Data deluge, research reproducibility and cloud computing: towards a collaborative and secure distributed infrastructure software for science and education

pullfarmInternet και Εφαρμογές Web

3 Νοε 2013 (πριν από 3 χρόνια και 7 μήνες)

64 εμφανίσεις

Data deluge, research repr
oducibility and cloud computing
: towards a collaborative and
secure

distributed infrastructure software for science and education

The scientific discovery process is becoming more and more a data
-
intensive and a compute
-
intensive

activity. While the Grid

-
foreseen as a major accelerator of discovery
-

didn't meet the
expectations and has excited at its beginnings


and was not adopted by the broad population of
research professionals,
Infrastructure
-
as
-
a
-
service style clouds hold
a

new promise

of revolutionising
research and education

and impacting radically on computational sciences and engineering
.

Bringing new era for scientific and statistical computing and for e
-
Learning still requires the software
that would bridge the gap be
tween the cloud and the scientists and educators' everyday tools,
making the cloud become a trivial commodity in academia and beyond.

Elastic
-
R is a new
cloud
-
based

e
-
research

and

e
-
learning
platform

and portal
currently operational on Amazon Cloud (EC2).
It

makes mainstream scientific computing environments such as R, scilab and SciPy accessible as a
service from a standard web browser
and enables
the scientist

to use them without any memory or
compute constraints.

The design of Elastic
-
R tackles numerous architectural and HCI challenges
inherent to the key use cases in e
-
science:

user
-
friendly access to federated computational
resources,

secure access to large scale data, multi
-
user environments for data analysis wi
th real
-
time
collaboration capabilities, accessibility of high performance
and
High throughput

computing,
research traceability and reproducibility,

seamless creation and publishing of scientific services,
etc.

The talk will overview
and demonstrate
the ma
in architectural principles of system design, key
capabilities and use cases

in the contexts of e
-
science, e
-
learning and ubiquitous computing
.

Published material:

•Chine K (2010) Open science in the cloud: towards a universal platform for scientific and
statistical
computing. In: Furht B, Escalante A (eds) Handbook of cloud computing, Springer, USA, pp 453

474.
ISBN 978
-
1
-
4419
-
6524
-
0.

•Karim Chine, "Learning math and statistics on the cloud, towards an EC2
-
based Google Docs
-
like
portal for teaching / lear
ning collaboratively with R and Scilab," icalt, pp.752
-
753, 2010 10th IEEE
International Conference on Advanced Learning Technologies, 2010.

•Karim Chine, "Scientific computing environments in the age of virtualization, toward a universal
platform for the
cloud" pp. 44
-
48, 2009 IEEE International Workshop on Open Source Software for
Scientific Computation (OSSC), 2009.

•Karim Chine, "Biocep, towards a federative, collaborative, user
-
centric, grid
-
enabled and cloud
-
ready computational open platform" escience
,pp.321
-
322, 2008 Fourth IEEE International
Conference on eScience, 2008.


Articles from the web:

http://www.readwriteweb.com/cloud/2010/07/the
-
biocep
-
r
-
project
-
brings
-
op.php

http://www.hpcinthecloud.com/features/SC10
-
Disruptive
-
Technology
-
Preview
--
The
-
First
-
Cloud
-
Portal
-
to
-
R
-
and
-
Beyond
-
105776458.html