Information Technology Reference
In-Depth Information
Computational.
Numerical simulations of earthquake, tsunami,
and other natural disasters (1900s).
Data-Intensive (e-Science).
The cyber-infrastructure and LHC
Computing Grid to support the CERN Large Hadron Collider
[156] where LHC stands for Large Hadron Collider and CERN
stands for European Organization for Nuclear Research.
In the data-intensive paradigm, scientists are facing an enormous
increase in raw data from various resources such as telescopes, instru-
ments, sensor networks, accelerators, and supercomputers. Here, we
give a few examples only. In 2010, ATLAS and the three other main
detectors at the LHC produced 13 petabytes of data [75].
PubMed
,a
database of references and abstracts on life sciences and biomedical
topics, contained 21 million entries as of July 2011 [157]. The
2011
Nucleic Acids Research Database Issue and the online Molecular
Biology Database Collection
[76] lists 1330 carefully selected molec-
ular biology databases among which,
GenBank
, the US NIH DNA
sequence database, contained more than 286 billions of entries for more
than 380,000 organisms as of August 2010 [77]. This
data deluge
[158]
calls for a uniformed and virtualized access method for all these data
and the computational resources to analyze them.
Service-Oriented Science
Compared to e-Science, or data-driven science, the concept of service-
oriented science (SOS) proposed by Professor Ian Foster in 2005 has a
similar connotation but more specifically focuses on using SOA as the
underlying infrastructure integrating data and computation capabilities.
Figure 7.1 illustrates the infrastructure and application scenarios of SOS.
SOS infrastructure provides the common facilities to integrate data
(such as DNA sequences, astronomical images, and particle physics
data), instruments (such as electron microscopes, accelerators, and
space telescopes), and computational resources (such as computer
clusters and cloud computing platforms). These common facilities
are shared by all the services just like the power grid is shared by
all power generators. The key facilities include the following:
Virtualization
. It uses standard protocols, such as HTTP, SOAP,
and REST,
to wrap heterogeneous data,
instruments, and
