Abstract: A device may identify assets associated with potential network outages, may receive best serving plot information for an asset of the assets, and may receive asset plots for geographic areas associated with remaining assets. The device may identify a coverage band for the asset based on the best serving plot information, may determine coverage tiers for the geographic areas based on the asset plots, and may calculate next best serving assets for the geographic areas. The device may compute PDFs for the coverage band and the coverage tiers associated with next best serving assets, may compute an intersection of the PDFs, and may calculate an area under the intersection to generate a coverage overlap coefficient. The device may utilize the coverage overlap coefficient to scale KPIs of the asset and to generate updated KPIs of the asset, and may perform one or more actions based on the updated KPIs.

Abstract: A device may receive time-series data, may divide the time-series data into sets, and may identify data gaps in each of the sets of time-series data. The device may normalize the data gaps to generate normalized data gaps, may generate images of the normalized data gaps, and may extract features from the images of the normalized data gaps. The device may compute spatial distances based on the features, may transform the spatial distances to vector form spatial distances, and may perform hierarchical and agglomerative clustering on the vector form spatial distances to generate clusters. The device may select a set of the clusters, may perform a data fill method on the set of the clusters to generate a final set of the clusters, and may train the machine learning model, with the final set of the clusters, to generate a trained machine learning model.

Abstract: The techniques described herein relate to a method that involves identifying a set of network elements with less than a specified percentage of missing data, removing a percentage of data to create a test data set for each network element, applying various data fill methods to the test data set to generate filled data sets, calculating the percentage of missing data successfully filled and the error between the filled data and the removed data for each data fill method, analyzing the relationships between the percentage of missing data, the percentage of successfully filled data, and the error to generate error curves for each data fill method, and selecting one or more data fill methods to apply to missing data in a network element based on the corresponding error curves.

Abstract: A carrier aggregation platform may obtain device data regarding first UEs associated with a geographical area and determine a data distribution of make and model combinations of the first UEs. The platform may analyze the data distribution to identify one or more make, model combinations that satisfy a threshold and determine carrier aggregation capabilities of UEs of the one or more make and model combinations. The platform may determine, based on the carrier aggregation capabilities, one or more combinations of frequency bands and a number of downlinks for the frequency bands. The platform may obtain network data indicating a carrier aggregation of a base station associated with the geographical area. The platform may determine carrier aggregation information based on the carrier aggregation , the one or more combinations of frequency bands, and the number of downlinks. Second UEs may be configured based on the carrier aggregation information.

Abstract: A system may receive, from a network, an estimate of coordinates of a location of a potential interference source; determine, based in the estimate, whether the system is within a first threshold distance from the location; if the system is with the first threshold distance from the location, obtain real-time interference data from the network; determine, based on the real-time interference data, whether a source of interference exists near a first location that is within a second distance from a second location specified by the real-time interference data; and send a reply that indicates a result of the determination to the network.

Abstract: A carrier aggregation platform may obtain device data regarding first UEs associated with a geographical area and determine a data distribution of make and model combinations of the first UEs. The platform may analyze the data distribution to identify one or more make, model and/or software combinations that satisfy a threshold and determine carrier aggregation capabilities of UEs of the one or more make and model combinations. The platform may determine, based on the carrier aggregation capabilities, one or more combinations of frequency bands and a number of downlinks for the frequency bands. The platform may obtain network data indicating a carrier aggregation capability of a base station associated with the geographical area. The platform may determine carrier aggregation information based on the carrier aggregation capability, the one or more combinations of frequency bands, and the number of downlinks. Second UEs may be configured based on the carrier aggregation information.

