The popularity of cloud computing is rising faster now than at any time in the past. And it’s no wonder; accessing services and applications through the Internet rather than storing the necessary data on your own computer makes sense now that links are so fast and reliable.
However, cloud computing has some significant drawbacks. Instead of localizing failures as conventional Internet computing does, the cloud makes failures system wide, say Alexandros Marinos at the University of Surrey and Gerard Briscoe at the London School of Economics, both in the U.K.. If the cloud goes down, as happened earlier this year with Gmail and last year with Amazon’s S3 service, entire companies and the industries associated with them can grind to a halt.
So Marinos and Briscoe have come up with an alternative: community clouds in which individuals offer a portion of their computing resources to a virtual cloud. That’s not unlike distributed computing ventures such as SETI@home and Folding@home that use processing cycles on idling personal computers to carry out intensive data analysis.
A virtual cloud would be more demanding but could have substantial benefits. Marinos and Briscoe say that Wikipedia might be an ideal test bed on which to try out the idea. At the moment, Wikipedia depends on substantial donations to keep its servers running and to keep the service free of advertisements. An interesting alternative might be a virtual cloud based on computing resources donated by users around the world.
Marinos and Briscoe point out that a virtual cloud should also be greener than the rapidly expanding data centers that are springing up all over the world. The combined carbon footprint of data centers is expected to exceed that of the world’s airlines by 2020. Even now, these facilities are challenging the capacity of power grids to deliver enough power to keep them going.
That alone may provide the necessary vision and momentum to get an idea like this off the ground.
Ref: arxiv.org/abs/0907.2485: Community Cloud Computing
The new version of GPT-3 is much better behaved (and should be less toxic)
OpenAI has trained its flagship language model to follow instructions, making it spit out less unwanted text—but there's still a way to go.
A horrifying new AI app swaps women into porn videos with a click
Deepfake researchers have long feared the day this would arrive.
We can’t afford to stop solar geoengineering research
It is the wrong time to take this strategy for combating climate change off the table.
Meet Altos Labs, Silicon Valley’s latest wild bet on living forever
Funders of a deep-pocketed new "rejuvenation" startup are said to include Jeff Bezos and Yuri Milner.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.