Grid Computing - Guide to Cloud Computing for Business and Technology Managers - page 244

differences between a grid computing infrastructure and the features
one should expect from a cloud computing infrastructure. All re-
sources constituting a grid computing infrastructure are predefined
and predetermined corresponding to the spare capacity that is avail-
able to promise with the constituents for participating in the grid. In
contrast, cloud computing releases or augments pre-identified and
dedicated resources dynamically, depending on the demand. Grid
computing is somewhat akin to an application service provider (ASP)
environment, but with a much higher level of performance and
assurance.
12.2 Introduction to Grid Computing
The vision of grid computing is to enable computing to be delivered as
a utility. This vision is most often presented with an analogy to electri-
cal power grids, from which it derives the name grid . So grid computing
was meant to be used by individual users who gain access to computing
devices without knowing where the resource is located or what hardware
it is running and so on. In this sense, it is pretty similar to cloud comput-
ing. However, just as electrical power grids can derive power from multiple
power generators and deliver the power as needed by the consumer, the key
emphasis of grid computing was to enable sharing of computing resources
or forming a pool of shared resources that can then be delivered to users.
So most of the initial technological focus of grid computing was limited to
enabling shared use of resources with common protocols for access. Also,
since the key takers of this fascinating vision were educational institutions,
a particular emphasis was given to handle heterogeneous infrastructure,
which was typical of a university data center. From a technical perspective,
a software-only solution was proposed (Globus) and implemented on this
heterogeneous infrastructure to enable use of these resources for higher
computing needs. Once reasonably successful within universities, grid
computing faced a serious issue when it came to sharing resources across
commercial institutions. Establishing trust and security models between
infrastructure resources pooled from two different administrative domains
became even more important.
The first most cited definition of grid computing reflected these origins
and was suggested by Foster and Kesselman (1998): “A computational
grid is a hardware and software infrastructure that provides dependable,
consistent, pervasive, and inexpensive access to high-end computational
capabilities.”