% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@PHDTHESIS{Holl:153150,
author = {Holl, Sonja},
title = {{A}utomated {O}ptimization {M}ethods for {S}cientific
{W}orkflows in e-{S}cience {I}nfrastructures},
volume = {24},
school = {Universität Bonn},
type = {Dr.},
address = {Jülich},
publisher = {Forschungszentrum Jülich GmbH Zentralbibliothek, Verlag},
reportid = {FZJ-2014-02813},
isbn = {978-3-89336-949-2},
series = {Schriften des Forschungszentrums Jülich. IAS Series},
pages = {xvi, 182 S.},
year = {2014},
note = {Universität Bonn, Diss., 2014},
abstract = {Scientific workflows have emerged as a key technology that
assists scientists with the design, management, execution,
sharing and reuse of in silico experiments. Workflow
management systems simplify the management of scientific
workflows by providing graphical interfaces for their
development, monitoring and analysis. Nowadays, e-Science
combines such workflow management systems with large-scale
data and computing resources into complex research
infrastructures. For instance, e-Science allows the
conveyance of best practice research in collaborations by
providing workflow repositories, which facilitate the
sharing and reuse of scientific workflows. However,
scientists are still faced with different limitations while
reusing workflows. One of the most common challenges they
meet is the need to select appropriate applications and
their individual execution parameters. If scientists do not
want to rely on default or experience-based parameters, the
best-effort option is to test different workflow set-ups
using either trial and error approaches or parameter sweeps.
Both methods may be inefficient or time consuming
respectively, especially when tuning a large number of
parameters. Therefore, scientists require an effective and
efficient mechanism that automatically tests different
workflow set-ups in an intelligent way and will help them to
improve their scientific results. This thesis addresses the
limitation described above by defining and implementing an
approach for the optimization of scientific workflows. In
the course of this work, scientists’ needs are
investigated and requirements are formulated resulting in an
appropriate optimization concept. In a following step, this
concept is prototypically implemented by extending a
workflow management system with an optimization framework,
including general mechanisms required to conduct workflow
optimization. As optimization is an ongoing research topic,
different algorithms are provided by pluggable extensions
(plugins) that can be loosely coupled with the framework,
resulting in a generic and quickly extendable system. In
this thesis, an exemplary plugin is introduced which applies
a Genetic Algorithm for parameter optimization. In order to
accelerate and therefore make workflow optimization feasible
at all, e-Science infrastructures are utilized for the
parallel execution of scientific workflows. This is
empowered by additional extensions enabling the execution of
applications and workflows on distributed computing
resources. The actual implementation and therewith the
general approach of workflow optimization is experimentally
verified by four use cases in the life science domain. All
workflows were significantly improved, which demonstrates
the advantage of the proposed workflow optimization.
Finally, a new collaboration-based approach is introduced
that harnesses optimization provenance to make optimization
faster and more robust in the future.},
keywords = {Dissertation (GND)},
cin = {JSC},
cid = {I:(DE-Juel1)JSC-20090406},
pnm = {412 - Grid Technologies and Infrastructures (POF2-412)},
pid = {G:(DE-HGF)POF2-412},
typ = {PUB:(DE-HGF)11},
urn = {urn:nbn:de:0001-2014022000},
url = {https://juser.fz-juelich.de/record/153150},
}