摘要:
Disclosed techniques include power manipulation using power caches within a datacenter. The power caches store power for later use when power demand exceeds the power available. A power source is coupled across a plurality of data racks to a power load within a datacenter. A power cache is coupled to the power load. Power for the power load is provided from the power source. The power cache is enabled to provide power to the power load when power requirements of the power load exceed a power threshold. The power threshold is determined by a set of power policies for the datacenter. The enabling the power cache to provide power to the power load provides power bursting capability.
摘要:
Embodiments provide techniques for datacenter power management using variable power sources. Power from the variable power sources is stored in a power cache. An optimization engine receives input criteria such as power availability from non-variable and variable power sources, as well as one or more power management goals. The optimization engine implements a dispatch strategy that dispatches stored energy from the power cache and feeds it to the datacenter, resulting in a mixture of non-variable and variable power sources used to achieve the power management goals, such as reduced power cost, increased power availability, and lowered carbon footprint for the datacenter.
摘要:
In disclosed techniques, simulations are performed to determine data center performance under certain conditions. The simulations are dynamic and allow for changes in power demand due to temporal data center activities. In order to accommodate predicted and unpredicted fluctuations in power demand of a data center, one or more power caches are configured to supply additional power during periods of peak demand. Power caches provide supplemental power during periods of peak demand. The simulations are used for a variety of purposes, including determining the effects of power caches going offline under various conditions. Disclosed techniques can simulate the cycling of a power cache and can determine if additional configuration changes to the data center are warranted to maintain optimal health of the power caches. Thus, power scenario simulation of a data center can provide information vital to efficient operation of the data center.
摘要:
Multi-level data center consolidated power is disclosed. One or more controllers communicate with one or more power supplies and sensors to adapt to dynamic load requirements and to distribute DC-power efficiently across multiple IT racks. The distributed DC-power includes one or more DC-voltages. Batteries can be temporarily switched into a power supply circuit to supplement the power supply during spikes in power load demand while a controller reconfigures power supplies to meet the new demand. In embodiments, one or more DC-to-AC converters handle legacy power loads. The DC-to-AC converters are modular and are paralleled for redundancy. The AC-power is synchronized for correct power flow control. The one or more controllers communicate with the one or more AC-power supplies to dynamically allocate AC-power from the DC-to-AC converters to the multiple IT racks.
摘要:
Embodiments provide techniques for datacenter power management using variable power sources. Power from the variable power sources is stored in a power cache. An optimization engine receives input criteria such as power availability from non-variable and variable power sources, as well as one or more power management goals. The optimization engine implements a dispatch strategy that dispatches stored energy from the power cache and feeds it to the datacenter, resulting in a mixture of non-variable and variable power sources used to achieve the power management goals, such as reduced power cost, increased power availability, and lowered carbon footprint for the datacenter.
摘要:
Techniques for datacenter power management using dynamic redundancy are disclosed. A power control switch is configured to selectively apply power to one or two power cords of a dual-corded electronic apparatus. When the power control switch energizes both power cords, the electronic apparatus operates in 2N redundancy. When the power control switch energizes only one of the power cords, the electronic apparatus operates in 1N redundancy. The power control switch is configured to dynamically change the redundancy mode based on service level agreement (SLA) criteria, power policies, power supply and demand, and environmental factors.
摘要:
Dynamic tiering of datacenter power for workloads is disclosed. A power capacity, including redundant power capacity and granular power capacity values within a datacenter, is determined. An outage time duration requirement for the power capacity that was determined is evaluated, where the outage time duration requirement is a number of minutes. A hold time duration requirement for the power capacity is evaluated, where the hold time duration is a number of minutes. A number of allowable occurrences of power outage for the power capacity is evaluated. A power requirement metric, based on the outage time duration requirement, the hold time duration requirement, and the number of occurrences, is calculated. A power topology within the datacenter is modified based on the power requirement metric. The modifying provides dynamic power tiering within the datacenter. The dynamic tiering includes a variable service level agreement for power within the datacenter.
摘要:
Techniques for datacenter power management using dynamic redundancy are disclosed. A power control switch is configured to selectively apply power to one or two power cords of a dual-corded electronic apparatus. When the power control switch energizes both power cords, the electronic apparatus operates in 2N redundancy. When the power control switch energizes only one of the power cords, the electronic apparatus operates in 1N redundancy. The power control switch is configured to dynamically change the redundancy mode based on service level agreement (SLA) criteria, power policies, power supply and demand, and environmental factors.
摘要:
Disclosed are systems and methods to provide energy control via power-requirement analysis and power-source enablement. Both demand-side and supply-side techniques are used alone or in conjunction to determine an optimal number of power sources to supply power to one or more loads. When fluctuations in power requirements are present, measures such as decoupling less-critical loads in order to continue delivering power to critical systems and turning on and off power sources as needed to meet the current power demands of a system are implemented. Power sources are periodically deactivated by the system on a rotational basis such that all power sources wear evenly, prolonging the life of the equipment. A scalable architecture that allows the virtualization of power from the underlying hardware form factor is also provided.
摘要:
In disclosed techniques, datacenter power management uses AC and DC power sources. An AC power distribution topology within a datacenter provides one or more AC power sources to computing devices. A DC power distribution topology within the datacenter provides one or more DC power sources to computing devices. An uninterruptible power supply (UPS) is provisioned to a rack of computing devices, wherein the UPS is capable of receiving the one or more AC power sources using the AC power distribution topology and the one or more DC power sources using the DC power distribution topology. The one or more DC power sources are evaluated for energizing the DC power distribution topology. The one or more DC power sources are connected to the UPS which is provisioned to the rack of computing devices, based on the evaluating and a datacenter power requirement.