted operating parameter setting.

[0015] The first model may include a regression model.

[0016] The method may further include, after generating the prediction of the operating parameter setting, applying a second model to generate a prediction of an operating performance measurement that is expected to be achieved after applying the operatingparameter setting, and adjusting the operating parameter setting based on the prediction of the operating performance measurement.

[0017] In some embodiments, the element includes an antenna, the system includes a wireless communication system, the operating parameter setting includes an electrical tilt angle of the antenna, the fundamental domain requirement includes a relationship between antenna tilt and expected range of the antenna, the synthetic data samples include a source tilt angle, a source range, a destination tilt angle and a destination range of the antenna, and the first model has source tilt angle, source range and predicted range as inputs and has destination tilt angle as an output. It can be noted that in the input data set, other operating parameters may include, but are not limited to, antenna height, horizontal beam width, RS power, antenna type and geographical parameters such as area type, clutter type, etc.

[0018] The operating performance measurement may include a range of the antenna. The second model may be trained using performance data associated with a cell of the wireless communication system in which the antenna operates. In some embodiments, the performance data includes reference signal received power, RSRP, measurements and / or channel quality indicator, CQI, measurements, and / or any other parameter included in the first model. The fundamental domain requirement may specify that an increase in tilt angle should correspond to a decrease in antenna range.

[0019] In some embodiments, generating the synthetic data samples includes obtaining a plurality of initial data samples for antennas in the wireless communication system, wherein each of the plurality of initial data samples includes an antenna tilt angle and an estimated range for the antenna, and, for each pair of the initial data samples, determining if a combination of the pair of initial data samples would result in a synthetic data sample that complies with the fundamental domain requirement.

[0020] The method may further include limiting the adjustment of the operating parameter setting based on a previous value of the operating parameter setting.

[0021] Some embodiments provide a computer program product including a non- transitory storage medium that contains computer program instructions for performing a method as described above.1

[0022] A parameter setting control system according to some embodiments includes a processing circuit, and

[0023] a memory coupled to the processing circuit. The memory stores computer program instructions that, when executed by the processing circuit, causes the processing circuit to perform operations including collecting (302) parameter data samples for a pluralityof elements in the system, wherein the parameter data samples include covariate parameters associated with the plurality of elements, generating (304) synthetic data samples based on the parameter data samples for the plurality of elements, wherein generating the synthetic data samples includes, for a pair of parameter data samples, combining the pair of parameter data samples to form a synthetic data sample only if the synthetic data sample is consistent with a fundamental domain requirement associated with the plurality of elements, training (306) a first model using the synthetic data samples to predict the operating parameter setting, and predicting (308) the operating parameter setting for the element using the model.BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 illustrates an antenna for a base station of a wireless communication system.

[0025] Figure 2 illustrates elements of a wireless communication system.

[0026] Figure 3 illustrates operations of systems / methods according to some embodiments.

[0027] Figure 4 illustrates operations for generating synthetic data samples according to some embodiments.

[0028] Figure 5 illustrates operations of systems / methods for generating a parameter prediction according to some embodiments.

[0029] Figure 6 shows an example of a communication system in accordance with some embodiments.

[0030] Figure 7 shows a UE in accordance with some embodiments.

[0031] Figure 8 shows a network node in accordance with some embodiments.

[0032] Figure 9 illustrates components of a parameter setting control system according to some embodiments.

[0033] Figure 10 illustrates various functional modules that may be stored in the memory of the parameter setting control system.DETAILED DESCRIPTION OF EMBODIMENTS

[0034] There currently exist certain challenge(s). As discussed above, optimization of antenna tilt angles in a wireless communication network has been addressed primarily from the standpoint of self-optimization algorithms. In such approaches, optimality is typically achieved by adjusting tilt based on live measurements following predetermined control rules. A limitation of such a control-based approach is that there is no guarantee that a tilt setting determined by the system at the cell level will comply with the fundamental domainrequirement of antenna tilt that when it is needed to increase a cell’s serving range, the current antenna tilt should be decreased, vice-versa. If this fundamental domain requirement is not complied with, changing the antenna tilt at cell level may affect the performance of a group of cells in unpredictable ways.

[0035] An antenna tilt prediction that complies with the fundamental domain requirement is referred to herein as a “legitimate tilt prediction.” For example, if the serving range of a cell is greater than the intended range for the cell, then the predicted tilt angle should reduce the range of the cell. To reduce the range of the cell, the predicted tilt angle that is predicted by the model should be increased relative to a previous tilt angle. If the model predicts a tilt angle that complies with this requirement (i.e., is greater than the previous tilt angle), the prediction is said to be “legitimate.” However, if the model predicts a tilt angle that is less than the previous tilt angle, the tilt prediction is not legitimate. If the legitimacy of a predicted tilt angle cannot be ensured, the expected behavior of the cells, individually and also collectively, becomes unpredictable.

[0036] Certain aspects of the disclosure and their embodiments may provide solutions to these or other challenges. In particular, some embodiments described herein provide a regression-based approach for parameter prediction that is combined with smart data generation to encourage legitimate parameter prediction.

[0037] Figure 3 illustrates operations according to some embodiments. As shown therein, systems / methods according to some embodiments collect parameter data for a plurality of devices (block 302). For example, the systems / methods may collect antenna tilt angle data for a plurality of antennas. Using the collected data, the systems / methods generate synthetic training data that is consistent with a fundamental domain requirement (block 304). For example, some embodiments generate synthetic training data for training a regression model for predicting an antenna tilt angle that complies with the fundamental domain requirement that an increase in antenna tilt angle should correspond to a decrease in cell range / coverage area. A prediction model is then trained using the synthetic training data (block 306) and the trained model used to predict a parameter setting, such as an antenna tilt angle, for a device (block 308).

[0038] For data acquisition, some embodiments may use covariate data that is readily obtained from network monitoring systems to generate unique profiles or clusters with which virtual experimental data can be extracted. For example, for antenna tilt angle prediction, some embodiments may use cell-level attributes such as antenna height, antenna type, horizontal antenna beam width, sector type (e.g., indoor / outdoor etc.), clutter type, andcurrent received signal (RS) power as covariate data. Antennas with identical sets of values of these covariates are grouped into unique clusters that can be used to generate synthetic data based on virtual experiments as described in more detail below.

[0039] For antenna tilt angle prediction, a data point may also include an electrical tilt angle and estimated range of the cell. Some embodiments may also use timing advance data for estimation of existing cell range and intended cell range that the cell is aimed to cover. Optionally, some embodiments may employ RSRP and CQI for fine-tuning an antenna tilt angle prediction as described below.

[0040] Synthetic data points are generated by combining pairs of sample data points in a virtual experiment that satisfies the fundamental domain requirement. That is all possible pairs of data points are considered, and pairs of data points that do not satisfy the fundamental domain requirement are discarded. If a pair of data points does satisfy the fundamental domain requirement, the pair of data points is combined into a single “legitimate” synthetic data point that is used for model training.

[0041] The use of “smart” or “legitimate” synthetic data samples as described above for model training may help to ensure that the fundamental domain requirement (e.g., the tiltrange relationship in the context of antenna tilt angle prediction) is being learned by the parameter prediction model.

