Viavi Solutions UK Limited

Viavi Solutions Inc.

Howard John Thomas

David Charles Padfield

Mihai Stanciuc

Christopher Michael Murphy

Mohsen Zadeh-Koochak

Peter Randall

Peter Kenington

Michael Joseph Flanagan

Nicholas James Randell

Stefan Ulrich Thiel

Walter Featherstone

Gareth James Smith

Philip Geoffrey Claridge

Takai Eddine Kennouche

Kexuan Sun

Baruch Friedman

Agustin Pozuelo

Joe Haver

Meng Wang

Dave Padfield

Robert Edward Trybulec

Krassimir Stoyanov Vassilev

Nicolas G Cotanis

John Govert

Sthiven Pinilla

Frank Mamani

Robert Clark

A device may receive real mobile radio data identifying measurements of radio transmissions of base stations and user devices of a mobile radio environment in a geographical area, and may receive network topology data associated with the geographical area. The device may utilize, based on the network topology data, a machine learning feature extraction approach to generate a representation of invariant aspects of spatiotemporal predictable components of the real mobile radio data, and may generate, based on the representation of invariant aspects, stochastic data that includes a probability that a radio signal will be obstructed. The device may utilize the stochastic data to identify a realistic discoverable spatiotemporal signature, and may train or evaluate a system to manage performance of a mobile radio network based on the realistic discoverable spatiotemporal signature.

Utilizing invariant shadow fading data for training a machine learning model

A device may receive a first type of data identifying measurements associated with user devices and/or base stations of a mobile radio environment, and a second type of data identifying spatiotemporal behavior associated with the user devices. The device may train a first model, with the first type of data, to generate a trained first model that yields dimensionality-reduced spatiotemporal characteristics of the first type of data, and may train a second model, with the second type of data and the dimensionality-reduced spatiotemporal characteristics, to generate a trained second model. The device may receive particular data identifying measurements associated with a user device and/or base stations, and may process the particular data, with the trained first model, to generate a dimensionality-reduced spatiotemporal characteristic of the particular data. The device may process the dimensionality-reduced spatiotemporal characteristic, with the trained second model, to predict a spatiotemporal behavior of the user device.

Utilizing machine learning models to estimate user device spatiotemporal behavior

A device may receive mobile radio data identifying utilization of a mobile radio network that includes base stations and user devices in a geographical area. The device may process the mobile radio data, with a machine learning feature extraction model, to generate a behavioral representation, that is probabilistic in nature, of invariant aspects of spatiotemporal utilization of the mobile radio network. The device may generate one or more instances of the spatiotemporal utilization of the mobile radio network that reflects the probabilistic nature of a spatiotemporal predictable component of the behavioral representation. The device may utilize the one or more instances of the spatiotemporal utilization of the mobile radio network as a dataset for training or evaluating a system to manage performance of the mobile radio network.

Utilizing invariant user behavior data for training a machine learning model

A first device for determining measurement information for a network may include one or more processors. The first device may identify one or more data streams of frames for monitoring. The first device may modify the frames of the one or more identified streams to identify the frames as one or more of count frames to be used to identify a quantity of dropped frames, or to identify the frames as measurement frames to be used to determine latency or jitter. The first device may transmit the one or more data streams toward a second device to permit the second device to collect measurement information based on identifying the count frames or the measurement frames.

Data stream monitoring

A device may detect a service condition associated with a network. The device may determine a prioritization of cells of the network based on characteristics of one or more subscribers to the cells of the network. The characteristics may include at least one of: a service type characteristic, an application type characteristic, a mobility characteristic, a vector characteristic, an altitude characteristic, a position characteristic, a location type characteristic, a device type characteristic, a device capability characteristic, a connection characteristic, a subscription characteristic, a call type characteristic, a user profile characteristic, a terrain characteristic, or an operator relationship characteristic. The device may perform an alteration to one or more network parameters based on the prioritization of cells of the network to reduce an impact of the service condition.

Network optimization based on characteristic information regarding a network

A device obtains uplink information associated with a base station and obtains downlink information associated with a mobile device in communication with the base station. The device determines observed network performance information based on the uplink information and the downlink information and determines a predictive model, based on the uplink information and the downlink information, to predict network performance information. The device also changes network configuration data, associated with the base station, to generate changed network configuration data and determines predicted network performance information for the changed network configuration data based on the predictive model. The device further selectively transmits the changed network configuration data, to the base station, based on comparing the predicted network performance information and the observed network performance information.

