Cisco Technology, Inc.

Amitesh Shukla

Manish Jhanji

Rakesh Mishra

Satish Kumar Mandavilly

Satpal Dalal

Kabiraj Sethi

Subhash Kodnad

Ajith Chandran

Jigar Amin

In one embodiment, a method includes receiving, by a mobile edge computing (MEC) controller and from an application analytic engine, a registration request for an application. The registration request includes a request for MEC key performance indicators (KPIs). The method also includes communicating, by the MEC controller, MEC data associated with a first MEC host and a second MEC host to the application analytic engine. The method further includes receiving, by the MEC controller, MEC policies from the application analytic engine, determining to host the application in the first MEC host based on the MEC policies, and communicating the MEC policies to the first MEC host.

Systems and methods for managing MEC application hosting

Methods are provided in which devices vulnerable to performance degradation during a network offload process are identified and handled accordingly. In these methods, a network controller obtains data associated with operational performance of devices in a radio network during one or more offload procedures in which the devices are to be transitioned off of the radio network. The network controller further analyzes the data to determine impact to at least one performance parameter of the devices during the one or more offload procedures, and during a subsequent offload procedure, the network controller orchestrates offloading of the devices according to the impact determined to the at least one performance parameter based on the analyzing.

Optimizing private network during offload for user equipment performance parameters

Systems, methods, and storage media for generating and/or recoverying an end-to-end hybrid cloud snapshot are disclosed. Exemplary implementations may: receive application specific triggering criteria for generating an end-to-end hybrid cloud snapshot; trigger a snapshot event based on the application specific triggering criteria and a machine learning model; accumulate snapshot portions from a plurality of nodes in a hybrid cloud network; and store, in a snapshot database, the end-to-end hybrid cloud snapshot comprising the snapshot portions from the plurality of nodes. Exemplary implementations may further include: generate a recovery model based on a snapshot database, wherein the snapshot database comprises a plurality of network snapshots associated with a network, receive parameters for a desired recovery state, and identify a recommended network snapshot from the plurality of network snapshots based on the recovery model and the parameters for the desired recovery state.

Intelligent snapshot generation and recovery in a distributed system

In one embodiment, a machine learning server in a computer network determines a plurality of computing features shared across a given set of computing products, and collects, from each computing product of the given set, problem-solution data for each computing feature of the plurality of computing features. Problem-solution data is indicative of problems related to a respective computing feature, attempted solution actions for the problems, and outcomes of the attempted solutions on the problem. The machine learning server updates a machine learning model of suggested solutions for computing-feature-specific problems based on the collected problem-solution data, and provides, based on the machine learning model, a particular suggested solution for a particular computing-feature-specific problem to a particular computing product. An outcome of the particular suggested solution for the particular computing-feature-specific problem on the particular computing product may then be fed back to the machine learning server as collected problem-solution data.

Feature-specific adaptive models for support tools

Systems and methods provide for managing a power consumption policy for a powered device. A network controller may be configured to receive power consumption information for a powered device (PD) connected to power sourcing equipment (e.g., a PSE device), calculate a predicted threshold for the PD based on the power consumption information for the PD, and transmit the predicted threshold for the PD to the PSE device. Power sourcing equipment is configured to calculate power consumption information for the PD, transmit the power consumption information for the PD to the network controller, receive a predicted threshold for the PD, and implement a power consumption policy for the PD based on the predicted threshold.

Controller-based management of noncompliant power over ethernet devices

Systems, methods, and computer-readable media are disclosed for implementing a load balance update. A system may be configured to receive a plurality performance reports for a plurality of service nodes running on the plurality of host entities, wherein each performance report comprises performance indicators for a service node in the plurality of service nodes running on a host entity in the plurality of host entities, generate a load balance update based on the performance reports, and implement the load balance update at a load balancer.

Load balancing in a distributed system

An antenna may be provided. First, a Machine Learning (ML) model may be used, at a predetermined time, to predict a probable location of at least one of a plurality of client devices. Next, spatial coordinates may be obtained for the probable location from the ML model. Then an antenna sub-array of an antenna array may be steered toward the spatial coordinates of the probable location. The antenna sub-array may be unallocated.

Growing community of inventors

San Ramon, CA, United States of America

Amitesh Shukla