Verizon Patent and Licensing Inc.

Matthew Kapala

Timothy E Coyle

Brian A Ward

Jason A Birr

Hector A Garcia Crespo

Ricardo Francisco Borges

Hector Alejandro Garcia Crespo

Sudha Subramaniam

Brent D Segner

Scott Anthony Townley

Dean P Jarski

Ammara Essa

Eric Freeman

Luis R Rosario

Randy Patrick

Jacob S Lynch

Deborah Lynn Liske

Mark David Lufburrow

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.

Systems and methods for carrier aggregation combination using device data and network data

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.

Systems and methods for selecting a machine learning model that predicts a subscriber network experience in a geographic area

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.

Systems and methods for identifying an optimal route for network performance testing

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.

System and method for identifying collocated cellular devices from known fraudulent devices

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.

Systems and methods for detecting and mitigating periodic and transient interference in a network

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.

Systems and methods for determining a source of interference based on current measurements of a measurement device

A device may receive interference data identifying interference associated with sectors provided by base stations, and may filter interference data associated with sectors with passive intermodulation issues and sectors with alarms related to sectors' radio, from the interference data, to generate interference data for a set of sectors. The device may perform an interference analysis on the sectors' physical resource blocks (PRBs) and receiving branches, of the interference data, to generate analysis results, and may determine interference associated with co-located sectors of the set of sectors. The device may identify neighbor sectors based on the interference, and may compare PRBs of the set of sectors with PRBs of the neighbor sectors to generate comparison results. The device may identify a particular sector that is the most impacted sector when compared to its neighboring and co-located sectors, associated with an interference source, based on the comparison results.

Systems and methods for detecting a most impacted base station sector by an external interference source

An interference detection system in a network determines that an unknown radio frequency (RF) interference source that causes RF interference experienced by a first wireless station is a persistent RF interference source over a plurality of time intervals in a selected time period. A predicted interference source location is identified for each time interval in the selected time period. An aggregated predicted interference source location is calculated based on the identified one or more predicted interference source locations.

Systems and methods for identifying a source of radio frequency interference in a wireless network

A method, a device, and a non-transitory storage medium are described in which a network performance spread service is provided. The service may include generating a dependency graph representative of a network and identifying current or prospective poor performance spread of network elements based on correlations between the network elements and performance data. The service may also include providing remedial services that address the poor performance spread in the network.

Network performance spread service

A device may receive antenna alert data associated with antennas of a plurality of base stations of a network, and may process the antenna alert data, with a correlation model, to generate a correlation heatmap matrix. The device may utilize a change point detection model to process the antenna alert data, associated with the correlation heatmap matrix, to determine change point metrics, and may calculate scores for the antenna alert data associated with the correlation heatmap matrix and the change point metrics. The device may perform one or more corrective actions based on the scores.

Systems and methods for determining radio access network antenna poor performance subscriber impact

Systems described herein may allow for the intelligent configuration of containers onto virtualized resources. Different configurations may be generated based on the simulation of alternate placements of containers onto nodes, where the placement of a particular container onto a particular node may serve as a root for several branches which may themselves simulate the placement of additional containers on the node (in addition to the container(s) indicated in the root). Once a set of configurations are generated, a particular configuration may be selected according to determined selection parameters and/or intelligent selection techniques.

Systems and methods for virtual machine resource optimization using tree traversal techniques representing alternate configurations

In some implementations, a network monitoring system may measure a traffic metric for a first component of a network device. The network monitoring system may determine, based on a trained component monitoring model, that an obtained measurement of the traffic metric for the first component satisfies a criteria associated with the traffic metric pattern. The network monitoring system may compare, based on determining that the obtained measurement satisfies the criteria, the obtained measurement to a corresponding measurement of the traffic metric for a second component of the network device. The network monitoring system may determine that a measurement difference between the obtained measurement for the first component and the corresponding measurement for the second component satisfies a difference threshold. The network monitoring system may perform, based on the measurement difference satisfying the difference threshold, an action associated with the first component.

Systems and methods for predicting failure of a network device

A device may receive location information associated with a fixed service satellite station (receiver) configured to communicate via a first radio frequency (RF) band. The device may obtain historical communication data associated with the location and relating to previous communications conducted via a second RF band, of user equipment (UEs). The historical communication data may include historical signal power measurements of the previous communications. The device may adjust the historical signal power measurements to model estimated signal power measurements relating to a UE to communicating via a first RF band. The device may determine, based on the estimated signal power measurements, an interference score associated with a probability of a UE interfering with the receiver when communicating, via a first RF band, with a base station.

Systems and methods for detecting interference probability within a radio frequency band

An interference detection system in a network identifies a first wireless station that has experienced radio frequency (RF) interference from an unknown source and identifies one or more second wireless stations that have experienced similar interference. A plurality of estimated interference source locations are scored based on a comparison of estimated interference to observed interference at the one or more second wireless stations. A predicted interference source location is identified based on the scored plurality of estimated interference source locations. It is determined whether the unknown interference source is a persistent interference source over a selected time period, wherein the predicted interference source location is identified for each interval in the selected time period. The predicted interference source locations for each interval in the selected time period are retrieved and an aggregated predicted interference source location is calculated based on the retrieved predicted interference source locations.

Growing community of inventors

North Billerica, MA, United States of America

Matthew Kapala