Modeling mobile network performance

Techniques for dynamic network optimization using geolocation and network modeling are disclosed. In one particular exemplary embodiment, the techniques may be realized as a system for network optimization. The system may comprise a data collection system configured to collect geolocated subscriber records from a plurality of mobile devices. The system may also comprise a SON optimization system communicatively coupled to the data collection system via a network. The SON optimization system may comprise at least one pre-processor configured to receive and process geolocated subscriber records from the data collection system. The SON optimization system may further comprise a network simulator configured to perform network simulation analysis based on the processed geolocated subscriber records, and provide a new network configuration based on the network simulation analysis, wherein the new network configuration is estimated to improve network performance.

Techniques for dynamic network optimization using geolocation and network modeling

A device may include one or more processors. The device may receive, via a plurality of data streams of a front haul link, a set of packets including information for transmission via an air interface. The set of packets may be associated with a data prioritization relating to transmission via the air interface. The set of packets may include information of a time-frequency resource element array. The device may reconstruct a set of time-frequency resource elements of the time-frequency resource element array based on the data prioritization of the set of packets. The device may transmit, via the air interface, the time-frequency resource element array.

Techniques for providing front-haul data awareness

A device receives subscriber records for mobile devices associated with a mobile network, and receives performance data associated with the mobile network in near real time. The performance data includes one or more of performance management statistics, call trace data associated with the subscriber records, and geolocated subscriber records for the mobile devices. The device stores the geolocated subscriber records with other types of data in an asynchronous manner, and receives configuration data associated with the mobile network and indicating a topology of the mobile network. The device identifies, based on at least one of the topology and the performance data, a desired topology of the mobile network. The desired topology is predicted to achieve at least one of improved network performance or alignment with a network design policy.

Self-optimizing network (SON) system for mobile networks

Techniques for multiple pass geolocation are disclosed. In one particular exemplary embodiment, the techniques may be realized as a system for multiple pass geolocation. The system may comprise one or more processors communicatively coupled to a mobile communications network. The one or more processors may be configured to conduct a first geolocation pass to identify one or more geolocation estimates under consideration. The one or more processors may also be configured to conduct at least one additional geolocation pass to refine one or more geolocation estimates under consideration. The one or more processors may further be configured to determine an approximate location of one or more mobile devices within an estimated coverage area of a network based on at least the first geolocation pass and the at least one additional geolocation pass.

Techniques for multiple pass geolocation

A device may include one or more processors configured to receive information associated with one or more performance goals to be achieved within a radio access network (RAN). The device may receive performance information for mobile devices associated with the RAN. The device may determine that at least one performance goal, of the one or more performance goals, is not being achieved within the RAN. The determining may be based on the information associated with the one or more performance goals and the performance information. The device may generate a small cell plan for improving performance within the RAN toward achievement of the at least one performance goal. The small cell plan may identify a set of locations at which a set of small cells are to be activated, deactivated, or deployed. The device may output information associated with the small cell plan.

Small cell planning

Techniques for estimating a coverage area for a distributed antenna system (DAS) or a repeater system are disclosed. In one particular exemplary embodiment, the techniques may be realized as a system for estimating a coverage area for a distributed antenna system (DAS) or a repeater system. The system may comprise one or more processors communicatively coupled to a mobile communications network. The one or more processors may be configured to identify a sector as being a base station sector that deploys a distributed antenna system (DAS) or a repeater system. The one or more processors may also be configured to determine an approximate location for one or more antennas deployed by the distributed antenna system (DAS) or the repeater system. The one or more processors may further be configured to construct an estimated coverage area for the base station sector that deploys the distributed antenna system (DAS) or the repeater system.

Techniques for estimating a coverage area for a distributed antenna system (DAS) or a repeater system

Techniques for dynamic network optimization using geolocation and network modeling are disclosed. In one particular exemplary embodiment, the techniques may be realized as a system for improving performance of a mobile communications network. The system may comprise one or more processors communicatively coupled to a mobile communications network. The one or more processors may be configured to determine allowable changes within a network and rank a cell or parameter based on a priority rule. The one or more processors may be further be configured to generate a plurality of network configurations and evaluate strength of the plurality of network configurations. The one or more processors may also be configured to output a set of network configurations that is strongest among the plurality of network configurations.

Growing community of inventors

Stonehouse, United Kingdom

Howard John Thomas