[0042] One or more parameter prediction models are then trained using the synthetic data samples. For example, multiple regression models may be trained, and a model may be chosen based on one or more metrics. In some embodiments, competing models may be ranked based on a directional alignment metric that indicates a degree of legitimacy achieved by the model, i.e., how effective the model is at generating legitimate parameter predictions that comply with the fundamental domain requirement.

[0043] In some embodiments, a secondary, or Stage 2, model is used to evaluate the parameter prediction. For example, in the context of antenna tilt angle prediction, a secondary model may be used to generate an estimate of the cell range that will result from implementation of the predicted antenna tilt angle. In some embodiments, the secondary model may use RSRP and / or CQI data from a cell to estimate the cell range that is expected to be achieved after implementation of the predicted antenna tilt angle.

[0044] In the secondary model, RSRP and CQI data are used as input data and cell coverage is an output variable. A plurality of alternative “legitimate” tilt angle candidates are identified (i.e., tilt angle candidates that comply with the fundamental domain requirement). Each such alternative tilt angle candidate that is generated is then evaluated to determine anestimated range. A tilt angle candidate with the smallest absolute difference between the estimated range and the desired or intended range may be selected as the predicted tilt angle to be applied to the antenna. This approach may cap the optimal tilt angle determined by the tilt angle prediction model by a domain knowledge driven threshold.

[0045] According to some embodiments, the predicted tilt angle for an antenna may be scored based on whether or not the cell is currently active (so that historical data is available) or inactive. If the cell is active, the systems / methods may collect available historical operational data (and impute data where it is not available), generate synthetic data as described above, and run a parameter prediction model, such as a regression model, to generate a prediction of the parameter setting.

[0046] If the cell is inactive (e.g., not yet launched), the systems / methods may use configuration data such as the covariate data specified by antenna height, antenna type, sector type and cluster type as described above as a basis to impute other values such as serving range and tilt, and run the regression model to predict the optimal tilt.

[0047] Certain embodiments may provide one or more of the following technical advantage(s). Some embodiments described herein provide an approach that is data driven. Systems / methods described herein use historical data of existing sites to build a tilt prediction model that can be re-trained and thus can be kept up to date easily.

[0048] A regression-based approach as described herein may be easy to scale and automate, easy to iterate and can be integrated for closed loop actuation. Moreover, systems / methods described herein may work for systems that are yet to be deployed where no historical data is available. Such systems / methods may be used to generate legitimate parameter predictions through modeling based on synthetic samples generated based on a fundamental domain requirement. Because the synthetic data samples are generated in compliance with the fundamental domain requirement, the prediction model may predict parameters that are also in compliance with the fundamental domain requirement with a high probability.

[0049] Some systems / methods described herein may validate the legitimacy of a predicted parameter based on the fundamental domain requirement. For example, when the predicted parameter is an antenna tilt angle, some embodiments may validate a predicted antenna tilt angle using a metric referred to herein as directional alignment, which measures the alignment of a predicted tilt with the fundamental domain concept. That is, in some embodiments, if the existing range is greater than the intended range, the predicted tilt should be higher than the existing tilt, and vice-versa.

[0050] As described in more detail below, the pre-requisite of the directional alignment metric is the new feature obtained from synthetic sample generation, which in turn is dependent on the abstract view of the data as an outcome of a virtual tilt changing experiment.

[0051] Because validated synthetic data samples are used for training, some systems / methods described herein may work reasonably well with poor quality data, i.e., when good quality samples are not available in abundance.

[0052] Some embodiments may further estimate the performance of a predicted parameter based on a second level of modeling. For example, some embodiments may further estimate the performance of a predicted antenna tilt angle to achieve an intended range based on signal measurements, such as reference signal received power (RSRP) and channel quality information (CQI) when such data is available. The predicted tilt can be adjusted based on the second model built on signal measurement data along with other covariate data used to build the first model.

[0053] The performance of a predicted tilt angle can be measured as the expected difference of the intended range with the predicted range when deployed. The performance of a predicted tilt angle can be estimated before its deployment using the stage II model and can be measured post its deployment from collected timing advance data. Before deployment, the performance can be estimated as the expected difference of the intended range with the predicted range (computed from the stage II model). Post deployment, the performance can be measured as difference of the intended range with post deployment coverage (computed from post deployment timing advance data collected from field).

[0054] Some systems / methods described herein may be less cost intensive both in network planning and human resources and in computational resources in comparison to existing approaches.

[0055] Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art. Although embodiments are described herein primarily in the context of a system / method for predicting an electrical antenna tilt angle of a base station antenna in a wireless communication system, it will be appreciated that the systems / methods described herein may be used to predict a different system parameter of a wireless communication system or other type of system.

[0056] Preprocessing and Feature Engineering

[0057] Various cell level attributes may be used as the training data for model building, including attributes such as antenna height, antenna type, horizontal beam width,sector type, clutter type, and current received signal (RS) power. Such values, which typically have static or slowly changing behavior, are referred to herein as “covariate” values. Additional data that can be used as input features may include current electrical tilt angle, timing advance (TA) data, the intended or desired cell range, and optionally, RSRP and CQI.

[0058] The current cell range may be estimated from timing advance data. In particular, for each cell, timing advance data provides counts of user equipment (UE) traces at fixed distance bins, measured from the cell tower, spanning the possible coverage area of a cell. The estimated coverage of a cell is considered to be the distance at which 90% of the counts of UE traces are observed.

[0059] After determining the current cell range for a plurality of cells, good quality samples are extracted from the cells. For example, all cells which have current cell range within + / - 8% of the intended cell range may be defined as good quality samples. The percentage threshold of + / - 8% may be user-configurable based on the amount of data that is available after filtering. If the amount of good quality data is less than needed, this threshold can be increased.

[0060] Synthetic Sample Generation

[0061] Starting with initial training samples described above having antenna tilt angle and estimated cell range, some embodiments generate synthetic samples that may be used to train an antenna tilt angle prediction model. The synthetic samples maybe thought of as the outcome of virtual experiments involving the initial training samples, and include values such as source tilt, source range, intended range and destination tilt. Generation of the synthetic samples is described below in detail.

[0062] Cells in a wireless communication system can be grouped into multiple clusters such that within one cluster the covariate values are the same, while cells belonging to different clusters have different covariate values. In a practical system, the possible number of unique sets of covariate values is limited. Thus, within a wireless communication system, there may be multiple cells having the same covariate values, and thus multiple cells within each cluster.

[0063] Initial data points corresponding to antennas in the wireless communication system may therefore be identified that include a cluster identifier, an electrical tilt and a current range of the antenna. These initial data points may be used to generate synthetic data points that are the product of virtual “experiments” as described below.

[0064] For example, consider a set of cells in a wireless communication network for which the values of the covariates shown in Table 1 are observed.Table 1 - Example Cluster Covariate Values

[0065] This collection of covariate values may define a particular profile or cluster(e.g., Cluster A) that may describe multiple antennas within the wireless communication system. That is, there may be many antennas within the wireless communication system that have the same collection of covariate values, but that have different values of electrical antenna tilt angle and serving range.

