At&t Intellectual Property I, L.p.

Sbc Technology Resources, Inc.

Chuxin Chen

George Dome

John Oetting

George T Noll

Ralph Gnauck

Dean Bragg

John Ng

David Kinsey

John Getting

The autonomous cloud design system may determine a design that may appropriately mix emerging technologies and operations to provide a versatile and cost-effective or efficient solution for a given cloud site.

Autonomous cloud design and control

Cloud infrastructure planning systems and methods can utilize artificial intelligence/machine learning agents for developing a plan of demand, plan of record, plan of execution, and plan of availability for developing cloud infrastructure plans that are more precise and accurate, and that learn from previous planning and deployments. Some agents include one or more of supervised, unsupervised, and reinforcement machine learning to develop accurate predictions and perform self-tuning alone or in conjunction with other agents.

Cloud infrastructure planning assistant via multi-agent AI

A method includes receiving, by a processor, metadata for deploying a virtual function on a cloud network. The method may include determining, by the processor, whether deployment of the virtual function is possible without conflicting with the metadata. The method may include based on the determination that the deployment of the virtual function is possible without conflicting with the metadata, designing, by the processor, a cloud plan, or a transport plan. The method may include determining, based on the metadata, a network configuration to implement the cloud plan or the transport plan. The method may include configuring, by the processor, the cloud network using the network configuration.

Closed-loop deployment of virtual functions and cloud infrastructure

Systems and methods disclosed herein relate to autonomous agents. A first autonomous agent receives, from a first sensor, a first set of event data indicating events relating to a subject. The first autonomous agent provides the first set of event data to a data aggregator. The first autonomous agent receives, from the data aggregator, correlated event data including events sensed by the first autonomous agent and a second autonomous agent. The first autonomous agent applies machine learning model to the correlated event data to predict a first pattern of activity and determines, based on the first pattern of activity, that a first action is to be performed, causing the first actuator module to perform the first action.

Integrated assistance platform

Systems and methods provide capacity planning, management, and engineering automation in networks including virtualization.

Capacity planning, management, and engineering automation platform

A method includes receiving metadata for deploying a virtual function on a cloud network. The metadata includes a recipe, policy, and template. The method includes, based on the metadata, designing a cloud plan and a transport plan for deploying the virtual function on the cloud network to meet a forecasted demand. The method includes determining a network configuration to implement the cloud plan and the network plan based on the metadata and causing the cloud network to be configured using the network configuration. The method includes instantiating the virtual function on the configured cloud network.

An intelligent preventative maintenance architecture for maintaining a plurality of cloud components operating within a cloud computing environment is disclosed. The architecture can perform a predictive failure analysis that monitors health of at least a portion of the plurality of cloud components that hosts a mission critical application. The predictive failure analysis receives sensor data that includes environmental data associated with environmental characteristics of the cloud computing environment and cloud component data associated with operational characteristics of at least a portion of the plurality of cloud components operating within the cloud computing environment. The predictive failure analysis analyzes the sensor data to detect an abnormal pattern within the sensor data, determines a root cause of the abnormal pattern, and predicts a probability of a failure of at least one cloud component of the plurality of cloud components.

Intelligent preventative maintenance of critical applications in cloud environments

An open-loop control assistance ('OLCA') system can collect data, correlate and aggregate the data, and perform multi-dimensional analytics on the correlated and aggregated data. The OLCA system can then determine plurality of viable options for a next action to be taken by an operator in an open-loop control process, and can determine a specific option as an optimal choice for the operator to select. The OLCA system can present the plurality of viable options and a rationale explaining why the operator should select the specific option. The OLCA system can capture action(s) taken by the operator, and if the action does not correspond to the recommended action, the OLCA system can capture a reason regarding why the optimal choice was not selected. The OLCA system can analyze results from the action(s). The OLCA system can then fine-tune the open-loop control process based upon the results and the cause(s) thereof.

Open-loop control assistant to guide human-machine interaction

A system for expansive network control comprising: a development engine includes a scenario building engine configured to build an abstracted view of at least one sub-network based on a network inventory; a gamification engine communicating with a user input/output device providing at least one simulated scenario involving a simulated network threat to the user input/output device; and a machine learning engine communicating with the gamification engine, wherein the machine learning engine generates at least one strategy, the machine learning engine capturing the scenario and the user input from the user input/output device; an expansive network control operation engine includes an expansive network control engine communicating with the machine learning engine; an execution engine communicating with the expansive network control engine; a threat detection engine communicating with at least one external threat data source, the at least one external threat data source including at least one of weather, seismic, natural disaster, law enforcement, news and public utility data; wherein the threat detection engine monitors the at least one data source to detect a threat and passes a threat type and an impacted sub-network location for the threat type to the expansive network control engine; wherein the expansive network control engine is configured to retrieve at least one of an available inventory and priority of the impacted sub-network; wherein based on the at least one strategy, the expansive network control engine triggers the execution engine to perform an action to address the threat; an expansive network planning engine includes a simulation engine; the simulation engine configured to trigger an event and record a simulation result of the event; and a spare recommender, wherein the simulation engine communicates the simulation result to the spare recommender and wherein the spare recommender analyzes the simulation result to determine if excessive spares exist.

Expansive network control design system

A computer-based monitoring system provides interactive topology information about a synchronized optical network (SONET). The monitoring system utilizes a trunks integrated record keeping system (TIRKS) connected to the SONET for collecting status data in a raw format. A computer system retrieves the raw format status data from TIRKS and provides the data in a simple graphical user interface to a user. The interface includes several menus from which the user may specify specific components of the SONET, and a graphical output for providing a graphical representation of the SONET. The graphical output illustrates each node and link and interactively provides more detailed information about any user selected link or node.

Interactive topology graphs for visualization and characterization of SONET consumption patterns

A rule based capacity management system for an inter office facility is provided. The system includes a presentation layer for providing a graphical user interface to a user. The presentation layer is capable of receiving one or more rules from the user and for providing one or more analytical reports of the equipment based on the rules. The system also includes a data layer for storing rules, including the rules received from the user, and for connecting to an inventory system such as trunks integrated record keeping system (TIRKS). The system also includes a business layer interfacing between the presentation layer and the data layer. The business layer creates the analytical reports responsive to the rules and the raw data.

Growing community of inventors

San Francisco, CA, United States of America

Chuxin Chen