Abstract: Systems and methods for managing airflow for cooling computing devices (e.g., in a data center) are disclosed. To prevent damage to computing devices after power outages in low temperatures, a subset of the computing devices may be preheated, started, and operated in an exhaust air recirculation mode to raise the temperatures of the other computing devices. Preheating may for example use heaters or warm air temporarily diverted from external sources such as nearby buildings. Thermal mass (e.g., phase change material) may be positioned near the computing devices to capture heat that is later released in the event of a dramatic temperature drop such a cold weather power outage.

Abstract: A facility (e.g., data center) for more efficient cooling of computing devices is disclosed. In one embodiment, the data center comprises a set of external walls, a ceiling connected to the external walls and having circular exhaust openings, and one or more pods positioned within the external walls and below the ceiling. A set of flexible tubes are used to connect the pod exhaust openings to the ceiling openings. Actuating closures may be used (e.g., at one end of each of the tubes) to control airflow, and air pressure sensors may be placed near or inside one or more of the tubes. A controller may be configured to receive air pressure data from the air pressure sensors and adjust the actuating closures to maintain a desired air pressure level. In some examples, the actuating closure may have a normally closed position when power is not applied.

Abstract: A system for operating and cooling a plurality of computing devices in a container-based data center is disclosed. Shipping containers are configured with air intake openings having triangular prism or trapezoidal prism shaped vents. The vents hold filters that can remove dust, debris, and moisture droplets from the incoming air. Fans draw fresh air into the container through the filters and direct the filtered air across the computing devices to cool them. The heated air is then expelled out of the container via exhaust openings on the opposite side of the container from the air intake openings.

Abstract: A cooling device for improving the cooling of computing devices in a data center is disclosed. The cooling device comprises an air deflector that is configured to be attached to a hot aisle air barrier at an angle to direct computing device exhaust air toward the nearest hot aisle exhaust vent. The device may comprise a mounting mechanism for fixing the air deflector in position, such as eyelets or clips that attach to the computing device's exhaust fan grille. The air deflector may be rotatable so that the angle between the hot aisle air barrier and the air deflector may be adjusted. The cooling device may further comprise a visual air flow indicator to assist in positioning of the air deflector and airflow monitoring.

Abstract: A computing device system may include a plurality of computing devices and a plurality of racks connected together to form a sled. The plurality of racks may each be connected with a respective set of computing devices of the plurality of computing devices. Each rack of the plurality of racks may include a thermal barrier configured to limit fluid and/or heat transfer. A method of operating computing devices in a facility may include connecting a respective set of computing devices to each of a plurality of racks, connecting the plurality of racks to form a sled, and/or connecting the sled to an opening of a thermal wall separating a first chamber from a second chamber.

Abstract: Systems and methods for managing airflow for cooling computing devices in a data center in normal and cold environments are disclosed. Computing devices are positioned on racks, and an air barrier may be connected to the racks and have openings configured to permit air to be drawn through the computing devices by cooling fans. In a first mode, cool air may be drawn in from a cold aisle, and heated air may be exhausted into a hot aisle. Temperature sensors may periodically measure temperatures for the cool air being drawn into the computing devices. A controller may select a subset of the computing devices for air flow reversal in response to the measured temperatures being below a predetermined threshold. Patterns that may be time-varying and temperature-varying may be used to select the computing devices for air flow reversal and to adjust the fan speed of the computing devices.

Abstract: A system and method for managing large numbers of computing devices such as cryptocurrency miners in a data center are disclosed. Status values from the computing devices are read and stored into a database, and a Gini coefficient is calculated on a subset of the stored status values. Coefficients beyond a predetermined threshold cause a support ticket to be generated if a support ticket has not already been generated and if the coefficients are not otherwise non-indicative of actual or likely computing device failures.

Abstract: Systems and methods for reporting health status for a plurality of computing devices such as within a data center are disclosed. A management device connected to the computing devices via a network executes a management application that periodically requests and receives status data from the computing devices. A pool checker may be used to track corresponding pool status data, and an environment checker may periodically request and receive environmental data from environmental sensors for temperature, humidity, and audio. A report generator creates health reports and assigns device health classifications based on the device status data, the environmental data, and the pool health data. The data may be associated with one or more locations and customers, permitting filtering of the report.

Abstract: Systems and apparatuses for provisioning computer services or resources and methods for making and using the same. In one embodiment, an exemplary method for performing an iterative search can include selecting a service from a group of available services for adjustment. An application associated with the selected service can be run, and an amount of resources consumed while the application is run can be captured. A provision level for the selected service, a provision type for the selected service or both can be adjusted based upon the captured amount of resources consumed. The method then can determine whether provision levels of the available services, provision types of the available services or both require further adjustment to be most performant. The approaches described herein advantageously can be applied, for example, to “right-size” or “scale” multiple resources.

Abstract: A system and method for efficiently creating and managing application instances in distributed computing systems is disclosed. Controls are presented for specifying an application for instantiation, a data file for use with the application, and a destination for results from the application. Application resources and topology may be recommended to the user based on prior application execution, and CPU, GPU, and interconnect parameters such as bandwidth and latency. The controls may enable to user to customize the recommendations prior to automated instantiation based on the user's needs, such as whether the application is to be run in batch mode or interactive mode.