[0066] Table 2 illustrates data points corresponding to three such cells in which each cell’s data, arranged in a row, corresponds to one data point.Table 2 : Initial Data Samples By Cluster

[0067] It will be appreciated that even though these data rows correspond to different cells, all the covariates (that influence the tilt and range values) are same, and thus the cells belong to the same cluster (Cluster A). Data points involving the same cluster can therefore be combined in virtual experiments to create synthetic data points. Given the data points such as those shown in Table 2, different virtual experiments may be performed by combining pairsof data points as initial or starting conditions and final or ending conditions. A data point corresponding to initial condition is termed as source data point and the other as destination data point. Four new variables are defined for the synthetic data points, namely, source tilt, source range, intended range, and destination tilt. The virtual experiment considered here is changing the source tilt to destination tilt and the outcome can be abstracted as the change of source range to destination range. Hence, source tilt is the electrical antenna tilt angle before adjustment of the tilt angle, and destination tilt is the electrical antenna tilt angle after adjustment of the tilt angle. Source range is the cell range prior to adjustment of the tilt angle and destination range is the estimated cell range after adjustment of the tilt angle.

[0068] For example, considering the data points 1 and 2 represented by the first two rows of Table 2, a virtual experiment may be constructed by considering data point 1 as a starting point and data point 2 as an ending point of an experiment. That is, data point 2 may be considered as being obtained from data point 1 by starting with a cell having an electrical antenna tilt angle of 40 degrees and a range of 0.313 km, as the source tilt and source range and then changing the electrical antenna tilt angle to 50 degrees as shown in row 2 of Table 2. The resulting range of the cell is 0.219 km.

[0069] By merging the data points 1 and 2 of Table 2, a synthetic data point S 1 may be constructed as shown in Table 3.Table 3 - Legitimate Synthetic Data Sample

[0070] After constructing a synthetic data point, the systems / methods may evaluate whether the synthetic data point complies with a fundamental domain requirement, for example, whether increasing the electrical tilt angle results in a decrease in cell range. In this case, synthetic data point S 1 does comply with the fundamental domain requirement, because increasing the electrical antenna tilt angle from 40 degrees to 50 degrees results in a decrease in the cell range from 0.313 km to 0.219 km. Thus, synthetic data point SI shown in Table 3 is considered to be a valid or legitimate synthetic data point.

[0071] Note that not all pairs of data points in shown in Table 2 can be merged to create a valid or legitimate synthetic data point. Consider for example synthetic data point S2that is formed by merging data points 1 and 3 of Table 2. The resulting synthetic data point S2 is shown in Table 4:Table 4 - Illegitimate Synthetic Data Sample

[0072] In this case, increasing the electrical antenna tilt angle from 40 to 45 degrees resulted in an increase in the cell range in the virtual experiment. Because this violates the fundamental domain requirement that increasing the electrical antenna tilt angle should decrease the cell range, this synthetic data sample is considered illegitimate, and would thus be discarded and not used for model training.

[0073] This process may be repeated for each pair of initial samples to obtain a set of legitimate synthetic data samples. Table 5 shows legitimate synthetic data samples that can be extracted from the initial data samples of Table 2.Table 5 - Synthetic Data Samples

[0074] Note that for each synthetic data sample shown in Table 5, the fundamental domain requirement that increasing the antenna tilt angle decreases the cell range, and vice- versa, is satisfied. Also note that the set of covariates that have same set of values in each row will appear as other data dimensions.

[0075] Operations for the generation of synthetic data samples are illustrated in Figure 4. As shown therein, initial data samples are provided in tabular format in which a row corresponds to a cell and corresponding columns hold observed data on that cell (block 402).A new column corresponding to cluster is derived by concatenating values of covariate features, and the data samples are grouped into rows corresponding to unique clusters (block 404).

[0076] For each cluster, all possible pairs of initial data points (corresponding to rows of data) are identified (block 406). The systems / methods then loop though each identified pair at blocks 408-414. At block 408, the next pair is selected, and at block 410, it is determined whether or not a combination of the selected pair would satisfy the fundamental domain requirement, e.g., the tilt-range relationship discussed above. If so, a synthetic data point is generated from the combination of the pair of data points by creating new feature and group rows according to unique clusters (block 412), and otherwise the pair of data points is disregarded. This process is repeated until the last pair of data points is reached at block 414. The resulting set of legitimate synthetic data points is then used for training a model, such as a regression model for predicting a system parameter such as an electrical antenna tilt angle, as described below.

[0077] Because the synthetic training data is generated only from data point pairs that fulfill the fundamental domain requirement, the synthetic data samples, which are used to train the parameter prediction model, carry information relating to the fundamental domain requirement explicitly through the augmented new dimensions, namely, source_tilt , source_range , intended_range and destination_tilt. In addition, the variation of the tilt-range relation across different cells is reflected in the synthetic data samples.

[0078] The use of modeling to predict a system parameter such as electrical antenna tilt may involve a single model, such as a regression model, or may include multiple models. For example, the regression model may be employed in a first stage, and then a second stage model may be used to refine the prediction.

[0079] In a first stage, a model, such as a regression model, is trained with destination_tilt as the target variable and all other variables, namely, covariates corresponding to a cluster, source_tilt, source_range and intended_range as input variables.

[0080] In some embodiments, a pool of data containing all of the synthetic data samples is constructed, and a subset of the data, e.g., 75% of the samples, are chosen at random from the data pool for use as training data.

[0081] A suite of models may be evaluated at this stage, and one or more of such models that show good directional alignment in the predicted tilt may be chosen for full training. The resulting models are then evaluated according to a metric, such as mean absoluteprediction error (MAPE). The model having the lowest value of MAPE may be chosen for use in parameter prediction.

[0082] In some embodiments, the performance of a stage 1 model may be evaluated by calculating a directional alignment of the model. For example, from a cell’s current range, current tilt and intendent range, the alignment of the predicted tilt with the fundamental domain requirement concept may be computed as follows, if the existing range is greater than the intended range and the predicted tilt is greater than the existing tilt, or if the existing range is less than the intended range and the predicted tilt is less than the existing tilt, then the alignment is equal to one, and is equal to zero otherwise. The final measure of directional alignment of a model is computed as percentage of all alignments over all tilt predictions for the cells in the test data.

[0083] In some embodiments a value of MAPE of the predicted tilt may be computed from the test data among the top N directionally aligned models, and the model having the lowest value of MAPE among the top N directionally aligned models may be selected for use as the stage 1 model.

[0084] In some embodiments, based on the availability of appropriate training data, a second stage model may be employed to refine the parameter prediction made by the first stage model. For example, in the case of antenna tilt angle prediction, a second stage model may be constructed that estimates the resulting cell range that is expected to be obtained when the predicted antenna tilt angle is implemented. The second stage model may take as inputs cell-level performance data, such as RSRP and CQI along with antenna tilt angle and generate an estimated cell range.

[0085] As with the stage one model, multiple models may be trained, and the model with the best performance in terms of MAPE may be selected for use in the second stage.

[0086] When a cell range corresponding to a predicted tilt from the stage 1 model is predicted using the stage 2 model, the closer the predicted range value is to the intended range, the better the tilt prediction is. This criterion is used to perform a calibration of the predicted tilt. If the predicted range is beyond the threshold considered in the data preparation stage for good sample filtering (e.g., within + / - 8% of the intended cell range), a calibration may be performed as described in the example below.

