Information Technology Reference
In-Depth Information
allocated to their computing needs and processes. At the core of Grid Computing
therefore are virtualization and virtual centralization as well as availability of
heterogeneous and distributed resources based on collaboration among and sharing
of existing infrastructures from different organizational domains which together
build the computing Grid.
Since the mid 1990s the concept of Grid has evolved. Similar to other infra-
structure innovations - for example the Internet - the Grid was first introduced
and adopted in science for the support of research in various scientific disciplines
that require high performance computing (HPC) together with huge amounts of
data stored in dedicated databases. Examples of such sciences are Earth Science,
Astroparticle Physics and Computational Chemistry. They are summarized under
the term eScience. To support eScience many national and international initiatives
have been started by governments in many countries in order to leverage existing
investments in research infrastructure and to enable sharing and efficient use of
available computational resources, data and specialized equipment. Examples of
national initiatives are: Austrian Grid (http://www.austriangrid.at), D-Grid - the
German Grid initiative, DutchGrid (http://www.dutchgrid.nl) and others.
One example of an international initiative is the Enabling Grid for E-SciencE
(EGEE) project supported by the European Commission (http://www.eu-egee.org).
The EGEE involves over 50 countries with the common aim of building on recent
advances in Grid technology and developing a service Grid infrastructure which
is available to scientists 24 hours-a-day (EGEE 2009). Another international
initiative has been initiated by CERN. CERN is building a Large Hadron Collider
(LHC) Computing Grid to manage and support the analysis of data generated
by LHC experiments. The largest experiment is generating over one petabyte of
data per year and around 2000 users and 150 institutions are involved in the
analysis of the experiments' data. The analysis of such large quantities of data
exceeds by far the available computing capacities of one single organization. All
involved research institutions are joining their resources in the LHC Computing
Grid.
The Grid Computing paradigm based on resource sharing was brought to broader
public by the popular project (http://setiathome.berkeley.edu) SETI@HOME. The
goal of the Search for Extraterrestrial Intelligence (SETI) project is the detection of
intelligent life outside earth. The project uses radio telescopes to listen for narrow-
bandwidth radio signals from space. As such signals are not known to occur natu-
rally, it is expected that a detection of them would provide evidence of extrater-
restrial technology. The analysis of radio telescope signals involves huge amounts
of data and is very computing-intensive. No single research lab could provide the
computing power needed for it. Given the tremendous number of household PCs,
the involved scientists came up with the idea to invite owners of PCs to participate
in the research by providing the computing power of their computers when they are
idle. Users download a small program on their desktop. When the desktop is idle,
the downloaded program would detect it and use the idle machine cycles. When the
PC is connected back to the Internet, it would send the results back to the central
site. The SETI initiative recently celebrated the 10
th
anniversary (it was launched
