Servers and data centers account for 23% of IT energy demand.[3] Data centers are a point source energy demand where a lot of focus has been on input control to reduce the power demand of cooling systems, and to make power inputs to servers themselves more efficient.[clarification needed]
As computing hardware becomes smaller and less expensive, energy costs constitute a larger portion of server or data center costs.[9]
Server and data center systems tend to be designed with significant computational redundancy. Typically, an individual server will only operate at around 18% of its capacity.[citation needed] The reasons for this are largely historical, and with current technology, this level of redundancy is not required.[citation needed]
This feature of data centers and servers allows major energy efficiency gains to be made through optimisation of servers. This is typically done by doing diagnostic tests on individual servers and developing a model for a data center’s energy demand using these measurements.
By analysing every server in a data centre, server power management software can identify servers that can be removed. It also enables servers to be virtualized, processes to be consolidated to a smaller number of servers, and servers with a predictable cyclical power demand to be fully powered down when not in use. Active power management features are also included which put remaining servers into their lowest power state that allows instant wake-up on demand when required.
This approach to server power management has the potential to make very large energy savings in data centers and server rooms.
Energy efficiency benchmarks, such as SPECpower, or specifications, like Average CPU power, can be used to comparing server efficiency and performance per watt.
Siting of data centers can increase or reduce their energy use. Siting in areas where climate allows air-cooling and lots of renewable electricity is available nearby can reduce the energy used and resulting environmental effects.
As computing hardware becomes smaller and less expensive, energy costs constitute a larger portion of server or data center costs.[9]
Server and data center systems tend to be designed with significant computational redundancy. Typically, an individual server will only operate at around 18% of its capacity.[citation needed] The reasons for this are largely historical, and with current technology, this level of redundancy is not required.[citation needed]
This feature of data centers and servers allows major energy efficiency gains to be made through optimisation of servers. This is typically done by doing diagnostic tests on individual servers and developing a model for a data center’s energy demand using these measurements.
By analysing every server in a data centre, server power management software can identify servers that can be removed. It also enables servers to be virtualized, processes to be consolidated to a smaller number of servers, and servers with a predictable cyclical power demand to be fully powered down when not in use. Active power management features are also included which put remaining servers into their lowest power state that allows instant wake-up on demand when required.
This approach to server power management has the potential to make very large energy savings in data centers and server rooms.
Energy efficiency benchmarks, such as SPECpower, or specifications, like Average CPU power, can be used to comparing server efficiency and performance per watt.
Siting of data centers can increase or reduce their energy use. Siting in areas where climate allows air-cooling and lots of renewable electricity is available nearby can reduce the energy used and resulting environmental effects.
Aucun commentaire:
Enregistrer un commentaire