 |
| Titel |
A data management system to enable urgent natural disaster computing |
| VerfasserIn |
Siew Hoon Leong, Dieter Kranzlmüller, Anton Frank |
| Konferenz |
EGU General Assembly 2014
|
| Medientyp |
Artikel
|
| Sprache |
Englisch
|
| Digitales Dokument |
PDF |
| Erschienen |
In: GRA - Volume 16 (2014) |
| Datensatznummer |
250090460
|
| Publikation (Nr.) |
 EGU/EGU2014-4699.pdf |
|
|
|
|
|
| Zusammenfassung |
| Civil protection, in particular natural disaster management, is very important to most nations
and civilians in the world. When disasters like flash floods, earthquakes and tsunamis are
expected or have taken place, it is of utmost importance to make timely decisions for
managing the affected areas and reduce casualties. Computer simulations can generate
information and provide predictions to facilitate this decision making process. Getting the
data to the required resources is a critical requirement to enable the timely computation of the
predictions.
An urgent data management system to support natural disaster computing is thus
necessary to effectively carry out data activities within a stipulated deadline. Since the trigger
of a natural disaster is usually unpredictable, it is not always possible to prepare required
resources well in advance. As such, an urgent data management system for natural disaster
computing has to be able to work with any type of resources. Additional requirements include
the need to manage deadlines and huge volume of data, fault tolerance, reliable, flexibility to
changes, ease of usage, etc.
The proposed data management platform includes a service manager to provide a uniform
and extensible interface for the supported data protocols, a configuration manager to check
and retrieve configurations of available resources, a scheduler manager to ensure that the
deadlines can be met, a fault tolerance manager to increase the reliability of the platform and
a data manager to initiate and perform the data activities. These managers will enable the
selection of the most appropriate resource, transfer protocol, etc. such that the hard deadline
of an urgent computation can be met for a particular urgent activity, e.g. data staging or
computation. We associated 2 types of deadlines [2] with an urgent computing
system.
Soft-hard deadline: Missing a soft-firm deadline will render the computation less
useful resulting in a cost that can have severe consequences
Hard deadline: Missing a hard deadline renders the computation useless and
results in full catastrophic consequences.
A prototype of this system has a REST-based service manager. The REST-based
implementation provides a uniform interface that is easy to use. New and upcoming file
transfer protocols can easily be extended and accessed via the service manager. The service
manager interacts with the other four managers to coordinate the data activities so that the
fundamental natural disaster urgent computing requirement, i.e. deadline, can be fulfilled in a
reliable manner. A data activity can include data storing, data archiving and data storing.
Reliability is ensured by the choice of a network of managers organisation model[1] the
configuration manager and the fault tolerance manager. With this proposed design, an easy to
use, resource-independent data management system that can support and fulfill the
computation of a natural disaster prediction within stipulated deadlines can thus be
realised.
References
[1] H. G. Hegering, S. Abeck, and B. Neumair, Integrated management of networked
systems - concepts, architectures, and their operational application, Morgan Kaufmann
Publishers, 340 Pine Stret, Sixth Floor, San Francisco, CA 94104-3205, USA, 1999.
[2] H. Kopetz, Real-time systems design principles for distributed embedded applications,
second edition, Springer, LLC, 233 Spring Street, New York, NY 10013, USA,
2011.
[3] S. H. Leong, A. Frank, and D. Kranzlmu¨ ller, Leveraging e-infrastructures for urgent
computing, Procedia Computer Science 18 (2013), no. 0, 2177 – 2186, 2013
International Conference on Computational Science.
[4] N. Trebon, Enabling urgent computing within the existing distributed
computing infrastructure, Ph.D. thesis, University of Chicago, August 2011,
http://people.cs.uchicago.edu/~ntrebon/docs/dissertation.pdf. |
|
|
|
|
|
|