[0087] For example, assume that for an existing tilt of 60 degrees, an existing range 0.4 km and intended range of 0.8 km, the predicted tilt value obtained from the stage 1 model is 40 degrees.

[0088] Assume further that based on these values, the cell range estimated by the stage 2 model corresponding to the predicted tilt of 40 degrees is more than 8% different than the intended range.

[0089] In that case, a potential alternative tilt set is constructed consisting of all possible tilt values that comply with the fundamental domain requirement, which dictates that the predicted tilt must be less than the existing tilt, since the intended range is greater than the existing range. Thus, the potential alternative tilt set will be 0, 5, 10, 15, 20, 25, 30 and 35 degrees.

[0090] For each tilt value in the set of potential tilt values, a corresponding value of cell range is computed using the stage 2 model. An antenna tilt is then selected from the set of potential values for which the absolute distance between the estimated range and the intended range is reduced and preferably minimized. Thus, for example, if the stage 2 model predicts that the absolute distance between the estimated range and the intended range is the smallest for a tilt angle of 15 degrees, then 15 degrees is used for the antenna tilt angle.

[0091] In some embodiments, the change to the tilt angle as a result of the calibration may be made limited due to domain governed variation limit so that the tilt angle does not change by more than a predetermined amount from the existing tilt angle. For example, in some embodiments, the change to the tilt angle may be limited such that the predicted tilt angle is no more than 40 degrees different from the existing tilt angle. In the foregoing example, the existing tilt angle is 60 degrees. Thus, the tilt angle of the antenna can be reduced to no less than 60-40=20 degrees. Thus, instead of a tilt angle of 15 degrees, a tilt angle of 20 degrees is used.

[0092] Figure 5 illustrates operations of systems / methods for generating a prediction of antenna tilt angle according to some embodiments. Referring to Figure 5, synthetic data samples are generated as described above at block 502. The systems / methods then determine if the cell for which antenna tilt is being predicted is already active (block 504). If not, then the systems / methods may impute values of unknown covariates at block 506 so that the cell can be identified with a cluster at block 507.

[0093] At block 508, the stage 1 model is applied to generate a predicted antenna tilt angle for the cell.

[0094] At block 510, the systems / methods determine whether cell-level data that is needed for the stage 2 model, such as RSRP and / or CQI data, is available. If not, operations proceed to block 514 where the calibration is limited and the predicted antenna tilt is applied to the cell at block 516 before operations terminate.

[0095] If the cell-level data is available, then at block 512, the systems / methods use the stage 2 model to estimate the range of the cell that will be obtained using the predicted tilt, and calibrate the predicted tilt accordingly.

[0096] At block 514, the systems / methods may optionally limit the calibration so that the resulting antenna tilt angle is less than a predetermined difference from an existing antenna tilt angle.

[0097] The calibrated antenna tilt angle is then applied to the cell at block 516, and operations terminate.

[0098] The performance improvement of cell-level coverage using systems / methods described above may be evaluated as follows.

[0099] For a set of cells for which it is desired to change the tilt for coverage improvement, cell trace data is collected for a desired day and time window to be compared with post tilt implementation performance. The best stage 1 model is implemented in a live network for the set of cells. After implementing the predicted tilt angles for the cells in the set of cells, the cells are allowed to operate for a period of time during which cell trace data is collected for the same day and time window corresponding pre-tilt implementation.

[0100] The cell coverage area may then be estimated from timing advance data. A change of number of cells that has estimated coverage within + / - 5% of the intended range after tilt implementation is determined and compared to pre-tilt implementation data. An increase of number of cells falling within + / - 5% of the corresponding intended range after tilt implementation indicates an increase of cell level performance driven by the implemented tilt.

[0101] A network level performance evaluation may be generated from cell trace data as follows. Pre-determined metrics such as CQI, RSRP, RSRQ are computed at the network level in a pre-tilt implementation and a post-tilt implementation scenario. If the values are improved in the post-tilt implemented data, it is considered to be a performance improvement driven by implemented tilt.

[0102] Figure 6 shows an example of a communication system 600 in accordance with some embodiments.

[0103] In the example, the communication system 600 includes a telecommunication network 602 that includes an access network 604, such as a radio access network (RAN), and a core network 606, which includes one or more core network nodes 608. The access network 604 includes one or more access network nodes, such as network nodes 610a and 610b (one or more of which may be generally referred to as network nodes 610), or any other similar 3rdGeneration Partnership Project (3GPP) access nodes or non-3GPP accesspoints. Moreover, as will be appreciated by those of skill in the art, a network node is not necessarily limited to an implementation in which a radio portion and a baseband portion are supplied and integrated by a single vendor. Thus, it will be understood that network nodes include disaggregated implementations or portions thereof. For example, in some embodiments, the telecommunication network 602 includes one or more Open-RAN (ORAN) network nodes. An ORAN network node is a node in the telecommunication network 602 that supports an ORAN specification (e.g., a specification published by the O-RAN Alliance, or any similar organization) and may operate alone or together with other nodes to implement one or more functionalities of any node in the telecommunication network 602, including one or more network nodes 610 and / or core network nodes 608.

[0104] Examples of an ORAN network node include an open radio unit (O-RU), an open distributed unit (O-DU), an open central unit (O-CU), including an O-CU control plane (O-CU-CP) or an O-CU user plane (O-CU-UP), a RAN intelligent controller (near-real time or non-real time) hosting software or software plug-ins, such as a near-real time control application (e.g., xApp) or a non-real time control application (e.g., rApp), or any combination thereof (the adjective “open” designating support of an ORAN specification). The network node may support a specification by, for example, supporting an interface defined by the ORAN specification, such as an Al, Fl, Wl, El, E2, X2, Xn interface, an open fronthaul user plane interface, or an open fronthaul management plane interface. Moreover, an ORAN access node may be a logical node in a physical node. Furthermore, an ORAN network node may be implemented in a virtualization environment (described further below) in which one or more network functions are virtualized. For example, the virtualization environment may include an O-Cloud computing platform orchestrated by a Service Management and Orchestration Framework via an O-2 interface defined by the O-RAN Alliance or comparable technologies. The network nodes 610 facilitate direct or indirect connection of user equipment (UE), such as by connecting UEs 612a, 612b, 612c, and 612d (one or more of which may be generally referred to as UEs 612) to the core network 606 over one or more wireless connections.

[0105] Example wireless communications over a wireless connection include transmitting and / or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and / or other types of signals suitable for conveying information without the use of wires, cables, or other material conductors. Moreover, in different embodiments, the communication system 600 may include any number of wired or wireless networks, network nodes, UEs, and / or any other components or systems that may facilitate or participate in the communication of data and / or signals whether via wired or wireless connections. Thecommunication system 600 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.

[0106] The UEs 612 may be any of a wide variety of communication devices, including wireless devices arranged, configured, and / or operable to communicate wirelessly with the network nodes 610 and other communication devices. Similarly, the network nodes 610 are arranged, capable, configured, and / or operable to communicate directly or indirectly with the UEs 612 and / or with other network nodes or equipment in the telecommunication network 602 to enable and / or provide network access, such as wireless network access, and / or to perform other functions, such as administration in the telecommunication network 602.

