Conference article

Data centers have become an essential operational component of nearly every sector of the economy; and as a result growing consumers of energy and emitters of greenhouse gases (GHGs). Developing strategies for optimizing power usage and reducing the associated life cycle GHG emissions are critical priorities for meeting climate policy objectives. We investigate data center power management through virtualization; a technique that consolidates data center workloads onto fewer computing resources within a data center and deploys computing resources only as needed. Based on an experimentally validated dynamic resource provisioning framework applied to a small scale computing cluster at Drexel University that employed lookahead control; a control scheme using virtualization demonstrated a 25% reduction in power consumption over a 24-hour period. Using the power savings results from the virtualization experiments; and extrapolating those savings to a medium-sized data center that hosts 500 servers; we estimate the avoided life cycle GHG emissions for implementing a virtualization strategy in hourly time-steps for marginal and average electricity units over a 24-hour day during the month of August; when electricity loads are typically highest for the year. Results from this work show virtualization could avoid the emission of approximately 0.8 to 1.2 metric tons CO₂e/day.

Energy; Power management; Buildings; Information technology; Life cycle assessment