Dell Products Inc.

Sandeep Venkatesh Pai

Shivendra Katiyar

Nikhil S

Harshendra Shetty

Vaideeswaran Ganesan

Rishi Mukherjee

Praveen S Lalgoudar

Rushyendra Velamuri

Pandiyan Varadharajan

Sivakumar Swamy

Harish Babu

Chandrasekhar R

Rekha Ms

Rekha M S

Nidhi Kant Arora

According to one embodiment, an Information Handling System (IHS) includes a host that is executed to manage deployment of a plurality of workspaces, and executable instructions to obtain an amount of energy consumed by one or more resources of the host, obtain workspace usage metrics of each of the workspaces, and determine, using the workspace usage metrics, a proportionate amount of energy used by each of the workspaces. The instructions can, using the determined proportionate amount of energy, determine an overall amount of energy used by each workspace by distributing the amount of energy used by each of the resources across each of the workspaces according to the proportionate amount of energy used by each of the workspaces.

Systems and methods for estimating energy usage of workspaces used in virtualized environments

The described technology is generally directed towards reallocating power to devices in a group, such as a rack of servers in a datacenter, when no power headroom remains available. Respective devices, which are classified into respective classes corresponding to respective priority device class levels, have power distributed thereto. Upon determining that available power headroom for power capacity distribution among the group of devices has reached an available power capacity distribution lower limit (e.g., zero), reallocation is performed by increasing power capacity allocated to a first device of a higher priority level class, and decreasing power capacity allocated to a second device of a lower priority level class. For more classes, such as high, medium and low, the power can be decreased among the lower priority level classes by a defined ratio, e.g., two-to-one between the medium and low priority classes.

Reallocation of available power among devices in a group

Systems and methods provide customers with a need-based warranty using a deep learning neural network. After categorizing, a customer need is mapped to a warranty type based on the SLA needs. Warranties may then be suggested based on customer need. In another embodiment, systems and methods detect an optimal warranty based on part failure and performance of a server. A mean time to resolve or replace can be minimized in future failure instances by comparing the derived replacement time with available warranty offerings to identify potential deviations and thereby recommend an optimal warranty from the available offerings. In a further embodiment, systems and methods identify and offer additional service contracts for vender services. A warranty proposer looks for warranty types that are emitted by a warranty-types analyzer and by a technical-support analyzer. The overlapping warranty offers are provided to customers.

System and method for warranty customization based on customer need and part failure rate

The described technology is generally directed towards a system and method to distribute available power to devices in a group. A group of devices, such as a rack of servers in a data center, can have a group power consumption limit, such as the limit of a power distribution unit that supplies power to the group. The group of devices can each report their individual power consumption to a manager, and the manager can combine the individual power consumptions. The manager can compare the combined power consumption of the group to the group power consumption limit to determine a power headroom. The manager can determine power consumption limits for the devices of the group based on the power headroom, the individual power consumptions, and device priority information.

Distribution of available power to devices in a group

A software-defined infrastructure can identify and remediate an airflow deficiency scenario on a rack device. A rack device manager can be configured to discover rack devices and create a representation of their physical locations. The rack device manager can also be configured to periodically retrieve airflow metrics of the rack devices to calculate an estimated airflow for each rack device. The rack device manager can use the estimated airflows and the airflow metrics to generate a rack device classifier for each rack device. Using these rack device classifiers, the rack device manager can detect when rack devices are experiencing airflow deficiencies and attempt to automatically remediate such deficiencies.

Software-defined infrastructure for identifying and remediating an airflow deficiency scenario on a rack device

Custom-tailored warranties are provided with improved service level agreements (SLA) based upon an estimated turnaround time for service and/or parts. The turnaround time is calculated using an artificial intelligence or machine learning engine considering parameters such as the transit time from the nearest service centers and warehouses, the availability of service engineers at the service centers, and the availability of replacement parts in the warehouse. A custom-tailored warranty also may be offered for a specific customer-selected SLA if supported by the estimated turnaround time for the location. A warranty recommendation may be based on device location for data centers in multiple locations. A Location-Based Warranty Monitor (LBWM) provides fine-grained warranty suggestions and Un-bound Warranty Tokens (UWTs) can be bound to a system to assign a warranty with a desired. SLA.

Growing community of inventors

Bengaluru, India

Sandeep Venkatesh Pai