A study by the Massachusetts Institute of Technology (MIT), Carnegie Mellon University, and Akamai indicates an Internet-routing algorithm that tracks electricity price fluctuations could save major Internet companies millions of dollars each year. Such an algorithm could reduce energy use by as much as 40% by rerouting data to locations where electricity prices are the lowest for that particular day.
MIT Ph.D. student Asfandyar Qureshi first outlined the concept of a smart routing algorithm capable of tracking electricity prices in a paper in October 2008, and this year Qureshi and colleagues approached Akamai researchers to obtain the real-world routing data needed to test the concept.
The researchers analyzed 39 months of electricity pricing data for 29 major U.S. cities and noted a surprising amount of volatility, even among geographically close locations. The team then created a routing scheme to take advantage of daily and hourly fluctuations in electricity costs around the country, creating an algorithm that compares the physical distance needed to route information, which also increases cost, against the likely cost savings from reduced energy consumption.
The routing scheme was tested on nine Akamai servers over 24 hours, and the researchers found that in the best scenario a company could cut energy use by 40%.
From Technology Review
View Full Article
Abstracts Copyright © 2009 Information Inc., Bethesda, Maryland, USA
No entries found