Premium
Decomposition and parallelization strategies for solving large‐scale MDO problems
Author(s) -
Grauer M.,
Eschenauer Hans A.
Publication year - 2007
Publication title -
gamm‐mitteilungen
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.239
H-Index - 18
eISSN - 1522-2608
pISSN - 0936-7195
DOI - 10.1002/gamm.200790018
Subject(s) - multidisciplinary design optimization , workbench , decomposition , computer science , multidisciplinary approach , workstation , scale (ratio) , engineering optimization , optimization problem , focus (optics) , operations research , industrial engineering , engineering , artificial intelligence , algorithm , ecology , social science , physics , quantum mechanics , sociology , visualization , biology , operating system , optics
During previous years, structural optimization has been recognized as a useful tool within the discriptines of engineering and economics. However, the optimization of large‐scale systems or structures is impeded by an immense solution effort. This was the reason to start a joint research and development (R& D) project between the Institute ofMechanics and Control Engineering and the Information and Decision Sciences Institute within the Research Center for Multidisciplinary Analyses and Applied Structural Optimization (FOMAAS) on cluster computing for parallel and distributed solution of multidisciplinary optimization (MDO) problems based on the OpTiX‐Workbench. Here the focus of attention will be put on coarsegrained parallelization and its implementation on clusters of workstations. A further point of emphasis was laid on the development of a parallel decomposition strategy calles PARDEC, for the solution of very complex optimization problems which cannot be solved efficiently by sequential integrated optimization. The use of the OptiX‐Workbench together with the FEM ground water simulation system FEFLOWis shown for a special water management problem. (© 2007 WILEY‐VCH Verlag GmbH & Co. KGaA, Weinheim)