[0107] In the depicted example, the core network 606 connects the network nodes 610 to one or more hosts, such as host 616. These connections may be direct or indirect via one or more intermediary networks or devices. In other examples, network nodes may be directly coupled to hosts. The core network 606 includes one more core network nodes (e.g., core network node 608) that are structured with hardware and software components. Features of these components may be substantially similar to those described with respect to the UEs, network nodes, and / or hosts, such that the descriptions thereof are generally applicable to the corresponding components of the core network node 608. Example core network nodes include functions of one or more of a Mobile Switching Center (MSC), Mobility Management Entity (MME), Home Subscriber Server (HSS), Access and Mobility Management Function (AMF), Session Management Function (SMF), Authentication Server Function (AUSF), Subscription Identifier De-concealing function (SIDE), Unified Data Management (UDM), Security Edge Protection Proxy (SEPP), Network Exposure Function (NEF), and / or a User Plane Function (UPF).

[0108] The host 616 may be under the ownership or control of a service provider other than an operator or provider of the access network 604 and / or the telecommunication network 602, and may be operated by the service provider or on behalf of the service provider. The host 616 may host a variety of applications to provide one or more service. Examples of such applications include live and pre-recorded audio / video content, data collection services such as retrieving and compiling data on various ambient conditions detected by a plurality of UEs, analytics functionality, social media, functions for controlling or otherwise interacting with remote devices, functions for an alarm and surveillance center, or any other such function performed by a server.

[0109] As a whole, the communication system 600 of Figure 6 enables connectivity between the UEs, network nodes, and hosts. In that sense, the communication system may beconfigured to operate according to predefined rules or procedures, such as specific standards that include, but are not limited to: Global System for Mobile Communications (GSM); Universal Mobile Telecommunications System (UMTS); Long Term Evolution (LTE), and / or other suitable 2G, 3G, 4G, 5G standards, or any applicable future generation standard (e.g., 6G); wireless local area network (WLAN) standards, such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standards (WiFi); and / or any other appropriate wireless communication standard, such as the Worldwide Interoperability for Microwave Access (WiMax), Bluetooth, Z-Wave, Near Field Communication (NFC) ZigBee, LiFi, and / or any low-power wide-area network (LPWAN) standards such as LoRa and Sigfox.

[0110] In some examples, the telecommunication network 602 is a cellular network that implements 3GPP standardized features. Accordingly, the telecommunications network 602 may support network slicing to provide different logical networks to different devices that are connected to the telecommunication network 602. For example, the telecommunications network 602 may provide Ultra Reliable Low Latency Communication (URLLC) services to some UEs, while providing Enhanced Mobile Broadband (eMBB) services to other UEs, and / or Massive Machine Type Communication (mMTC) / Massive loT services to yet further UEs.

[0111] In some examples, the UEs 612 are configured to transmit and / or receive information without direct human interaction. For instance, a UE may be designed to transmit information to the access network 604 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network 604. Additionally, a UE may be configured for operating in single- or multi-RAT or multi-standard mode. For example, a UE may operate with any one or combination of Wi-Fi, NR (New Radio) and LTE, i.e. being configured for multi-radio dual connectivity (MR-DC), such as E-UTRAN (Evolved- UMTS Terrestrial Radio Access Network) New Radio - Dual Connectivity (EN-DC).

[0112] In the example, the hub 614 communicates with the access network 604 to facilitate indirect communication between one or more UEs (e.g., UE 612c and / or 612d) and network nodes (e.g., network node 610b). In some examples, the hub 614 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub 614 may be a broadband router enabling access to the core network 606 for the UEs. As another example, the hub 614 may be a controller that sends commands or instructions to one or more actuators in the UEs. Commands or instructions may be received from the UEs, network nodes 610, or by executable code, script, process, or other instructions in the hub 614. As another example, the hub 614 may be a data collector that acts as temporary storage for UE data and, in some embodiments, may perform analysis orother processing of the data. As another example, the hub 614 may be a content source. For example, for a UE that is a VR headset, display, loudspeaker or other media delivery device, the hub 614 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub 614 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub 614 acts as a proxy server or orchestrator for the UEs, in particular if one or more of the UEs are low energy loT devices.

[0113] The hub 614 may have a constant / persistent or intermittent connection to the network node 610b. The hub 614 may also allow for a different communication scheme and / or schedule between the hub 614 and UEs (e.g., UE 612c and / or 612d), and between the hub 614 and the core network 606. In other examples, the hub 614 is connected to the core network 606 and / or one or more UEs via a wired connection. Moreover, the hub 614 may be configured to connect to an M2M service provider over the access network 604 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes 610 while still connected via the hub 614 via a wired or wireless connection. In some embodiments, the hub 614 may be a dedicated hub - that is, a hub whose primary function is to route communications to / from the UEs from / to the network node 610b. In other embodiments, the hub 614 may be a non-dedicated hub - that is, a device which is capable of operating to route communications between the UEs and network node 610b, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0114] Figure 7 shows a UE 700 in accordance with some embodiments. As used herein, a UE refers to a device capable, configured, arranged and / or operable to communicate wirelessly with network nodes and / or other UEs. Examples of a UE include, but are not limited to, a smart phone, mobile phone, cell phone, voice over IP (VoIP) phone, wireless local loop phone, desktop computer, personal digital assistant (PDA), wireless cameras, gaming console or device, music storage device, playback appliance, wearable terminal device, wireless endpoint, mobile station, tablet, laptop, laptop -embedded equipment (LEE), laptop-mounted equipment (LME), smart device, wireless customer-premise equipment (CPE), vehicle, vehicle-mounted or vehicle embedded / integrated wireless device, etc. Other examples include any UE identified by the 3rd Generation Partnership Project (3GPP), including a narrow band internet of things (NB-IoT) UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.

[0115] A UE may support device-to-device (D2D) communication, for example by implementing a 3GPP standard for sidelink communication, Dedicated Short-Range Communication (DSRC), vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), or vehicle- to-everything (V2X). In other examples, a UE may not necessarily have a user in the sense of a human user who owns and / or operates the relevant device. Instead, a UE may represent a device that is intended for sale to, or operation by, a human user but which may not, or which may not initially, be associated with a specific human user (e.g., a smart sprinkler controller). Alternatively, a UE may represent a device that is not intended for sale to, or operation by, an end user but which may be associated with or operated for the benefit of a user (e.g., a smart power meter).

[0116] The UE 700 includes processing circuitry 702 that is operatively coupled via a bus 704 to an input / output interface 706, a power source 708, a memory 710, a communication interface 712, and / or any other component, or any combination thereof. Certain UEs may utilize all or a subset of the components shown in Figure 7. The level of integration between the components may vary from one UE to another UE. Further, certain UEs may contain multiple instances of a component, such as multiple processors, memories, transceivers, transmitters, receivers, etc.

[0117] The processing circuitry 702 is configured to process instructions and data and may be configured to implement any sequential state machine operative to execute instructions stored as machine -readable computer programs in the memory 710. The processing circuitry 702 may be implemented as one or more hardware-implemented state machines (e.g., in discrete logic, field-programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), etc.); programmable logic together with appropriate firmware; one or more stored computer programs, general-purpose processors, such as a microprocessor or digital signal processor (DSP), together with appropriate software; or any combination of the above. For example, the processing circuitry 702 may include multiple central processing units (CPUs).