Abstract: A device may receive network data identifying key performance indicators associated with a base station and user equipment (UEs), UE data identifying UE data records and UE locations, and geographic data identifying a geographic area and features of the geographic area. The device may correlate the network data, the UE data, and the geographic data to generate correlated data. The device may process, the correlated data, with a plurality of machine learning models, to generate a corresponding plurality of results, and may evaluate the plurality of results, with prediction models, to generate a set of results. The device may compare classification cost function weighted predictions and the set of results to generate comparisons, and may select a machine learning model, for the geographic area and from the plurality of machine learning models, based on the comparisons. The device may implement the machine learning model for the geographic area.

Abstract: The techniques described herein relate to a method that involves identifying a set of network elements with less than a specified percentage of missing data, removing a percentage of data to create a test data set for each network element, applying various data fill methods to the test data set to generate filled data sets, calculating the percentage of missing data successfully filled and the error between the filled data and the removed data for each data fill method, analyzing the relationships between the percentage of missing data, the percentage of successfully filled data, and the error to generate error curves for each data fill method, and selecting one or more data fill methods to apply to missing data in a network element based on the corresponding error curves.

Abstract: A device may receive load data identifying a load on a radio access network (RAN), and may select one or more time series forecasting models and a classification model based on seasonality metrics associated with the load data. The device may process the load data, with the one or more time series forecasting models, to forecast a capacity for the RAN, and may process the load data and the capacity, with the classification model, to determine whether the capacity exceeds a capacity threshold. The device may selectively determine that the RAN does not need an upgrade based on determining that the capacity fails to exceed the capacity threshold, or may adjust, based on determining that the capacity exceeds the capacity threshold, the capacity to generate an adjusted capacity. The device may perform one or more actions based on the adjusted capacity.

Abstract: In some implementations, a first UE may identify a configuration that includes artificial intelligence or machine learning (AI/ML) model parameters to be used and shared for federated learning. The first UE may generate an AI/ML model based on the configuration, wherein the AI/ML model is based on an anonymization and encryption of one or more information elements (IEs) using policy information. The first UE may secure the AI/ML model. The first UE may establish a circle-of-trust to include the first UE and a second UE. The first UE may transmit the AI/ML model to the second UE based on the second UE being included in the circle-of-trust.

Abstract: A device may receive user criteria associated with a route for network performance testing of a network, network data associated with the network, and cartographic data associated with a location of the network. The device may calculate network spatial data based on the user criteria and the network data, and may perform feature extraction of the network spatial data to calculate network statistics and to extract network event locations. The device may generate waypoint criteria based on the network statistics and the network event locations, and may map the network spatial data to valid roadways identified in the cartographic data to generate mapped data. The device may identify a list of viable waypoints based on comparing the mapped data and the waypoint criteria, and may process the list of viable waypoints, the network data, and the cartographic data, with a clustering model, to generate the route.

Abstract: A method may include identifying, in a network, a location of a Fifth Generation (5G) node and determining, based on the location of the 5G node and capabilities associated with the 5G node, a number of areas around the 5G node, wherein each area corresponds to a bin. The method may also include identifying, in at least some of the of bins, candidate anchor nodes for the 5G node and ranking the candidate anchor nodes based on parameters associated with the candidate anchor nodes. The method may further include selecting, for the 5G node, an anchor node from the candidate anchor nodes based on the ranking.

Abstract: In some aspects, the techniques described herein relate to a method including: receiving an identity of fraudulent user equipment (UE); identifying a plurality of candidate UEs based on locations associated with the fraudulent UE and a duration of a session of the fraudulent UE; computing vectors representing the plurality of candidate UEs based on activity data associated with the plurality of candidate UEs recorded during the duration; comparing the plurality of vectors to a vector associated with activity data associated with the fraudulent UE to compute distances between the plurality of candidate UEs and the fraudulent UE; sorting the plurality of candidate UEs based on the distances; storing a top subset of the plurality of candidate UEs as co-located UEs; and performing an action using the top subset of the plurality of candidate UEs.

