Researchers at Rutgers University have built a solar-powered programming framework that would allow for datacentres to better harness solar power.
Using pieces of the software framework Hadoop, the researchers have devised a way to run solar-powered severs more effectively, predicting incoming workloads and deciding whether to use solar or traditional power input.
GreenHadoop, as the researchers call it, could offer a viable option to companies trying to get clean.
"Our experimental results demonstrate that GreenHadoop can signiﬁcantly increase green energy consumption and decrease electricity cost," said the researchers in a report of their findings [PDF].
Current datacentres are ill-equipped to harness solar power because of the large amount of power needed to run a 24-hour centre.
GreenHadoop allows servers to switch between solar and traditional energy depending on the power needs of a specific process, making solar energy more viable.
The researchers have demonstrated GreenHadoop's capabilities at a micro-datacentre facility at Rutgers known as Parasol.
Early research indicates that the new server framework would reduce the cost of traditional energy bills. The teams study shows that GreenHadoop can increase green energy consumption by up to 31 per cent, and decrease overall electricity costs by up to 39 per cent.
GreenHadoop comes as companies try to reduce the power needs of their datacentres. Facebook recently opened a new energy efficient centre in Oregon, while firms including Apple were recently criticised by Greenpeace over the use of coal power at their datacentre facilities.
As the project currently stands, GreenHadoop appears best-suited for small or medium sized datacentres. However, researchers do believe that the potential for running larger facilities may come in the future.
Could be used for everything from search-and-rescue robots to wearable tech
Don't require the rare material being mined from the mountains of South America
IBM hopes that its new tool will avoid bias in artificial intelligence
Found by calculating the strength of the material deep inside the crust of neutron stars