At&t Intellectual Property I, L.p.

At&t Mobility Ii LLC

Georgia Tech Research Corporation

He Yan

Zihui Ge

Sarat Puthenpura

Alexandre Gerber

Jennifer Yates

Dan Pei

Ashley Flavel

Matthew Osinski

Hiren Shah

Ioannis Broustis

Shuai Hao

Jason Tipton

Anthony Caracciolo

Hector Perez

Mark Brisbay

Gavin Anderson

Kathryn Childs

Mira Desta

Brian Heard

Oliver Spatscheck

Nemmara K Shankaranarayanan

Slawomir Mikolaj Stawiarski

Jia Wang

Ajay Mahimkar

Leonid Razoumov

Aman M Shaikh

Supratim Deb

Karunasish Biswas

Xing Xu

Giritharan Rana

Robert Samson

Joseph Allen Notter

Lynn Lopez

Jason Pipkin

Chichi Boderoux

Carla Sykes

Kevin Wilkins

Mario Kosseifi

Dongmei Wang

Richard Miller

Jun Xu

Xuan Liu

Heather Magrini

Brandon Hall

Edward Ball

Sen Yang

Aspects of the subject disclosure may include, for example, detecting an interruption of a supply of operating power to a cell site of a cellular communication network, estimating an estimated time to restoration (ETR) of the supply of operating power to the cell site, wherein the estimating is based on information of an operator of the cellular communication network, determining, based in part on the ETR, to dispatch a portable generator to the cell site to provide a new supply of operating power to the cell site, and initiating a communication to dispatch the portable generator. Other embodiments are disclosed.

Portable generator dispatch recommendation engine

A processing system may apply a data set comprising utilization metrics of a cells of a cell sector to a throughput prediction model to obtain a first predicted throughput for the cell sector for a designated future time period and for all cells being in an active state. The processing system may generate a first modified data set simulating a first cell being placed in an inactive state, by distributing utilization metrics of the first cell over at least one additional cell, and may apply the first modified data set to the throughput prediction model to obtain a second predicted throughput. The processing system may then determine that the second predicted throughput meets a threshold throughput that is based on the first predicted throughput, and transmit at least one instruction to place the first cell in the inactive state for the designated future time period in response to the determining.

Cell site energy utilization management

The described technology is generally directed towards cellular communication network sleep management. A central network automation platform can control sleep settings deployed to radio access network nodes that support the cells of the cellular communication network. The network automation platform can collect cell configuration data and can use the cell configuration data to determine sleep settings for sleep-eligible cells. The network automation platform can furthermore monitor performance of the sleep-eligible cells and neighbor cells to determine whether the sleep settings have led to degraded performance.

Cellular communication network sleep management

A method and apparatus for providing trouble isolation are disclosed. For example, the method monitors a plurality of sessions for a user group for detecting an abnormal cause code associated with the user group, determines a root cause for the abnormal cause code when a deviation is determined to have occurred for the cause code of the user group, wherein the root cause identifies either an issue associated with the communications network or an issue associated with user endpoint devices of the user group, and generates a ticket indicating the root cause.

Method and apparatus for providing trouble isolation via a network

A method, system and computer-readable medium where a weighted composite quality index having a plurality of components for a network element is identified. A historical baseline value from historical data for each component is determined, and a deviation from the historical baseline values is measured. A risk level for the deviation is assigned. A loss score for the measured components is computed by mapping the risk level to a numerical score. An aggregated risk score based on a sum of weighted risk scores for each of the components is computed. An expected risk score based on probabilities associated with the aggregated risk score is determined by computing future probabilities of each risk level at the network element based on a trained machine learning model.

Methods, systems and computer readable media for predicting risk in network elements using machine learning

Aspects of the subject disclosure may include, for example, embodiments include receiving a first trouble ticket reporting a first service outage of a communication network and a second trouble ticket reporting a second service outage of the communication network. Further embodiments can include determining a first customer impact according to the first service outage and determining a second customer impact according to the second service outage. The first customer impact is determined by a degradation of quality metrics, a site priority, and a number of complaints due to each service outage. Additional embodiments can include identifying that the second customer impact is higher than the first customer impact. Also, embodiments can include prioritizing a resolution of the second trouble ticket over the first trouble ticket according to the second customer impact being higher than the first customer impact. Other embodiments are disclosed.

Methods, devices, and systems for prioritizing mobile network trouble tickets based on customer impact

A method includes collecting operational data from a system, segregating the data into a first component comprising one or more service quality anomalies and a second component comprising one or more network-based events, correlating the first component and the second component to determine whether the one or more network-based events have an impact on service quality, and prioritizing a resolution of the network-based events that have an impact on service quality.

Automatic integrated control loop for fault, performance and service quality management

Various embodiments disclosed herein provide for a tower outage impact predictor that can determine the service impact on an end user during a cellular tower outage. Radio signal profiling divides an area into grids, and then constructs a radio signal profile for each grid based on user equipment (UE) measurement data for each grid. The number of UEs in each grid is then determined, and then the number of UEs that lose service for a simulated cellular tower outage is determined. Based on the impact analysis, a more resilient backhaul network can be implemented by determining backhaul rehoming changes that optimally home cellular towers to various backhaul network devices.

Predictive impact analysis for designing a resilient cellular backhaul network

Methods, systems, and products infer performance of a domain name system. Queries to, and responses from, the domain name system are logged and categorized. Each category is associated with a different performance issue related to the domain name system. The number of entries in each category may be used to infer the performance of the domain name system.

Methods, systems, and products for monitoring domain name servers

Growing community of inventors

Berkeley Heights, NJ, United States of America

He Yan