Abstract: A device may receive user criteria associated with a route for network performance testing of a network, network data associated with the network, and cartographic data associated with a location of the network. The device may calculate network spatial data based on the user criteria and the network data, and may perform feature extraction of the network spatial data to calculate network statistics and to extract network event locations. The device may generate waypoint criteria based on the network statistics and the network event locations, and may map the network spatial data to valid roadways identified in the cartographic data to generate mapped data. The device may identify a list of viable waypoints based on comparing the mapped data and the waypoint criteria, and may process the list of viable waypoints, the network data, and the cartographic data, with a clustering model, to generate the route.

Abstract: A device may receive time domain PRB data associated with a plurality of base stations of a network, and may transform the time domain PRB data into frequency domain PRB data. The device may identify, based on the frequency domain PRB data, periodic interference patterns associated with the network, and may process periodic data associated with the periodic interference patterns, with a clustering model, to identify clusters of periodic interference patterns. The device may utilize a time offset analysis to link clusters and identify a transient periodic interferer, and may process cluster data associated with the clusters and the transient periodic interferer, and public transportation data, with a machine learning model, to predict a route associated with the transient periodic interferer. The device may perform one or more actions based on the route associated with the transient periodic interferer.

Abstract: A method may include identifying, in a network, a location of a Fifth Generation (5G) node and determining, based on the location of the 5G node and capabilities associated with the 5G node, a number of areas around the 5G node, wherein each area corresponds to a bin. The method may also include identifying, in at least some of the of bins, candidate anchor nodes for the 5G node and ranking the candidate anchor nodes based on parameters associated with the candidate anchor nodes. The method may further include selecting, for the 5G node, an anchor node from the candidate anchor nodes based on the ranking.

Abstract: A device may determine that a first geographical area satisfies an area threshold. The first geographical area includes an estimated location of a source of interference associated with base stations. A first plurality of vertices, of the first geographical area, are based on locations of the base stations. The device may determine a second plurality of vertices. The second plurality of vertices are closer to the estimated location than the first plurality of vertices. The device may provide information regarding the second plurality of vertices and may obtain magnitude information indicating magnitudes of the interference measured at the second plurality of vertices. The device may determine a third plurality of vertices based on the magnitude information. The device may provide information regarding a second geographical area, formed by the third plurality of vertices, to cause a search of the second geographical area to identify the source of the interference.

Abstract: A management system may receive base station information regarding 5G base stations identified by a fixed wireless access (FWA) device. The base station information may identify the 5G base stations and sectors of the 5G base stations. The management system may provide a request for a quantity of devices connected to each of the sectors. The management system may receive device information indicating the quantity of devices connected to each sector of the sectors of the 5G base stations. The management system may determine loads of the 5G base stations based on the device information. The management system may provide load information regarding the loads of the 5G base stations. The load information may be provided to cause a 4G base station to determine the loads of the 5G base stations prior to causing a 5G base station to establish a connection with the FWA device.

Abstract: A device may receive time domain PRB data associated with a plurality of base stations of a network, and may transform the time domain PRB data into frequency domain PRB data. The device may identify, based on the frequency domain PRB data, periodic interference patterns associated with the network, and may process periodic data associated with the periodic interference patterns, with a clustering model, to identify clusters of periodic interference patterns. The device may utilize a time offset analysis to link clusters and identify a transient periodic interferer, and may process cluster data associated with the clusters and the transient periodic interferer, and public transportation data, with a machine learning model, to predict a route associated with the transient periodic interferer. The device may perform one or more actions based on the route associated with the transient periodic interferer.

Abstract: A device may include a processor configured to receive a report from a fixed wireless access device indicating that no anchoring relationship exists between a Fourth Generation (4G) base station and a Fifth Generation (5G) base station to which the fixed wireless access device is attempting to connect. The device may be further configured to instruct a network management system to create the anchoring relationship between the 4G base station and the 5G base station; and update an anchoring relationships database with information relating to the created anchoring relationship, wherein the anchoring relationships database stores information relating to anchoring relationships between base stations in a radio access network.