Dell Products Inc.

Vasanth Sathyanarayanan

Parminder Singh Sethi

Lakshmi Saroja Nalam

Bing Liu

Rahul Deo Vishwakarma

A method comprises generating a plurality of device trees for respective ones of a plurality of devices. The plurality of device trees respectively comprise a plurality of nodes corresponding to a device, one or more components of the device and one or more alerts associated with the one or more components. In the method, weights are assigned to the plurality of nodes of the plurality of device trees, and rates of degradation for the respective ones of the plurality of devices are computed based, at least in part, on the assigned weights. Workloads for the respective ones of the plurality of devices are predicted using one or more machine learning models, and a ranking of the respective ones of the plurality of devices is generated based, at least in part, on at least one of the rates of degradation and the predicted workloads.

Device management based on degradation and workload

In one aspect, an example methodology implementing the disclosed techniques includes, by a disk controller of a plurality of disks of a data storage system, collecting usage telemetry from the plurality of disks and initiating determination of one or more candidate time slots for performing a battery learn cycle using a machine learning model. The machine learning model is trained using the usage telemetry from the plurality of disks. The method also includes, by the disk controller, presenting one or more of the one or more candidate time slots for performing a battery learn cycle.

Battery learn cycle management

Methods, apparatus, and processor-readable storage media for automated power-related device usage determinations using artificial intelligence techniques are provided herein. An example computer-implemented method includes determining power-related information for one or more devices by processing utilization data associated with the device(s) using artificial intelligence techniques; determining, based at least in part on the power-related information, multiple instances of inactivity and durations thereof for the device(s); determining at least one particular duration of inactivity for the device(s) based at least in part on a number of occurrences of each of the determined durations of instances of inactivity; generating, based at least in part on the at least one particular duration of inactivity, one or more sleep mode configuration modification recommendations for the device(s); and performing one or more automated actions based on the one or more sleep mode configuration modification recommendations.

Automated power-related device usage determinations using artificial intelligence techniques

The described technology is generally directed towards predicting the survival of a storage device (e.g., a hard disk drive or a solid state drive) to a specified time point, expressed as a confidence score, via a prediction uncertainty quantifier framework with a machine learning classifier. The confidence score corresponds to the likelihood of a storage device surviving until a specified time point (e.g., for n hours). In one implementation, a conformal prediction framework provides the confidence score for a storage device, based on survival rate data predicted using recent telemetry data collected for that storage device by an online semi-parametric Mondrian survival forest classifier. Updated confidence scores based on updated telemetry data can be obtained at various evaluation stages to reevaluate whether to take remedial action with respect to a storage device (e.g., replace the storage device). Multiple storage devices can be ranked by their respective associated confidence scores.

Growing community of inventors

Bengaluru, India

Vasanth Sathyanarayanan