公开(公告)号：US20210051060A1

公开(公告)日：2021-02-18

申请号：US16538978

申请日：2019-08-13

Applicant: Verizon Patent and Licensing Inc.

Inventor： Raghuram Parvataneni ,  Kirk Campbell ,  Ravi Sharma ,  Anil K. Guntupalli

IPC: H04L12/24 ,  H04L12/911 ,  H04L12/26 ,  G06N20/00

Abstract: A method, a device, and a non-transitory storage medium are described in which a machine learning-based resource management service is provided. A network device obtains network and end device information, and uses machine learning to determine whether to adjust an auto-scaling rule pertaining to the provisioning of an application service. The network device generates a modified auto-scaling rule based on the analysis.

公开(公告)号：US20200382581A1

公开(公告)日：2020-12-03

申请号：US16996659

申请日：2020-08-18

Applicant: Verizon Patent and Licensing Inc.

Inventor： Kirk Campbell ,  Ravi Sharma ,  Raghuram Parvataneni

IPC: H04L29/08 ,  H04L12/813 ,  H04W24/02

Abstract: An exemplary edge compute orchestration system that is communicatively coupled with a set of edge compute nodes in a communication network accesses performance data aggregated by a particular edge compute node of the set. The performance data includes a performance metric and geolocation data detected by a user equipment (UE) device communicatively coupled to the communication network. The edge compute orchestration system integrates the performance data into a geolocation-indexed performance dataset representative of detected performance metrics, indexed by geolocation, for the communication network. Then, based on the geolocation-indexed performance dataset, the edge compute orchestration system selects the particular edge compute node for performance of an edge compute task. Corresponding systems and methods are also disclosed.