Vigyanlabs Innovations Private Limited

Mousumi Paul

Srivatsa Krishnaswamy

Sanjaya Ganesh

Srinivas Varadarajan

A system and method configured in an electrical device for providing a monitoring solution that identifies the intermittent or anomalous behavior of electronic/electric appliances when in use, comprising: receiving present real-time power features like current, voltage, power factor, power consumption of the associated device, and maintaining a history of past real-time readings of the device in its ideal working periods; forming rule-based clusters of different internal states of the device from the past history data at ideal working periods; determining which of said present readings are correlated; computing a deviation between at least some of said present and at least some of said clusters; and declaring an anomaly when said present readings deviation exceeds a predetermined threshold from all of the said clusters.

System and method of monitoring electrical devices to detect anomaly in the electrical devices

Data Center (DC) server power management monitors resource utilization and energy consumption characteristics of an individual host server, and a Virtual Machine (VM) and the applications running inside any VM of DC servers. An analysis and learning module identifies trends and opportunities to optimize DC resources by releasing the underutilized host servers. It derives power metrics to measure the energy footprint of the VMs and the associated applications. It suggests optimal destination servers to migrate each of the VMs with corresponding applications from the underutilized host servers. The power consumption of these VMs with their applications on the power-efficient destination servers is less after the migration. Powering off the underutilized freed-up servers saves energy impacting the overall power consumption of the data center. The learning modules predict the opportunities for power capping on any VM or physical host server to reduce the data center's energy consumption without impacting performance.

System and method to analyze and optimize application level resource and energy consumption by data center servers

A system and method configured with an electronic device to enable prediction-based power management by providing direct transition to a lower power state such that overall energy consumption is reduced. The system and method includes an idleness information recording module configured to, using a power management agent, non-intrusively observe and record usage and idleness information of the electronic device, a learning module configured to, using a neural network operatively coupled with the power management agent, conduct deep learning of idleness patterns of the electronic device, a prediction module configured to predict future idleness of the electronic device based on the deep learning of the idleness patterns, and a prediction-based lower power state transfer module configured to directly transition the electronic device to lower power state based on the predicted future idleness.

Growing community of inventors

Howrah, India

Mousumi Paul