My notes on Delic, K. A., & Walker, M. A. (2008). Emergence of the academic computing clouds. Ubiquity, 2008(August), 1.
I was intrigued by this short paper from 2008, prefiguring a number of themes which are central to contemporary debates about digital infrastructure. It reflected on the “emergence of the cloud as the generic infrastructural fabric enabling a huge number of services”, as well as what this might mean for research practice. They talk about the emergence of cloud computing in terms of the transition from data centres to grids:
Grids are very large-scale virtualized, distributed computing systems. They cover multiple administrative domains and enable virtual organizations. The key characteristic of grids is their ability to upscale and downscale rapidly and gracefully. So, they provide utility type of computing which enables another type of business model and spawns start-up businesses.
Grids are collections of data centres, operating through “aggregation, virtualization and scheduling” to provide a platform for executing immensely computationally intense applications. They draw an analogy between computing grids in this sense and energy, communication and transportation grids. Grids transform large swathes of hardware and software assets into computational services which can be drawn upon by many users. The cloud is what we get from the assembly of distinct grids, though I was slightly confused by this definition as it seems to reproduce their distinction between grids and data centres.
They make the important observation that “the typical workloads for academic/scientific applications are very different from commercial workloads”, with the former revolving around the ‘mega-scale simulations’ which are becoming possible due to the affordances of the cloud. They correctly predict this will lead to new forms of scientific inquiry, driven by the “vast amounts of data coming not only from the web but also from a rising number of instruments and sensors”.