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 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 include obtaining overlay telemetry data from a plurality of overlays, wherein each overlay is an application and there is a corresponding telemetry adaptor for each overlay; obtaining underlay telemetry data from one or more underlays, wherein each underlay includes physical infrastructure for supporting one or more of network, compute, and store functions for the plurality of overlays; analyzing the overlay telemetry data and the underlay telemetry data via a Key Performance Factor (KPF) model that correlates one or more of the plurality of overlays and the one or more underlays together; responsive to an anomaly or a threshold crossing based on the KPF model, performing a Root Cause Analysis (RCA) to identify a root cause of the anomaly or the threshold crossing; and mapping one or more actions with associated priorities to the root cause utilizing one or more remediation modules each associated with an overlay.

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: In various embodiments, the present disclosure relates to systems and methods for enhanced reinforcement learning (RL) algorithms using future state prediction. In some embodiments, an offline emulator can be applied allowing the generation of samples, thus supporting continuous training of the system and fast-forward fabric saturation. The fabric accepts transactions which allocate resources with respect to the transactions needs and constraints and contains an RL/AI model(s) which are continuously learning based on the current reward combined with reward scaling. By modelling the fabric and transactions in an emulator, it is possible to predict future states and calculate adjusted rewards with respect to the optimal criterion. A state generator is based on modeling past historical transactions, allowing a user to anticipate future state characteristics of the fabric. In some embodiments, online learning is based on adjusted rewards which are more representative with respect to the objective function.

Abstract: Systems, methods, and computer-readable media are provided for logging long-term data and analyzing the long-term data with short-term data to determine the health of fiber connections in an optical network. A method, according to one implementation, includes a step of obtaining data associated with performance of fiber connections of an optical network. The fiber connections include at least an inter-node fiber connecting two adjacent network nodes and an intra-node fiber connection connecting two photonic devices within each of the two adjacent network nodes. The method further includes the step of logging the data over time as historical data and then analyzing the health of the fiber connections based on the historical data and newly-obtained data. Also, the method includes displaying a report on an interactive user interface, whereby the report is configured to show the health of the fiber connections.

Abstract: Systems and methods include obtaining overlay telemetry data from a plurality of overlays, wherein each overlay is an application and there is a corresponding telemetry adaptor for each overlay; obtaining underlay telemetry data from one or more underlays, wherein each underlay includes physical infrastructure for supporting one or more of network, compute, and store functions for the plurality of overlays; analyzing the overlay telemetry data and the underlay telemetry data via a Key Performance Factor (KPF) model that correlates one or more of the plurality of overlays and the one or more underlays together; responsive to an anomaly or a threshold crossing based on the KPF model, performing a Root Cause Analysis (RCA) to identify a root cause of the anomaly or the threshold crossing; and mapping one or more actions with associated priorities to the root cause utilizing one or more remediation modules each associated with an overlay.

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 detecting patterns in data from a time-series are provided. According to some implementations, the systems and methods may use network topology information combined with object recognition techniques to detect patterns. One embodiment of a method includes the steps of obtaining information defining a topology of a multi-layer network having a plurality of Network Elements (NEs) and a plurality of links interconnecting the NEs and receiving Performance Monitoring (PM) metrics and one or more alarms from the multi-layer network. Based on the information defining the topology, the PM metrics, and the one or more alarms, the method also includes the step of utilizing a Machine Learning (ML) process to identify a problematic component from the plurality of NEs and links and to identify a root cause associated with the problematic component.

Abstract: Systems and methods for recommending actions in a closed-loop system are provided. In one embodiment, an Action Recommendation Engine (ARE) may include a processor and memory configured to store computer programs having instructions that cause the processor to obtain input data pertaining to a state of a network and obtain information regarding one or more historical actions performed on the network. Also, the instructions may cause the processor to utilize a Machine Learning (ML) model for imposing one or more current actions on the network, the one or more current actions selected from the group of procedures consisting of: a) suggesting one or more remediation actions that, when performed, transition the network from a problematic state to a normal state, and b) identifying one or more root causes in response to detecting a transition in the network from a normal state to a problematic state.

