picture courtesy of siliconrepublic.com

With every new advancement, whether technological, medical, industrial, or other, the question of "what impact will this have on the environment?" is bound to arise. Big Data is not immune.

In James Glanz's Sept. 22 New York Times piece entitled The Cloud Factories: Power, Pollution and the Internet, he rips data centers to shreds because he deems them to be a culprit in wastefulness and environmental degradation.

He contends that, "A yearlong examination by The New York Times has revealed that this foundation of the information industry is sharply at odds with its image of sleek efficiency and environmental friendliness." He goes on to say that "Most data centers, by design, consume vast amounts of energy in an incongruously wasteful manner, interviews and documents show. Online companies typically run their facilities at maximum capacity around the clock, whatever the demand. As a result, data centers can waste 90 percent or more of the electricity they pull off the grid, The Times found."

He also cites the need for big data centers to always be running, lest there be a crash of some sort, so they also employ the use of generators that run on diesel fuel. In all, the amount of energy used world wide is roughly that of the output of 30 nuclear power plants. WHOA, that's a lot of juice. And that we, internet users assume a lot of the blame for this. If taken at face value (and maybe also in a vacuum), this sounds like trouble.

But we are not in a vacuum, and thankfully Charles Babcock of InformationWeek has our collective backs in his Sept. 25 rebuttal, N.Y. Times Data Center Indictment Misses Big Picture.

One of the first things he does to refute this accusation of wastefulness is cite an EPA report. He says, "The Environmental Protection Agency had predicted that between 2005 and 2010, the electricity consumed by data centers around the world would double, based on the rate of new construction. In 2011, the EPA had to back off that prediction because during that period, data center electricity consumption had increased by 36%, not 100%." Sounds a little like someone jumped the gun there.

The times article goes on to cite a McKinsey study that discovered the typical server uses approximately 6-12% of its available CPU cycles. Babcock observantly points out that this sounds there is one application running on each server, and that they're all running out of the fear that at any one point, one can go down.

The problem with this assertion is that it doesn't take into account the trend towards virtualization. Instead of wasting all of that energy on one app per server, each server is loaded with more than 15 times that amount. Sounds like consolidation and efficiency by cutting back on the number of servers, and increasing the amount of work each server is doing.

Babcock goes on to say that not only do the cloud centers employ virtualization, they also have less staff, and keep their machine space at around 98 degrees. Sounds a bit more efficient eh?

But of all the busted fallacies that Babcock takes care of, the one thing that the NYT article completely overlooks is that of the overall environmental situation of the current times. At no point does Glanz talk about where we are as a society that is constantly connected to the internet. Nowhere does he mention the break afforded to the trees that are no longer being chopped down to make paper. Forget about the fact that people don't have to drive anymore to places like the grocery store, the mall, the DMV, travel agencies, etc... Heck, you can even adopt pets online and not have to drive to the pound! Less paper, less air pollution, are these bad things?

As the technologies progress further, we will do more to become more efficient and thrifty, if not only because of the current economic climate. I can't think of something more eco-friendly than cutting back on making paper and moving all of your data to a cloud.

And then you have Integrate.io. We provide you with the finest Hadoop Cloud service we can. If you’re a big company, we can shoulder the load. If you’re a small company that aspires to do great things, our infrastructure is scalable and we can quickly meet your growing needs.

We’re efficient, cost-effective, AND environmentally friendly. Heck, our guys take trains, buses, and scooters to work because we care.

Learn more about what Big Data collection, processing, and analysis can do for your business.