The problem is measuring the hypothetical. What is the hypothetical footprint of a startup that may have chosen to built their own data center versus using someone elses? Things like transportation, development, construction, management, etc are very difficult to measure and arguably still create vast amounts of CO2, yet are generally not taken into consideration. Also the power sources can have dramatically different CO2 footprints, say a coal source Vs wind or Nuclear.

Then there is the question of consumption, we now have the ability to run our applications on thousands of servers, but previously this wasn't even possible. To say it another way, we can potentially use several years worth of energy in literary a few hours, where previously this wasn't even an option. So in direct contrast, hypothetically we're using more resources, not less. On the flip side, if we bought those thousand servers and had them running (under utilized) the power usage would be significantly higher. But then again, buying those servers would have been out reach for most, so it's not a fair comparison. There we are -- back, at where we started. You may use 80% less energy per unit, but have 1000% more capacity which at the end of the day means you're using more, not less energy.

I'm not alone in this thinking, more broadly, the the International Organization for Standardization (ISO) considers the label "Environmentally Friendly" to be too vague to be meaningful because there is no single international standard for this concept. Although there are a few emerging Data Center Energy Efficiency Initiatives, notably by the EPA in the United States through their Energy Star program. The EPA programs are working to identify ways in which energy efficiency can be measured, documented, and implemented in data centers and the equipment they house, especially servers. This may be the foundation for potential cloud "eco-friendliness", but until cloud computing providers step up and provide the data, it does little to resolve the question.

Let me be clear, it's not that I'm saying Cloud Computing isn't green, I'm sure that if you were to compare a traditional data center deployment to a near exact replication in the cloud you'd find the cloud to be more efficent, but the problem is there currently is no way to justify this statement without some kind of data to support it.

If you know of some hard data, please free to pass it along.