At&t Intellectual Property I, LP

Eshrat Huda

David H Lu

Moshiur Rahman

Mukundan Sarukkai

Rajan Anand

Sachin Lohe

Timothy Neville

Mark Cottrell

Nimish Buch

James Gordon Beattie, Jr

Roque Rios, Iii

Stephen Francis Triano

Amee Fontanetta

Luis Ramos

Pei-En Pamela Hsu

Douglas Riecken

Kevin L D'Souza

Sunil Maloo

Russell Fischer

Prafulla Verma

Aspects of the subject disclosure may include, for example, a device having a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, including: selecting a first building block pattern function (bbDNA) having a first weight from a catalog, wherein the first bbDNA is based on a first mature pattern reaching a first bbDNA frequency threshold, wherein the first bbDNA is associated with at least one machine learning (ML) model of a plurality of ML models; selecting a second bbDNA having a second weight from the catalog, wherein the second bbDNA is associated with at least one ML model in the plurality of ML models; and creating a new ML model based on a combination of the first bbDNA and the second bbDNA. Other embodiments are disclosed.

System and method for automated cataloging and building machine learning models

Facilitating radio access network on-demand dynamic bandwidth allocation in advanced networks is provided herein. Operations of a system include determining that a group of network slice resources associated with network equipment fail to satisfy a specification applicable to a user equipment. The operations can also include extracting a first group of resource blocks from a first network slice resource of the group of network slice resources. Further, the operations can include reallocating the first group of resource blocks to a second network slice resource of the group of network slice resources. A combination of the first group of resource blocks and a second group of resource blocks of the second network slice resource is determined to satisfy the specification applicable to the user equipment.

Facilitating radio access network on-demand dynamic bandwidth allocation in advanced networks

An automated system provides end-to-end (E2E) orchestration for machine learning (ML)-enabled and software-defined network (SDN)-enabled reactive and predictive (e.g., 5G) cell-on-drone (COD) dispatch and deployment. The system may be configured to detect or predict traffic surges (e.g., relative to typical or baseline levels) in a given cell site and orchestrate provisioning of resources, including COD deployment, to address the surge. COD deployment may involve one or more clusters or colonies of drones equipped with low-powered cellular radio access (or small cell) nodes, where each cluster includes (or is led by) one or more SDN-equipped drones that provide intelligent SDN-on-drone (SOD) functionality.

Universal uncrewed aerial vehicle (UAV) colony wireline wireless orchestration and automation management

In one example, the present disclosure describes a device, computer-readable medium, and method for proactively adjusting the infrastructure of a communications network in response to reporting of real-time network performance. For instance, in one example, a method includes obtaining real-time network performance metrics directly from a user endpoint device operated by a customer of a telecommunication service provider network, correlating the real-time network performance metrics with data from another data source, wherein the data includes data other than network performance metrics, and adjusting an infrastructure of the telecommunication service provider network in response to an insight gleaned through the correlating.

Proactively adjusting network infrastructure in response to reporting of real-time network performance

Aspects of the subject disclosure may include, for example, a system including a cross-segment slice controller (CSSC) configured to interface with a software-defined network (SDN) controller and a software-defined radio (SDR) controller. The SDN controller may be associated with a core network and the SDR controller may be associated with a radio access network (RAN). The system further includes a machine learning (ML) component configured to obtain and analyze data regarding the core network and the RAN, and an intelligent end-to-end (E2E) orchestration platform (IEOP) configured to coordinate with the SDN controller and the SDR controller via the CSSC based on outputs of the ML component to provide dynamic cross-segment network slice management. Other embodiments are disclosed.

Intelligent machine learning (ML)-enabled end-to-end (E2E) automated orchestration for collaborative next-generation wireless wireline convergence (WWC)

Methods, systems, and apparatuses, among other things, may provide for an interactive dynamic mapping engine (IDME) for business intelligence, which may interactively obtain information for user devices from sources and schema unknown to the user devices.

Interactive and dynamic mapping engine (IDME)

Aspects of the subject disclosure may include, for example, monitoring status of a network configured to provide end-to-end delivery of services to priority user equipment authorized according to a prioritized class of service and other user equipment not authorized for the prioritized class of service. The prioritized class of service extends a reserved network capacity for end-to-end delivery of a service via first domain including first network slices and a second domain including second network slices. A network interruption compromising the reserved capacity is determined based on the monitored status and integration of an alternate group of slices into one of the first network domain, the second network domain, or both to replace the compromised group of slices, is orchestrated. Integration of the alternate group of slices restores reserved network capacity according to the prioritized class of service. Other embodiments are disclosed.

Network resiliency and impact coordination

Aspects of the subject disclosure may include, for example, receiving workload requests for tenant devices providing services to user devices; partitioning node resources to facilitate network slicing in a software defined network to provide the services; determining that the workload requests exceed available resources of the node; and outsourcing a portion of a load to one or more neighboring nodes, where the outsourcing is performed in coordination with a regional orchestrator and a SDN intelligence module. Other embodiments are disclosed.

System and method of software defined network enabled slicing as a service utilizing artificial intelligence

Methods, systems, and apparatuses, among other things, may provide for an interactive dynamic mapping engine (iDME) for business intelligence, which may interactively obtain information for user devices from sources and schema unknown to the user devices.

Techniques for mechanized modify/add/create/delete (MACD) for network configuration are provided. A method can include creating a data object from input data relating to a requested change to a target network configuration, the data object comprising a first parameter indicating a type of the requested change and a second parameter identifying the target network configuration; retrieving, from a repository according to a group of logical rules, executable instructions associated with the type of the requested change, as given by the first parameter of the data object, and the target network configuration, as given by the second parameter of the data object; and performing, further according to the group of logical rules, the requested change to the target network configuration, the performing of the requested change comprising executing the executable instructions retrieved from the repository.

Mechanized modify/add/create/delete for network configuration

Interactive and dynamic mapping engine (iDME)

Aspects of the subject disclosure may include, for example, participating in a communication session over a network with a second communication device that is remote from the communication device where the communication session includes a computer supported collaborative work environment utilizing a non-baton passing protocol, presenting content at a display device where the content is presented by the second communication device at a second display device, receiving first user input at the user interface where second user input is received by the second communication device where a conflict resolution is applied to events associated with the first and second user input, and presenting adjusted content at the display device. Other embodiments are disclosed.

Growing community of inventors

Hillsborough, NJ, United States of America

Eshrat Huda