Abstract: Systems and methods include steps of determining a state of a network based on telemetry data; determining a value of a reward associated with the state; determining an action to take on the network to bring the network to a next state that is expected to have a better than or equal to value of the reward; and causing the action to be implemented in the network. The steps can also include continuing the determining steps and the causing step.

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: Artificial Intelligence (AI)-based network control includes obtaining data from a network having a plurality of network elements; analyzing the data with one or more Machine Learning (ML) algorithms to determine one or more actions for network control; analyzing the determined one or more actions to determine any risks associated therewith; and one of allowing, modifying, and blocking the determined one or more actions based on the determined risks to safeguard the network. The risks can be based on one or more of (1) non-deterministic behavior AI inference which is statistical in nature, (2) unbounded uncertainty of the AI inference that can result in arbitrarily large inaccuracy on rare occasions, (3) unpredictable behavior of the AI inference in presence of input data that is different than data in training and testing datasets, and (4) malicious input data.

Abstract: Systems and methods described herein are adapted to predict the intent of a network operator when it is determined that configuration changes (or config changes) are made to a network device. A method, according to one implementation, includes the step of collecting raw data related to a Network Element (NE). The method also includes the step of pre-processing the raw data to obtain a config change associated with the NE. Also, the method includes the step of applying the config change as input to a ML model to predict a user intent representing a desired network outcome.

Abstract: Systems and methods are provided for analyzing one or more root causes of service degradation events in a network or other environment. A method, according to one implementation, includes a step of monitoring a plurality of overlying services offered in an underlying infrastructure having a plurality of resources arranged with a specific topology. In response to detecting a negative impact on the overlying services during a predetermined time window and based on an understanding of the specific topology, the method further includes the step of identifying suspect components from the plurality of resources in the underlying infrastructure. The method also includes the step of obtaining status information with respect to the suspect components to determine a root cause of the negative impact on the overlying services.

Abstract: Systems, methods, and Machine Learning (ML) techniques are provided for detecting changes to configuration information associated with network devices and determining if the changes are network compliant. A method, according to one implementation, includes the step of fetching configuration data associated with a Network Element (NE) to be monitored. Based on detection of a configuration difference (config diff), whereby the configuration data has changed with respect to previously-stored configuration information, the method further includes the step of monitoring the configuration data to determine if the configuration data conforms to predetermined compliance rules and policies.

Abstract: Systems and methods include receiving a machine learning model that is configured to detect anomalies in network devices operating in a multi-layer network, wherein the machine learning model is trained via unsupervised learning that includes training the machine learning model with unlabeled data that describes an operational status of the network devices over time; receiving live data related to a current operational status of the network devices; analyzing the live data with the machine learning model; and detecting an anomaly related to any of the network device based on the analyzing.

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, methods, and computer-readable media including software logic are provided for optimizing Border Gateway Protocol (BGP) traffic in a telecommunications network. In one embodiment, systems and methods include, with a current state of one or more inter-Autonomous Systems (AS) links, causing performance of an action in the telecommunication network, determining a metric based on the action to determine an updated current state of the one or more inter-AS links, and utilizing the metric to perform a further action to achieve one or more rewards associated with the one or more inter-AS links.

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 include receiving alarms from a network; utilizing a machine learning model to classify the alarms as one of important and non-important; and displaying the important alarms and suppressing display of the non-important alarms. The systems and methods can further include training the machine learning model with historical alarm data that includes features related to an associated device and comments related to how a Network Operations Center (NOC) handles an associated alarm or group of alarms. The training can be via supervised machine learning with the features used as labels or via reinforcement learning with the features used as a reward.

Abstract: Artificial Intelligence (AI)-based network control includes obtaining data from a network having a plurality of network elements; analyzing the data with one or more Machine Learning (ML) algorithms to determine one or more actions for network control; analyzing the determined one or more actions to determine any risks associated therewith; and one of allowing, modifying, and blocking the determined one or more actions based on the determined risks to safeguard the network. The risks can be based on one or more of (1) non-deterministic behavior AI inference which is statistical in nature, (2) unbounded uncertainty of the AI inference that can result in arbitrarily large inaccuracy on rare occasions, (3) unpredictable behavior of the AI inference in presence of input data that is different than data in training and testing datasets, and (4) malicious input data.

Abstract: Systems and methods are provided for analyzing one or more root causes of service degradation events in a network or other environment. A method, according to one implementation, includes a step of monitoring a plurality of overlying services offered in an underlying infrastructure having a plurality of resources arranged with a specific topology. In response to detecting a negative impact on the overlying services during a predetermined time window and based on an understanding of the specific topology, the method further includes the step of identifying suspect components from the plurality of resources in the underlying infrastructure. The method also includes the step of obtaining status information with respect to the suspect components to determine a root cause of the negative impact on the overlying services.

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 are provided herein for analyzing root-causes of network access failures in a wireless network. In response to detecting that a client device experiences a network access failure that prevents communication with a server device, a method, according to one implementation, includes a step of analyzing the network access failure to predict one or more root-causes. Also, the method includes beginning a remediation procedure for remediating the one or more root-causes.

Abstract: An Artificial Intelligence (AI)-based network control system includes an AI system configured to obtain data from a network having a plurality of network elements and to determine actions for network control through one or more Machine Learning (ML) algorithms; a controller configured to cause the actions in the network; and a safeguard module between the AI system and the controller, wherein the safeguard module is configured to one of allow, block, and modify the actions from the AI system.

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 include obtaining input data related to a networking system; modeling operation of the networking system via a composite model that includes a plurality of sub-models that collectively form the composite model, wherein at least one sub-model is a behavioral sub-model and at least one sub-model is a machine learning model, wherein various data in the input data is provided to corresponding sub-models, and wherein each sub-model is configured to model one or more components in the networking system; and providing output data based on the modeling.

Abstract: Systems and methods include receiving a machine learning model that is configured to detect anomalies in network devices operating in a multi-layer network, wherein the machine learning model is trained via unsupervised learning that includes training the machine learning model with unlabeled data that describes an operational status of the network devices over time; receiving live data related to a current operational status of the network devices; analyzing the live data with the machine learning model; and detecting an anomaly related to any of the network device based on the analyzing.