Researchers devise energy-aware internet routing

Researchers have come up with a new way to route internet traffic that could save big internet companies such as Google millions on their electricity bills, according to an article published by MIT's Technology Review.

Researchers from MIT, Carnegie Mellon University and the networking company Akamai recently published results from a study that suggest big internet companies could save up to 40 percent on their electricity bills by using an algorithm to send internet traffic to datacentres where electricity is less expensive.

Datacentres consume a lot of energy, which costs operators such as Google and Amazon millions of dollars to run each year. And now, as more digital information is 'virtualised' and accessed in the cloud, centralised datacentres are getting even bigger and are consuming even more energy.

In fact, datacentre energy usage is expected to quadruple during the next decade in the absence of efforts to improve efficiency, according to the article, which referenced a report from McKinsey & Company and the Uptime Institute published in July 2008. The article also estimated that today, some large internet companies spend more than $30m (£18m) a year on energy costs.

But now there could be a way for these companies to lower their energy costs. Using an algorithm developed and tested by researchers at MIT, Carnegie Mellon and Akamai, these companies can track electricity prices that fluctuate by location and time of day.

It then calculates the best option depending on the price of electricity and the distance that data must travel to get to a particular location, to provide the most cost-effective route for data based on energy costs.

There is mounting pressure for big internet companies to reduce their energy usage. Not only is it expensive, but these companies face pressure from governments and others concerned with the environment to reduce their carbon footprints.

The algorithm developed by these researchers does not necessarily cut the use of energy. It merely helps companies better manage their energy costs. But researchers argue it could also be used to direct traffic to facilities where greener forms of energy are being used.

The example used in the article is a Google datacentre in Belgium that relies on ambient cooling to keep its facilities under a certain temperature instead of firing up expensive air-conditioning systems. On days when the weather is too warm, the servers in the datacentre simply shut down.

One researcher working on the project said the energy-routing algorithm is an extension of this idea.

Managing energy and its costs is likely to be big business in the coming years for technology companies. Cisco, the largest networking company in the world, recently said it sees a $100bn market in helping power utilities better manage their electrical grids using communication technology.

Other high-tech companies, including IBM, Intel and several start-ups, are also ramping up to develop sensors and other technology that alert power companies and their customers about energy usage in an effort to balance usage and reduce costs.

The idea of the 'smart grid' is to modernise the electricity industry by overlaying digital communications onto the grid. For example, smart meters in a person's home can communicate energy usage to utilities, allowing these companies to more efficiently manage the electricity supply and potentially allow a consumer to take advantage of cheaper rates.

Some utilities are already testing technology from Cisco that will help its routers and switches more efficiently manage the flow of electricity and prevent outages in grid distribution equipment.

Cisco also released new software earlier this year called EnergyWise, which allows more efficient use of energy in office buildings. The software is a free upgrade to Cisco Catalyst switches that can monitor and manage how energy is used on IP-connected devices, including phones and wireless routers.

Using the software, companies can set policies on energy use, allowing PCs or networking equipment to go into sleep mode after work hours, for example.