AT&T Intellectual Property I, LP

Princeton University

Cornell University

Simon Tse

Gagan Choudhury

Kathleen S Meier-Hellstern

Narayan Padi

Martin Birk

Tzuu-Yi Wang

Alvin Goddard

Steven A Monetti

Yaron Koral

Gaurav Thakur

Guy Jacobson

Kathleen Tse

Colin Goodall

Richard Koch

Richard Drechsler

Shweta Vachhani

John Mark F Mocenigo

Jennifer Lynn Rexford

Tuan Duong

David Frederick Lynch

Xiaoqi Chen

Shir Landau Feibish

Lynn Rivera

Kenneth Duell

Sarat Puthenpura

Han Q Nguyen

Wenjie Zhao

Sam Houston Parker

David Gerald Belanger

John Mark Mocenigo

Kang Xi

Ao Tang

Kenichi Futamura

Kartik Pandit

Aswatnarayan Raghuram

Catherine Ferraro

Shih-Hao Tseng

Systems, methods, and apparatuses provide a scalable framework for analyzing queuing and transient congestion in network switches. The system reports which flows contributed to the queue buildup and enables direct per-packet action in the data plane to prevent transient congestion. The system may be configured to analyze queuing in legacy network switches.

Microburst detection and management

A system for closed loop prefix management for white boxes includes a network device, a route reflector coupled to the network device, a software defined network controller coupled to the route reflector and the network device, and a prefix usage analyzer in the software defined network controller. The prefix usage analyzer determines usage attributes of prefixes and identifies the prefixes with a predetermined usage attribute. The software defined network controller instructs a network controller in the network device to store the prefixes with the predetermined usage attributes in a table in the network device.

Closed loop prefix management and controller for whiteboxes

A parser model may be used with software-defined applications or controllers. A network topology may be detected and based on the change in the network topology, a network device may filter certain network data traffic for processing by a software-defined network controller.

Network data extraction parser-model in SDN

Systems and methods mediate anomaly notifications in health data to health alerts using data structures and logic to organize, contain, and dispose of identified health anomalies. Multiple detection algorithms, operating asynchronously and independently, run against one or more health data streams. Examples of data streams are electronic laboratory requisitions and results, OTC sales of medicines and medical supplies, emergency department visit data, and others. The outputs of anomaly detection generators&#x2014;anomaly notifications (anomalies)&#x2014;are processed by the invention. The case manager organizes anomaly notifications and supports collaborative decision making and disposition among expert users.

Biosurveillance notifications

A system for network device measurements may use a white box to perform measurements that may help determine the likelihood of network anomalies, such as microbursts.

Network device measurements employing white boxes

Devices, computer-readable media and methods are disclosed for verifying that an optical transmit/receive device is correctly installed. For example, a processing system including at least one processor may activate a first light source of an optical transmit/receive device of a telecommunication network and detect a receiving of a light from the first light source at a port of an optical add/drop multiplexer of the telecommunication network. The processing system may then verify the optical transmit/receive device and the port of the optical add/drop multiplexer match a network provisioning order, when the receiving of the light from the first light source is detected, and may generate an indication that the optical transmit/receive device is correctly installed, when the optical transmit/receive device and the port of the optical add/drop multiplexer match the network provisioning order.

Network switch and optical transponder connectivity verification for wavelength division multiplexing network

Devices, computer-readable media and methods are disclosed for selecting paths in reconfigurable optical add/drop multiplexer (ROADM) networks using machine learning. In one example, a method includes defining a feature set for a proposed path through a wavelength division multiplexing network, wherein the proposed path traverses at least one link in the network, and wherein the at least one link connects a pair of reconfigurable optical add/drop multiplexers, predicting an optical performance of the proposed path, wherein the predicting employs a machine learning model that takes the feature set as an input and outputs a metric that quantifies predicted optical performance, and determining whether to deploy a new wavelength on the proposed path based on the predicted optical performance of the proposed path.

Machine learning techniques for selecting paths in multi-vendor reconfigurable optical add/drop multiplexer networks

A processing system including at least one processor may obtain traffic measurements for end-to-end paths in a telecommunication network, calculate traffic estimates for the end-to-end paths in future time periods based on the traffic measurements in accordance with at least one machine learning model, calculate traffic estimates for primary paths in the telecommunication network based upon the traffic estimates for the end-to-end paths, compute a backup path configuration for a primary path of the telecommunication network for the future time periods based upon the traffic estimates for the primary paths in the future time periods, detect a change in the backup path configuration for the primary path in a future time period based upon the computing, and adjust a backup path in accordance with the backup path configuration when the change in the backup path configuration is detected.

Traffic matrix prediction and fast reroute path computation in packet networks

Methods, systems, and computer-readable media for measuring packet delays are provided. An input port of a network device is tapped to duplicate an input packet stream having a first packet. An output port of the network device is tapped to duplicate an output packet stream including the first packet. The duplicated input packet stream and the duplicated output packet stream is transmitted to a programmable device. The first packet in the first input packet stream is matched to the first packet in the first output packet stream. An arrival time and a departure time for the first packet is measured. The difference between the departure time of the first packet and the arrival time of the first packet is determined and the value is reported to an external collector.

Systems, methods and computer-readable media for external non-intrusive packet delay measurement

The technologies described herein are generally directed to centralized management of wireless relay node equipment in a fifth generation (5G) or other next generation networks. In accordance with one or more embodiments, a method described herein can include facilitating identifying a connection between first network equipment and second network equipment, the first network equipment being connected to a user equipment and the second network equipment. In embodiments, the method can further include facilitating monitoring the connection between the first network equipment and the second network equipment, resulting in monitoring data, wherein the second network equipment is communicatively coupled to backhaul network equipment, and with the user equipment being communicatively coupled to the backhaul network equipment via the second network equipment. Further, based on the monitoring data, adjusting, by the centralized controller system, a characteristic of the connection, in accordance with embodiments.

Centralized management of wireless relay node equipment in a fifth generation (5G) or other next generation networks

A software-defined network multi-layer controller (SDN-MLC) may communicate with multiple layers of a telecommunication network. The SDN-MLC may have an optimization algorithm that helps manage, in near real-time, the multiple layers of the telecommunication network.

Multi-layer system optimization

Growing community of inventors

Holmdel, NJ, United States of America

Simon Tse