Being a proponent of the G-Cloud, but also a long-time environmental activist leaves me in a quandary – how green is the ‘cloud’? A report by James Urqhart of the Wisdom of Clouds on ‘Cloud computing’s green paradox‘ was a useful guide, establishing that “the “greenness” of cloud computing is a kind of Schroedinger’s box problem today, in which we won’t know the actual savings to the environment until someone actually observes–or measures–it”. Another person pushing the need for measurement is the Greenmonk.
There is obviously a very fine balance to be drawn between having a fully resilient data centre with lots of empty rack space using electricity for air-conditioning, delivering services over a crumbling network infrastructure that is leaking power with numerous balanced data centres delivering local services over an efficient local network. How will anybody know? Will anybody check? It has to be done by measuring the Kilo Watt/Hours over an extended period for both server rooms, desktop and local area and wide area networks. Perhaps importantly, have we got our local measurement done to set a benchmark before we set out on this adventure?
Has anybody come up with a tidy model that includes end-to-end costs in relation to performance, before and after?