[0118] In the example, the input / output interface 706 may be configured to provide an interface or interfaces to an input device, output device, or one or more input and / or output devices. Examples of an output device include a speaker, a sound card, a video card, a display, a monitor, a printer, an actuator, an emitter, a smartcard, another output device, or any combination thereof. An input device may allow a user to capture information into the UE 700. Examples of an input device include a touch- sensitive or presence- sensitive display, a camera (e.g., a digital camera, a digital video camera, a web camera, etc.), a microphone, a sensor, amouse, a trackball, a directional pad, a trackpad, a scroll wheel, a smartcard, and the like. The presence- sensitive display may include a capacitive or resistive touch sensor to sense input from a user. A sensor may be, for instance, an accelerometer, a gyroscope, a tilt sensor, a force sensor, a magnetometer, an optical sensor, a proximity sensor, a biometric sensor, etc., or any combination thereof. An output device may use the same type of interface port as an input device. For example, a Universal Serial Bus (USB) port may be used to provide an input device and an output device.

[0119] In some embodiments, the power source 708 is structured as a battery or battery pack. Other types of power sources, such as an external power source (e.g., an electricity outlet), photovoltaic device, or power cell, may be used. The power source 708 may further include power circuitry for delivering power from the power source 708 itself, and / or an external power source, to the various parts of the UE 700 via input circuitry or an interface such as an electrical power cable. Delivering power may be, for example, for charging of the power source 708. Power circuitry may perform any formatting, converting, or other modification to the power from the power source 708 to make the power suitable for the respective components of the UE 700 to which power is supplied.

[0120] The memory 710 may be or be configured to include memory such as random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disks, optical disks, hard disks, removable cartridges, flash drives, and so forth. In one example, the memory 710 includes one or more application programs 714, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data 716. The memory 710 may store, for use by the UE 700, any of a variety of various operating systems or combinations of operating systems.

[0121] The memory 710 may be configured to include a number of physical drive units, such as redundant array of independent disks (RAID), flash memory, USB flash drive, external hard disk drive, thumb drive, pen drive, key drive, high-density digital versatile disc (HD-DVD) optical disc drive, internal hard disk drive, Blu-Ray optical disc drive, holographic digital data storage (HDDS) optical disc drive, external mini-dual in-line memory module (DIMM), synchronous dynamic random access memory (SDRAM), external micro-DIMM SDRAM, smartcard memory such as tamper resistant module in the form of a universal integrated circuit card (UICC) including one or more subscriber identity modules (SIMs), such as a US IM and / or IS IM, other memory, or any combination thereof. The UICC may forexample be an embedded UICC (eUICC), integrated UICC (iUICC) or a removable UICC commonly known as ‘SIM card.’ The memory 710 may allow the UE 700 to access instructions, application programs and the like, stored on transitory or non-transitory memory media, to off-load data, or to upload data. An article of manufacture, such as one utilizing a communication system may be tangibly embodied as or in the memory 710, which may be or comprise a device-readable storage medium.

[0122] The processing circuitry 702 may be configured to communicate with an access network or other network using the communication interface 712. The communication interface 712 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna 722. The communication interface 712 may include one or more transceivers used to communicate, such as by communicating with one or more remote transceivers of another device capable of wireless communication (e.g., another UE or a network node in an access network). Each transceiver may include a transmitter 718 and / or a receiver 720 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover, the transmitter 718 and receiver 720 may be coupled to one or more antennas (e.g., antenna 722) and may share circuit components, software or firmware, or alternatively be implemented separately.

[0123] In the illustrated embodiment, communication functions of the communication interface 712 may include cellular communication, Wi-Fi communication, LPWAN communication, data communication, voice communication, multimedia communication, short-range communications such as Bluetooth, near-field communication, location-based communication such as the use of the global positioning system (GPS) to determine a location, another like communication function, or any combination thereof. Communications may be implemented in according to one or more communication protocols and / or standards, such as IEEE 802.11, Code Division Multiplexing Access (CDMA), Wideband Code Division Multiple Access (WCDMA), GSM, LTE, New Radio (NR), UMTS, WiMax, Ethernet, transmission control protocol / intemet protocol (TCP / IP), synchronous optical networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), and so forth.

[0124] Regardless of the type of sensor, a UE may provide an output of data captured by its sensors, through its communication interface 712, via a wireless connection to a network node. Data captured by sensors of a UE can be communicated through a wireless connection to a network node via another UE. The output may be periodic (e.g., once every 15 minutes if it reports the sensed temperature), random (e.g., to even out the load from reporting fromseveral sensors), in response to a triggering event (e.g., when moisture is detected an alert is sent), in response to a request (e.g., a user initiated request), or a continuous stream (e.g., a live video feed of a patient).

[0125] As another example, a UE comprises an actuator, a motor, or a switch, related to a communication interface configured to receive wireless input from a network node via a wireless connection. In response to the received wireless input the states of the actuator, the motor, or the switch may change. For example, the UE may comprise a motor that adjusts the control surfaces or rotors of a drone in flight according to the received input or to a robotic arm performing a medical procedure according to the received input.

[0126] A UE, when in the form of an Internet of Things (loT) device, may be a device for use in one or more application domains, these domains comprising, but not limited to, city wearable technology, extended industrial application and healthcare. Non-limiting examples of such an loT device are a device which is or which is embedded in: a connected refrigerator or freezer, a TV, a connected lighting device, an electricity meter, a robot vacuum cleaner, a voice controlled smart speaker, a home security camera, a motion detector, a thermostat, a smoke detector, a door / window sensor, a flood / moisture sensor, an electrical door lock, a connected doorbell, an air conditioning system like a heat pump, an autonomous vehicle, a surveillance system, a weather monitoring device, a vehicle parking monitoring device, an electric vehicle charging station, a smart watch, a fitness tracker, a head-mounted display for Augmented Reality (AR) or Virtual Reality (VR), a wearable for tactile augmentation or sensory enhancement, a water sprinkler, an animal- or item-tracking device, a sensor for monitoring a plant or animal, an industrial robot, an Unmanned Aerial Vehicle (UAV), and any kind of medical device, like a heart rate monitor or a remote controlled surgical robot. A UE in the form of an loT device comprises circuitry and / or software in dependence of the intended application of the loT device in addition to other components as described in relation to the UE 700 shown in Figure 7.

[0127] As yet another specific example, in an loT scenario, a UE may represent a machine or other device that performs monitoring and / or measurements, and transmits the results of such monitoring and / or measurements to another UE and / or a network node. The UE may in this case be an M2M device, which may in a 3 GPP context be referred to as an MTC device. As one particular example, the UE may implement the 3GPP NB-IoT standard. In other scenarios, a UE may represent a vehicle, such as a car, a bus, a truck, a ship and an airplane, or other equipment that is capable of monitoring and / or reporting on its operational status or other functions associated with its operation.

[0128] In practice, any number of UEs may be used together with respect to a single use case. For example, a first UE might be or be integrated in a drone and provide the drone’s speed information (obtained through a speed sensor) to a second UE that is a remote controller operating the drone. When the user makes changes from the remote controller, the first UE may adjust the throttle on the drone (e.g. by controlling an actuator) to increase or decrease the drone’s speed. The first and / or the second UE can also include more than one of the functionalities described above. For example, a UE might comprise the sensor and the actuator, and handle communication of data for both the speed sensor and the actuators.

