October 11, 2010
Researchers from the University of Melbourne in Australia have come to the conclusion that cloud computing is not always the greenest option on the storage and processing as well as the software level. This research examined the issue in both the public and private cloud context in comparison to the energy consumption used for the same tasks on a local system.
The authors argued that most studies seeking an answer to a similar question about the “green” nature of the cloud have only looked at the datacenter’s energy consumption and have thus failed to include the important issue of energy use during data transfer. They suggest that the transport of data to and from datacenters, particularly since public cloud center might be a continent away, uses quite a bit more energy overall than simply storing data locally.
PhysOrg.com reported that, “for cloud processing services (in which a server such as Amazon Elastic Compute Cloud processes large computational tasks only and smaller tasks are processed on the user’s computer) the researchers again found that the cloud alternative can use lower consumption only under certain conditions.” This is because “the large number of router hops required on the public Internet greatly increases the energy consumption in transport, and private cloud processing requires significantly fewer routers.”
The leader of the research project, Rod Tucker, told PhysOrg.com that when one is using the cloud for data storage (for instance on Amazon’s Simple Storage platform) cloud uses less energy than typical computing, but only when that service is used infrequently and not in a high-performance context since data transport energy use is minimal.
While the study focused on more garden variety processors and systems common for desktop users, this research might lend some insight to larger enterprise centers that are reliant on the cloud for some or all of their business operations. While many enterprise users might look at their bottom line before analyzing their overall carbon footprint, a study on the large enterprise scale that takes data transfer into account to offer a “green” score for a company might be a good idea.
Making the process of data transport more energy efficient needs to become a priority, but luckily there are incentives to do so. While the end user might not be bearing much of the cost of inefficient data transfer consumptions, it is in the best interest of cloud providers, who must remain competitive via pricing models, to constantly improve this critical aspect of their datacenters.
The research from the University of Melbourne will be published soon from Jayant Baliga and colleagues. The paper is called “Green Cloud Computing: Balancing Energy in Processing, Storage and Transport” and will be published in the journal Proceedings of the IEEE.
Full story at PhysOrg
The ever-growing complexity of scientific and engineering problems continues to pose new computational challenges. Thus, we present a novel federation model that enables end-users with the ability to aggregate heterogeneous resource scale problems. The feasibility of this federation model has been proven, in the context of the UberCloud HPC Experiment, by gathering the most comprehensive information to date on the effects of pillars on microfluid channel flow.
Large-scale, worldwide scientific initiatives rely on some cloud-based system to both coordinate efforts and manage computational efforts at peak times that cannot be contained within the combined in-house HPC resources. Last week at Google I/O, Brookhaven National Lab’s Sergey Panitkin discussed the role of the Google Compute Engine in providing computational support to ATLAS, a detector of high-energy particles at the Large Hadron Collider (LHC).
Frank Ding, engineering analysis & technical computing manager at Simpson Strong-Tie, discussed the advantages of utilizing the cloud for occasional scientific computing, identified the obstacles to doing so, and proposed workarounds to some of those obstacles.
05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.
04/02/2012 | AMD | Developers today are just beginning to explore the potential of heterogeneous computing, but the potential for this new paradigm is huge. This brief article reviews how the technology might impact a range of application development areas, including client experiences and cloud-based data management. As platforms like OpenCL continue to evolve, the benefits of heterogeneous computing will become even more accessible. Use this quick article to jump-start your own thinking on heterogeneous computing.