Abstract: Systems and methods implemented by a computer to detect abnormal behavior in a network include obtaining Performance Monitoring (PM) data including one or more of production PM data, lab PM data, and simulated PM data; determining a model based on machine learning training with the PM data; receiving live PM data from the network; utilizing the live PM data with the model to detect an anomaly in the network; and causing an action to address the anomaly.

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 recommending actions in a closed-loop system are provided. In one embodiment, an Action Recommendation Engine (ARE) may include a processor and memory configured to store computer programs having instructions that cause the processor to obtain input data pertaining to a state of a network and obtain information regarding one or more historical actions performed on the network. Also, the instructions may cause the processor to utilize a Machine Learning (ML) model for imposing one or more current actions on the network, the one or more current actions selected from the group of procedures consisting of: a) suggesting one or more remediation actions that, when performed, transition the network from a problematic state to a normal state, and b) identifying one or more root causes in response to detecting a transition in the network from a normal state to a problematic state.

Abstract: System and methods for autonomous resource partitioning in a network include a resource controller configured to provision resources which are any of virtual resources and physical resources in one or more layers in the network and monitor availability of the resources in the network; a resource manager configured to determine the any of virtual resources and physical resources as required for Quality of Service (QoS) in the network; a resource broker configured to advertise and assign resource requests to corresponding resources; and a partition manager configured to track the utilization of the resources provided by the one or more layers and to adjust resource usage of the resources in negotiation with the resource broker to minimize a cost of implementation.

Abstract: Systems and methods include obtaining performance monitoring data from a network which operates and generates the performance monitoring data which reflects a current state of the network; responsive to a predetermined reward which quantifies minimizing or maximizing an aspect in the network for Reinforcement Learning, causing one or more actions to be performed in the network, wherein the one or more actions are based on the predetermined reward; obtaining updated performance monitoring data from the network subsequent to the one or more actions to determine an updated state of the network; and continuing the causing the one or more actions to be performed in the network based on the current state and the updated state. The causing the one or more actions to be performed in the network is performed to maximize or minimize a total discounted accumulated reward.

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 enacting or applying configuration changes (e.g., updates, optimizations) in a network element of a production network are provided. The configuration changes may be proposed and enacted in a collaboration system between artificial intelligence (AI) devices and human-controlled devices. According to one implementation, a system includes a production network having a plurality of network elements and a computer connected to the production network. The computer is configured to request a new configuration update regarding a first network element. The system further includes an electronic ledger configured to store a history of one or more configuration updates that have been previously enacted with respect to the first network element.

Abstract: Systems and methods for detecting patterns in data from a time-series are provided. According to some implementations, the systems and methods may use network topology information combined with object recognition techniques to detect patterns. One embodiment of a method includes the steps of obtaining information defining a topology of a multi-layer network having a plurality of Network Elements (NEs) and a plurality of links interconnecting the NEs and receiving Performance Monitoring (PM) metrics and one or more alarms from the multi-layer network. Based on the information defining the topology, the PM metrics, and the one or more alarms, the method also includes the step of utilizing a Machine Learning (ML) process to identify a problematic component from the plurality of NEs and links and to identify a root cause associated with the problematic component.

Abstract: Systems and methods for enacting or applying configuration changes (e.g., updates, optimizations) in a network element of a production network are provided. The configuration changes may be proposed and enacted in a collaboration system between artificial intelligence (AI) devices and human-controlled devices. According to one implementation, a system includes a production network having a plurality of network elements and a computer connected to the production network. The computer is configured to request a new configuration update regarding a first network element. The system further includes an electronic ledger configured to store a history of one or more configuration updates that have been previously enacted with respect to the first network element.

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).