[0129] Figure 8 shows a network node 800 in accordance with some embodiments. As used herein, network node refers to equipment capable, configured, arranged and / or operable to communicate directly or indirectly with a UE and / or with other network nodes or equipment, in a telecommunication network. Examples of network nodes include, but are not limited to, access points (APs) (e.g., radio access points), base stations (BSs) (e.g., radio base stations, Node Bs, evolved Node Bs (eNBs) and NR NodeBs (gNBs)), O-RAN nodes or components of an O-RAN node (e.g., O-RU, O-DU, O-CU).

[0130] Base stations may be categorized based on the amount of coverage they provide (or, stated differently, their transmit power level) and so, depending on the provided amount of coverage, may be referred to as femto base stations, pico base stations, micro base stations, or macro base stations. A base station may be a relay node or a relay donor node controlling a relay. A network node may also include one or more (or all) parts of a distributed radio base station such as centralized digital units, distributed units (e.g., in an O-RAN access node) and / or remote radio units (RRUs), sometimes referred to as Remote Radio Heads (RRHs). Such remote radio units may or may not be integrated with an antenna as an antenna integrated radio. Parts of a distributed radio base station may also be referred to as nodes in a distributed antenna system (DAS).

[0131] Other examples of network nodes include multiple transmission point (multi- TRP) 5G access nodes, multi- standard radio (MSR) equipment such as MSR BSs, network controllers such as radio network controllers (RNCs) or base station controllers (BSCs), base transceiver stations (BTSs), transmission points, transmission nodes, multi-cell / multicast coordination entities (MCEs), Operation and Maintenance (O&M) nodes, Operations Support System (OSS) nodes, Self-Organizing Network (SON) nodes, positioning nodes (e.g., Evolved Serving Mobile Location Centers (E-SMLCs)), and / or minimization of Drive Tests (MDTs).

[0132] The network node 800 includes a processing circuitry 802, a memory 804, a communication interface 806, and a power source 808. The network node 800 may becomposed of multiple physically separate components (e.g., a NodeB component and a RNC component, or a BTS component and a BSC component, etc.), which may each have their own respective components. In certain scenarios in which the network node 800 comprises multiple separate components (e.g., BTS and BSC components), one or more of the separate components may be shared among several network nodes. For example, a single RNC may control multiple NodeB s. In such a scenario, each unique NodeB and RNC pair, may in some instances be considered a single separate network node. In some embodiments, the network node 800 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memory 804 for different RATs) and some components may be reused (e.g., a same antenna 810 may be shared by different RATs). The network node 800 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node 800, for example GSM, WCDMA, LTE, NR, WiFi, Zigbee, Z-wave, LoRaWAN, Radio Frequency Identification (RFID) or Bluetooth wireless technologies. These wireless technologies may be integrated into the same or different chip or set of chips and other components within network node 800.

[0133] The processing circuitry 802 may comprise a combination of one or more of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application-specific integrated circuit, field programmable gate array, or any other suitable computing device, resource, or combination of hardware, software and / or encoded logic operable to provide, either alone or in conjunction with other network node 800 components, such as the memory 804, to provide network node 800 functionality.

[0134] In some embodiments, the processing circuitry 802 includes a system on a chip (SOC). In some embodiments, the processing circuitry 802 includes one or more of radio frequency (RF) transceiver circuitry 812 and baseband processing circuitry 814. In some embodiments, the radio frequency (RF) transceiver circuitry 812 and the baseband processing circuitry 814 may be on separate chips (or sets of chips), boards, or units, such as radio units and digital units. In alternative embodiments, part or all of RF transceiver circuitry 812 and baseband processing circuitry 814 may be on the same chip or set of chips, boards, or units.

[0135] The memory 804 may comprise any form of volatile or non-volatile computer-readable memory including, without limitation, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), read-only memory (ROM), mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD) or a Digital Video Disk(DVD)), and / or any other volatile or non-volatile, non-transitory device-readable and / or computer-executable memory devices that store information, data, and / or instructions that may be used by the processing circuitry 802. The memory 804 may store any suitable instructions, data, or information, including a computer program, software, an application including one or more of logic, rules, code, tables, and / or other instructions capable of being executed by the processing circuitry 802 and utilized by the network node 800. The memory 804 may be used to store any calculations made by the processing circuitry 802 and / or any data received via the communication interface 806. In some embodiments, the processing circuitry 802 and memory 804 is integrated.

[0136] The communication interface 806 is used in wired or wireless communication of signaling and / or data between a network node, access network, and / or UE. As illustrated, the communication interface 806 comprises port(s) / terminal(s) 816 to send and receive data, for example to and from a network over a wired connection. The communication interface 806 also includes radio front-end circuitry 818 that may be coupled to, or in certain embodiments a part of, the antenna 810. Radio front-end circuitry 818 comprises filters 820 and amplifiers 822. The radio front-end circuitry 818 may be connected to an antenna 810 and processing circuitry 802. The radio front-end circuitry may be configured to condition signals communicated between antenna 810 and processing circuitry 802. The radio front-end circuitry 818 may receive digital data that is to be sent out to other network nodes or UEs via a wireless connection. The radio front-end circuitry 818 may convert the digital data into a radio signal having the appropriate channel and bandwidth parameters using a combination of filters 820 and / or amplifiers 822. The radio signal may then be transmitted via the antenna 810. Similarly, when receiving data, the antenna 810 may collect radio signals which are then converted into digital data by the radio front-end circuitry 818. The digital data may be passed to the processing circuitry 802. In other embodiments, the communication interface may comprise different components and / or different combinations of components.

[0137] In certain alternative embodiments, the network node 800 does not include separate radio front-end circuitry 818, instead, the processing circuitry 802 includes radio frontend circuitry and is connected to the antenna 810. Similarly, in some embodiments, all or some of the RF transceiver circuitry 812 is part of the communication interface 806. In still other embodiments, the communication interface 806 includes one or more ports or terminals 816, the radio front-end circuitry 818, and the RF transceiver circuitry 812, as part of a radio unit (not shown), and the communication interface 806 communicates with the baseband processing circuitry 814, which is part of a digital unit (not shown).

[0138] The antenna 810 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna 810 may be coupled to the radio front-end circuitry 818 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna 810 is separate from the network node 800 and connectable to the network node 800 through an interface or port.

[0139] The antenna 810, communication interface 806, and / or the processing circuitry 802 may be configured to perform any receiving operations and / or certain obtaining operations described herein as being performed by the network node. Any information, data and / or signals may be received from a UE, another network node and / or any other network equipment. Similarly, the antenna 810, the communication interface 806, and / or the processing circuitry 802 may be configured to perform any transmitting operations described herein as being performed by the network node. Any information, data and / or signals may be transmitted to a UE, another network node and / or any other network equipment.

[0140] The power source 808 provides power to the various components of network node 800 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source 808 may further comprise, or be coupled to, power management circuitry to supply the components of the network node 800 with power for performing the functionality described herein. For example, the network node 800 may be connectable to an external power source (e.g., the power grid, an electricity outlet) via an input circuitry or interface such as an electrical cable, whereby the external power source supplies power to power circuitry of the power source 808. As a further example, the power source 808 may comprise a source of power in the form of a battery or battery pack which is connected to, or integrated in, power circuitry. The battery may provide backup power should the external power source fail.

