Using the new algorithms, collectively called Stratus, the scientists were able to model a worldwide network of connected data centers and predict how to keep carbon emissions from cloud computing low while still performing the needed computing and data transfer.
The research team was inspired by Amazon’s Elastic Compute Cloud (EC2) data center setup, IEEE says. EC2 considers three variables: carbon emissions, electricity cost, and time needed for computation and data transfer. By using Stratus, the scientists reduced the EC2 cloud’s emissions by 21 percent over a common commercial scheme for balancing computing loads.
An Open Data Center Alliance whitepaper published in November outlines how ODCA members BMW, Datapipe and Verne Global used the ODCA Carbon Footprint and Energy Efficiency Usage Model to track, evaluate and manage enterprise cloud CO2 emissions across the entire cloud ecosystem.
The cloud generally beats on-premise computing for energy efficiency, according to a study of IT products and services for small- and medium-sized businesses published in October.
Image Credit: cloud computing via Shutterstock