Communication network optimization based on predicted enhancement gain

    公开(公告)号:US10979914B2

    公开(公告)日:2021-04-13

    申请号:US16389226

    申请日:2019-04-19

    Applicant: Facebook, Inc.

    Abstract: 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.

    Detecting Communication Network Insights of Alerts

    公开(公告)号:US20200351698A1

    公开(公告)日:2020-11-05

    申请号:US16932483

    申请日:2020-07-17

    Applicant: Facebook, Inc.

    Abstract: 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.

    Measuring the Impact of Network Deployments
    13.
    发明申请

    公开(公告)号:US20200296006A1

    公开(公告)日:2020-09-17

    申请号:US16352593

    申请日:2019-03-13

    Applicant: Facebook, Inc.

    Abstract: In one embodiment, a computing system may determine network metrics for geographic regions connected by a communication network. The geographic regions may include a geographic region of interest impacted by a network deployment. The system may identify candidate control regions by clustering geographic regions of into a first group based on metric feature of network metric shared by the geographic regions. The system may select control regions by identifying a second group of geographic regions from the first group of geographic regions based on a comparison between the region of interest and each of the first group of geographic regions. The system may compare a first network metric of the geographic region of interest to first a metric baseline determined based on the one or more control regions. The system may determine whether the first network metric has a change greater than a threshold after the network deployment.

    Detecting communication network insights of alerts

    公开(公告)号:US10779183B2

    公开(公告)日:2020-09-15

    申请号:US16226477

    申请日:2018-12-19

    Applicant: Facebook, Inc.

    Abstract: 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.

    Detecting Communication Network Insights Of Alerts

    公开(公告)号:US20200028782A1

    公开(公告)日:2020-01-23

    申请号:US16155510

    申请日:2018-10-09

    Applicant: Facebook, Inc.

    Abstract: 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.

Patent Agency Ranking