More and more services require high real-time per-formance, and to achieve high real-time
performance, a server's power-saving features tend to be disabled to achieve strict latency …

User-facing applications running in modern datacenters exhibit irregular request patterns
and are implemented using a multitude of services with tight latency requirements (30–250 μ …

User-facing applications running in modern datacenters exhibit irregular request patterns
and are implemented using a multitude of services with tight latency requirements (30 …

User-facing applications running in modern datacenters exhibit irregular request patterns
and are implemented using a multitude of services with tight latency requirements. These …

Lack of energy proportionality in server systems results in significant waste of energy when
operating at low utilization, a common scenario in today's data centers. We propose DIMMer …

We introduce a novel power capping technique, IdleCap, that achieves higher effective
server frequency for a given power constraint than existing techniques. IdleCap works by …

Data center power consumption is growing to unprecedented levels: the EPA estimates US
data centers will consume 100 billion kilowatt hours annually by 2011. Much of this energy is …

Since idle-state is the dominant state for embedded systems, disabling unused devices in
idle-states can lead to significant power reduction. Among the various sleep modes provided …

Power capping in computer clusters enables energy budgeting, efficient power delivery, and
management of operational and cooling costs. Pack and Cap is a novel, practical …

During the last decades various low-power states have been implemented in processors.
They can be used by the operating system to reduce the power consumption. The applied …