[0141] Embodiments of the network node 800 may include additional components beyond those shown in Figure 8 for providing certain aspects of the network node’s functionality, including any of the functionality described herein and / or any functionality necessary to support the subject matter described herein. For example, the network node 800 may include user interface equipment to allow input of information into the network node 800 and to allow output of information from the network node 800. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the network node 800.

[0142] Figure 9 illustrates components of a parameter setting control system 900 according to some embodiments. The parameter setting control system 900 includes a processing circuit 902, a memory that stores data and computer program instructions that are executable by the processing circuit 902 for performing the operations described herein, and a communication module 906 for communicating with a system that is controlled by the parameter setting control system 900.

[0143] Figure 10 illustrates various functional modules that may be stored in the memory 904 of the parameter setting control system 900. As shown in Figure 10, the memory 904 may contain a data acquisition module 912 that acquires initial data samples from the controlled system, a synthetic data generation module 912 that generates synthetic data samples from the initial data samples, a stage 1 model 916 that generates a prediction of an operating parameter setting of the controlled system, and a stage 2 model 918 that generates a prediction of an operating performance measurement that is expected to be observed after application of the predicted operating parameter setting.

[0144] Although the computing devices described herein (e.g., UEs, network nodes, hosts) may include the illustrated combination of hardware components, other embodiments may comprise computing devices with different combinations of components. It is to be understood that these computing devices may comprise any suitable combination of hardware and / or software needed to perform the tasks, features, functions and methods disclosed herein. Determining, calculating, obtaining or similar operations described herein may be performed by processing circuitry, which may process information by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored in the network node, and / or performing one or more operations based on the obtained information or converted information, and as a result of said processing making a determination. Moreover, while components are depicted as single boxes located within a larger box, or nested within multiple boxes, in practice, computing devices may comprise multiple different physical components that make up a single illustrated component, and functionality may be partitioned between separate components. For example, a communication interface may be configured to include any of the components described herein, and / or the functionality of the components may be partitioned between the processing circuitry and the communication interface. In another example, non-computationally intensive functions of any of such components may be implemented in software or firmware and computationally intensive functions may be implemented in hardware.

[0145] In certain embodiments, some or all of the functionality described herein may be provided by processing circuitry executing instructions stored on in memory, which in certain embodiments may be a computer program product in the form of a non-transitory computer-readable storage medium. In alternative embodiments, some or all of the functionality may be provided by the processing circuitry without executing instructions stored on a separate or discrete device-readable storage medium, such as in a hard-wired manner. In any of those particular embodiments, whether executing instructions stored on a non-transitory computer-readable storage medium or not, the processing circuitry can be configured to perform the described functionality. The benefits provided by such functionality are not limited to the processing circuitry alone or to other components of the computing device, but are enjoyed by the computing device as a whole, and / or by end users and a wireless network generally.

Claims

Claims:

1. A method of generating a prediction of an operating parameter setting for an element in a system, comprising: collecting (302) parameter data samples for a plurality of elements in the system, wherein the parameter data samples comprise covariate parameters associated with the plurality of elements; generating (304) synthetic data samples based on the parameter data samples for the plurality of elements, wherein generating the synthetic data samples comprises, for a pair of parameter data samples, combining the pair of parameter data samples to form a synthetic data sample only if the synthetic data sample is consistent with a fundamental domain requirement associated with the plurality of elements; training (306) a first model using the synthetic data samples to predict the operating parameter setting; and predicting (308) the operating parameter setting for the element using the first model.

2. The method of Claim 1, further comprising: adjusting the operating parameter setting of the element in accordance with the predicted operating parameter setting.

3. The method of Claim 1, further comprising, after generating the prediction of the operating parameter setting, applying a second model to generate a prediction of an operating performance measurement that is expected to be achieved after applying the operating parameter setting, and adjusting the operating parameter setting based on the prediction of the operating performance measurement.

4. The method of any previous Claim, wherein the element comprises an antenna.

5. The method of Claim 4 when dependent on Claim 3, wherein: the system comprises a wireless communication system, the operating parameter setting comprises an electrical tilt angle of the antenna, the fundamental domain requirement comprises a relationship between antenna tilt and expected range of the antenna, the synthetic data samples comprise a source tilt angle, a source range, a destination tilt angle and a destination range of the antenna, and the first model has source tilt angle, source range and predicted range as inputs and has destination tilt angle as an output.

6. The method of Claim 5, wherein the operating performance measurement comprises a range of the antenna.

7. The method of Claim 5, wherein the second model is trained using performance data associated with a cell of the wireless communication system in which the antenna operates.

8. The method of Claim 4, wherein the fundamental domain requirement specifies that an increase in tilt angle should correspond to a decrease in antenna range.

9. The method of any of Claims 4 to 8, wherein generating the synthetic data samples comprises obtaining a plurality of initial data samples for antennas in the wireless communication system, wherein each of the plurality of initial data samples includes an antenna tilt angle and an estimated range for the antenna, and, for each pair of the initial data samples, determining if a combination of the pair of initial data samples would result in a synthetic data sample that complies with the fundamental domain requirement.

10. The method of Claim 9, further comprising: limiting the adjustment of the operating parameter setting based on a previous value of the operating parameter setting.

11. A computer program product comprising a non-transitory storage medium that contains computer program instructions for performing the method according to any of Claims 1 to 10.

12. A parameter setting control system (900), comprising: a processing circuit; and a memory coupled to the processing circuit, wherein the memory stores computer program instructions that, when executed by the processing circuit, causes the processing circuit to perform operations comprising: collecting (302) parameter data samples for a plurality of elements in the system, wherein the parameter data samples comprise covariate parameters associated with the plurality of elements; generating (304) synthetic data samples based on the parameter data samples for the plurality of elements, wherein generating the synthetic data samples comprises, for a pair of parameter data samples, combining the pair of parameter data samples to form a synthetic data sample only if the synthetic data sample is consistent with a fundamental domain requirement associated with the plurality of elements; training (306) a first model using the synthetic data samples to predict the operating parameter setting; and predicting (308) the operating parameter setting for the element using the model.

13. The parameter setting control system of Claim 12, wherein the operations further comprise: adjusting the operating parameter setting of the element in accordance with the predicted operating parameter setting.

14. The parameter setting control system of Claim 12, wherein the operations further comprise, after generating the prediction of the operating parameter setting, applying a second model to generate a prediction of an operating performance measurement that is expected to be achieved after applying the operating parameter setting, and adjusting the operating parameter setting based on the prediction of the operating performance measurement.

15. The parameter setting control system of any of Claims 12 to 14, wherein the element comprises an antenna.

16. The parameter setting control system of Claim 15 when dependent on Claim 14, wherein: the system comprises a wireless communication system, the operating parameter setting comprises an electrical tilt angle of the antenna, the fundamental domain requirement comprises a relationship between antenna tilt and expected range of the antenna, the synthetic data samples comprise a source tilt angle, a source range, a destination tilt angle and a destination range of the antenna, and the first model has source tilt angle, source range and predicted range as inputs and has destination tilt angle as an output.

Images