Cloud Computing Is Not A New Idea!

While doing the research for a talk on cloud computing at Space Telescope next week,  my eyes were opened to the history of cloud computing. We all know, of course, of the commercial cloud offerings of the Amazon Elastic Compute cloud 2 (EC2), and of the growth of applications such as Google apps and Gmail. These types of services have taken off in the past few years because, among other reasons, the internet is able to support high bandwidth transmissions.

The ideas are, however, much older than that. Let’s rewind to the 1960′s, and look at the ideas of two visionary computer scientists, John McCarthy (September 4, 1927 – October 24, 2011) and J. C. R. Licklider (March 11, 1915 – June 26, 1990).

McCarthy coined the term “Artificial Intelligence.” He also came up with the notion of “time-sharing” of computing resources, in which computing power is made available on-demand as a utility in much the same way as is electricity and water. As far as I can tell from my reading, he saw this as a way forward because computers in those days, of course, were so big that many thought that they would only ever be installed in dedicated computing centers.

Licklider had a quite different vision. Best known as the inventor of ARPANET, the forerunner of the modern internet, his prescience extended far beyond that. He came up with the wonderfully named “intergalactic computer network.” I include here a description of it from a memo expounding this idea, written in 1963:

” … It will possibly turn out, I realize, that only on rare occasions do most or all of the computers in the overall system operate together in an integrated network. It seems to me to be interesting and important, nevertheless, to develop a capability for integrated network operation. If such a network as I envisage nebulously could be brought into operation, we would have at least four large computers, perhaps six or eight small computers, and a great assortment of disc files and magnetic tape units–not to mention the remote consoles and teletype stations–all churning away. It seems easiest to approach this matter from the individual user’s point of view–to see what he would like to have, what he might like to do, and then to try to figure out how to make a system within which his requirements can be met.”

He went to describe an example of how he could store data on the system, discover fitting and plotting functions to analyze, and what properties the network would need to make this happen. What he described, in the language of his day, was not just a system of small computers connected by the internet, but cloud storage and computing, and discovery tools such as astronomy’s Virtual Observatory. Only now, 49 years later, are we beginning to fully realize this vision.

M. Mitchell Waldrop wrote what appears to be a fascinating biography of Licklider, “The Dream Machine: J.C.R. Licklider and the Revolution That Made Computing Personal,” and I look forward to reading it.

I was inspired to delve into this subject by the article  “A History of Cloud Computing.”

Read more at astrocompute