Abstract: Systems and methods for analyzing and prioritizing alarms in a communications network are provided. A method, according to one implementation, includes the step of obtaining network information regarding the condition of a network. Using the network information, the method further includes performing a hybrid Machine Learning (ML) technique that includes training and inference of a plurality of ML models to calculate metrics of the network. Also, the method includes the step of selecting one of the plurality of ML models based on a combination of the metrics.

Abstract: Systems and methods for analyzing and prioritizing alarms in a communications network are provided. A method, according to one implementation, includes the step of obtaining network information regarding the condition of a network. Using the network information, the method further includes performing a hybrid Machine Learning (ML) technique that includes training and inference of a plurality of ML models to calculate metrics of the network. Also, the method includes the step of selecting one of the plurality of ML models based on a combination of the metrics.

Abstract: Systems and methods for analyzing root-causes of Wi-Fi issues in a Wi-Fi system associated with a Local Area Network (LAN) are described in the present disclosure. A method, according to one embodiment, includes a step of monitoring a Wi-Fi system associated with a LAN to detect authentication failures in the Wi-Fi system. In response to detecting an authentication failure in the Wi-Fi system, the method also includes the step of analyzing the authentication failure to determine one or more root-causes of the authentication failure. The method also includes pushing changes to the Wi-Fi system to automatically remediate the one or more root-causes in the Wi-Fi system.

Abstract: Systems and methods for predicting the location of unknown network devices within a particular site of a multi-site network are provided. A method, according to one implementation, includes obtaining transmission characteristics related to any of packets and frames transmitted between an unknown network device and a plurality of beacon devices. Each beacon device is a network device associated with a fixed site location within a multi-site network. The method also includes utilizing the transmission characteristics to predict a site within the multi-site network where the unknown network device is located.

Abstract: Systems and methods for analyzing root-causes of Wi-Fi issues in a Wi-Fi system associated with a Local Area Network (LAN) are described in the present disclosure. A method, according to one embodiment, includes a step of monitoring a Wi-Fi system associated with a LAN to detect authentication failures in the Wi-Fi system. In response to detecting an authentication failure in the Wi-Fi system, the method also includes the step of analyzing the authentication failure to determine one or more root-causes of the authentication failure. The method also includes pushing changes to the Wi-Fi system to automatically remediate the one or more root-causes in the Wi-Fi system.

Abstract: Systems and methods for analyzing a root cause of issues in a network, such as an optical communication network, are provided. A method, according to one implementation, includes the steps of deriving symptoms indicative of issues in a network by utilizing performance data obtained from network elements in the network and storing the derived symptoms in a database. The method also includes the step of obtaining diagnostics from the network elements. Also, the method may include utilizing the database to compute distances between the derived symptoms and each of the diagnostics, whereby the computed distances may be configured to correspond to dissimilarities between the derived symptoms and the diagnostics. The distances are computed based on machine learning models, user feedback, and analytical functions. Also, the method includes analyzing a root cause of the derived symptoms based on a lowest distance selected from the computed distances.

Abstract: Systems and methods for analyzing a root cause of issues in a network, such as an optical communication network, are provided. A method, according to one implementation, includes the steps of deriving symptoms indicative of issues in a network by utilizing performance data obtained from network elements in the network and storing the derived symptoms in a database. The method also includes the step of obtaining diagnostics from the network elements. Also, the method may include utilizing the database to compute distances between the derived symptoms and each of the diagnostics, whereby the computed distances may be configured to correspond to dissimilarities between the derived symptoms and the diagnostics. The distances are computed based on machine learning models, user feedback, and analytical functions. Also, the method includes analyzing a root cause of the derived symptoms based on a lowest distance selected from the computed distances.

Abstract: Systems and methods of automated feature selection and pattern discovery of multi-variate time-series include obtaining a multi-variate times-series from a network; preprocessing the multi-variate times-series to account for sampling intervals and missing data in the multi-variate times-series; determining a distance matrix for the multi-variate times-series which estimates correlation among features in the multi-variate times-series; performing clustering on the distance matrix; reducing dimensionality of the multi-variate times-series based on the clustering to provide a lower-dimensionality time-series; and providing the lower-dimensionality time-series to one or more applications configured to analyze the multi-variate times-series from the network, wherein the lower-dimensionality time-series provides similar information as the multi-variate time-series with fewer dimensions thereby improving computational complexity of the one or more applications.

Abstract: A monitoring system for microservices includes a messaging system communicatively coupled to a plurality of services, wherein the messaging system is configured to publish metrics from the plurality of services to the analytics engine; an analytics engine communicatively coupled to the messaging system, wherein the analytics engine is configured to analyze the metrics to determine insights related to operation of the plurality of services; and a policy engine communicatively coupled to the analytics engine, wherein the policy engine is configured to determine actions associated with one or more services based on the analysis and push the actions to the one or more services for implementation.

Abstract: Systems and methods of automated feature selection and pattern discovery of multi-variate time-series include obtaining a multi-variate times-series from a network; preprocessing the multi-variate times-series to account for sampling intervals and missing data in the multi-variate times-series; determining a distance matrix for the multi-variate times-series which estimates correlation among features in the multi-variate times-series; performing clustering on the distance matrix; reducing dimensionality of the multi-variate times-series based on the clustering to provide a lower-dimensionality time-series; and providing the lower-dimensionality time-series to one or more applications configured to analyze the multi-variate times-series from the network, wherein the lower-dimensionality time-series provides similar information as the multi-variate time-series with fewer dimensions thereby improving computational complexity of the one or more applications.

Abstract: A system to predict events in a telecommunications network includes a processor; and memory storing instructions that, when executed, cause the processor to, responsive to obtained Performance Monitoring (PM) data over time from the telecommunications network, reduce an n-dimensional time-series into a 1-dimensional distribution, n being an integer represent a number of different PM data, wherein the n different PM data relate to a component, device, or link in the telecommunications network, utilize one or more forecast models to match the 1-dimensional distribution and to extrapolate the 1-dimensional distribution towards future time, and display a graphical user interface of a graph of the 1-dimensional distribution and the extrapolated 1-dimensional distribution, wherein the graph displays a probability of the component, device, or link being normal versus time. Also, techniques are described herein for labeling of PM data for use in supervised Machine Learning (ML).

Abstract: A monitoring system for microservices includes a messaging system communicatively coupled to a plurality of services, wherein the messaging system is configured to publish metrics from the plurality of services to the analytics engine; an analytics engine communicatively coupled to the messaging system, wherein the analytics engine is configured to analyze the metrics to determine insights related to operation of the plurality of services; and a policy engine communicatively coupled to the analytics engine, wherein the policy engine is configured to determine actions associated with one or more services based on the analysis and push the actions to the one or more services for implementation.