Scientific Clouds reveal their powers

We always talk about the advantages of cloud technology for companies and entrepreneurs, but it is amazing to see what the scientific community is doing and the way it has embraced the technology.

The number of projects that are being developed in the cloud is incredible, and every day we see new announcements, of big initiatives or small projects that rely on the cloud to develop investigation that otherwise could not be accomplished because of costs, delays in acquisition of servers and difficulties in creating support infrastructures.

Scientists have an increasing need of computational power, and sometimes the institutions don’t have the resources to provide the necessary systems and supercomputers they would need. Until recently grid computing was used to ensure the connection between different computing elements and create a virtual distributed computer center where the scientific applications could run, searching for the cure to a disease or the origins of the Universe.

But Cloud Computing is becoming a better alternative, responding to some of the problems faced by the increasing needs and lack of financial resources with the ability to provide flexible, on-demand and cost-effective computing power and storage.

However it’s necessary to consider that not all the services are appropriate for the research needs. The conclusion has already been presented in some reports, like a two-year study by the computer centers Argonne National Laboratory in Illinois and Lawrence Berkeley National Laboratory in California. Called Magellan, the project used similar IBM computing clusters at the two labs. Scientific applications were run on the systems, as well as on commercial cloud offerings for comparison.

After two years, the 169 page report explains that although commercial clouds are well-suited for enterprise applications, scientific applications are more computationally demanding, requiring more robust computing systems. And the popular “plug and play” concept of cloud computing might not carry over to scientific computing.

The solution is to create Cloud Computing platforms dedicated to scientific projects, and some initiatives are already on the way, like Helix Nebula, a consortium of 18 companies and research organizations. The cloud will become available to governmental organizations and industry after a two-year pilot phase involving three flagship projects proposed by the research facilities like CERN, the European Molecular Biology Laboratory and the European Space Agency (ESA).

Another good example is the Venus-C  (Virtual Multidisciplinary Environments Using Cloud Infrastructures), which started on 1 June 2010 linking the European Commission and Microsoft, that provided access to its cloud computing platform, Windows Azure, free of charge. The platform provides, seven applications across four thematic areas: biomedicine, civil engineering, civil protection and emergencies and data for science with a focus on marine biodiversity.

These developments can be a positive influence to the development of Cloud Computing and technology for the clouds, and I am sure there will be a lot of information to share in the near future.

Leave a Reply