Facebook, Inc.

Meta Platforms, Inc.

Servicenow, Inc.

Ying Li

Martinus Arnold De Jongh

Vincent Gonguet

Nabil Abu Asba

James Donovan

Fan Sun

Laurent Corigliano

Djordje Tujkovic

Guan Pang

Yanzi Zhu

A system for network optimization using geo-data may access a set of geotagged data samples associated with a cell. The set of geotagged data samples may be obtained from an application associated with one or more user equipment associated with the cell and the cell includes at least one antenna. The system may also determine a metric associated with the cell based on the set of geotagged data samples, generate one or more antenna adjustments based on the metric, and predict, based on the one or more antenna adjustments, a performance improvement associated with the cell.

Systems and methods for wireless network optimization using geo-data for improved user experience

Display screen with graphical user interface

In one embodiment, a computing system may receive a request for an optimization recommendation of a geographic area of interest covered by a communication network. The computing system may determine a network traffic trend associated with the geographic area of interest based on a current number of data samples that may be aggregated into a plurality of data points. The computing system may predict a value of a number of data samples for a future time associated with the geographic area of interest, based on the determined network traffic trend and the current number of data samples. The computing system may predict, based on the determined network traffic trend and the predicted value of the number of data samples at the future time, network traffic associated with the geographic area of interest at the future time, and send instructions for presenting the optimization recommendation based on the predicted network traffic.

Communication network optimization based on predicted enhancement gain

In one embodiment, a computing system receives a request for a quality of experience report associated with a plurality of geographic areas connected by a communication network. The system accesses a plurality of quality of experience metrics from the plurality of geographic areas. The system identifies one or more of the plurality of geographic areas that have low quality of experiences based on their respective quality of experience metrics and a set of criteria which includes one or more thresholds corresponding to the quality of experience metrics. The system determines for each identified geographic area, a severity of the low quality of experiences. The severity is based on a connection demand metric associated with each geographic area. The system sends instructions for presenting the quality of experience report which indicates the severity of the low quality of experiences for each identified geographic area.

Detecting communication network insights of alerts

In one embodiment, the system identifies one or more geographic areas covered by a communication network. The system determines, for each identified geographic area, a congestion metric for the identified geographic area based at least on a difference between a first and second reference point on a network speed curve, wherein the network speed curve represents download speeds for a volume of traffic in the identified geographic area. The system identifies one or more network traffic congestions in one or more of the identified geographic areas based on a comparison of the respective congestion metrics of the identified geographic areas to a threshold congestion metric. The system sends, to one or more operators of the communication network, one or more alerts about the identified network traffic congestions.

In one embodiment, a computing system may access data samples associated with an access point of a communication network. The data samples may be collected at an application level from client devices associated with the access point and aggregated into data points correlating a first network metric to a traffic-volume metric. The system may partition the data points into a first and second set of data points using a first network metric threshold. The system may determine trends of the traffic-volume metric with respect to the first network metric based on regression analysis on the first and second sets of data points. The system may predict, based on the trends of the traffic-volume metric with respect to the first network metric, an amount of time until a network-capacity metric of the access point meets a traffic-loss threshold. The network-capacity metric may be determined based on the traffic-volume metric.

Communication network out-of-capacity predictions

In one embodiment, a method includes accessing time series data of a wireless communication link between a first node and a second node on a millimeter-wave communications network; determining that an anomaly exists in the time series data; determining an anomaly type for the anomaly by inputting one or more features derived from the time series data into a machine learning module; generating a report comprising an indication that the anomaly exists and a description of the anomaly type, and determining one or more treatments for the determined anomaly.

Machine learning assisted anomaly detection on a millimeter-wave communications network

In one embodiment, a computing system may collect data samples associated with a geographic area of interest covered by a communication network. The system may aggregate the data samples into data points. The system may split the aggregated data points into two sets of data points using a first threshold of a first network metric. The system may determine a trend of a second network metric over the first network metric based on regression on the two sets of data points. The system may determine a predicted gain of the second network metric for a network enhancement operation based on the trend of the second network metric and a reference value of the first network metric. The system may generate network optimization recommendations for the geographic area of interest based at least in part on the predicted gain of the second network metric.

A system and method is disclosed for configuring a performance analytics (PA) software application operational for analysis of performance data of a managed network. The system may include a PA database containing data for generating a unified graphical user interface (GUI) for consolidating configuration of key performance indicators (KPIs) of the managed network, and one or more server devices configured to receive, from a client device, a request to view information representative of a particular KPI. Based on the request, the server devices may obtain information regarding the particular KPI from the PA database and then transmit, to the client device, a representation of the unified GUI. The unified GUI may include a tabbed interface containing views corresponding to groups of related attributes of the particular KPI, the views including: (i) a data source view, (ii) a breakdown view, (iii) a data collection view, and (iv) an impact analysis view.

Guided interface for configuring key performance indicators

A system and method is disclosed for configuring a performance analytics (PA) system for processing key performance indicators of a managed network. The PA system may include a database containing PA entity records, each including data associated with a respective PA entity. Each PA entity may be a software and/or hardware component of the PA system. The system also includes a dependency assessment tree having respective nodes corresponding to the respective PA entities and branches connecting functionally dependent nodes of PA. The PA system may be configured to: transmit information to a client device for displaying a graphical representation of one or more respective PA entities; receive a request from the client device for dependency information for a first PA entity; and transmit to the client device a graphical representation of a first portion of the dependency assessment tree depicting the first PA entity and associated dependency nodes.

Dependency assessment interface for components of graphical user interfaces

Apparatuses, methods, and systems for monitoring performance of a wireless network and assigning sectors of nodes of the wireless network are disclosed. A method includes monitoring a performance of links between sectors of wireless nodes of the wireless network, assigning or reassigning sectors of the wireless nodes to operate in a first mode based on the monitored performance of the links, wherein all of the sectors operating in the first mode are configured to transmit signals or simultaneously receive signals, and assigning or reassigning sectors of the plurality of wireless nodes to operate in a second mode based on the monitored performance of the links, wherein all of the sectors operating in the second mode are configured to transmit signals when all of the sectors operating in the first mode are receiving signals, or receive signals when all of the sectors operating in the first mode are transmitting signals.

Wireless network performance monitoring and sector assignment

In one embodiment, a computing system determines quality of experience metrics and root-cause metrics for geographic areas connected by a communication network based on application data. The system determines that one or more of the geographic areas have low quality of experience based on the quality of experience metrics and a first set of criteria which includes one or more first thresholds for the quality of experience metrics. The system determines causes for the low quality of experience in each associated geographic area having low quality of experience based on the root-cause metrics and a second set of criteria which includes one or more second thresholds and is looser than the first set of criteria. The system determines a solution recommendation for the low quality of experience in each associated geographic area based on the causes of the low quality of experience of that geographic area.

In one embodiment, the system identifies geographic areas covered by a communication network. The system determines, for each identified geographic area, a network performance metric for the identified geographic area based on a difference between: (1) a first average network speed of the communication network in the identified geographic area during prior time periods in which the communication network is busy, and (2) a second average network speed of the communication network in the identified geographic area during second prior time periods in which the communication network is not busy. The system compares the respective performance metrics of the geographic areas to a threshold network performance metric, which is determined by a congestion-analysis machine learning (ML) model. The system identifies traffic congestions in one or more of the identified geographic areas having a determined network performance metric below the threshold network performance metric.

Growing community of inventors

Menlo Park, CA, United States of America

Ying Li