A service-oriented framework for integration of domain-specific data models in scientific workflows

被引：9

作者：

Bender, Andreas ^{[1
]}

Poschlad, Angela ^{[1
]}

Bozic, Stefan ^{[1
]}

Kondov, Ivan ^{[1
]}

机构：

[1] KIT, Steinbuch Ctr Comp, D-76021 Karlsruhe, Germany

来源：

2013 INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE | 2013年 / 18卷

关键词：

multiscale materials modeling; simulation workflow; simulation dataflow; data model; service-oriented architecture; web services;

D O I：

10.1016/j.procs.2013.05.274

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

Managing data exchange in scientific workflow simulations is a challenge for which existing solutions have only limited success. Basing on a data-model approach we developed a service-oriented, platform-and language-independent framework which provides seamless access for heterogeneous applications to data storage resources distributed over grids and clouds. After implementing a working prototype of the framework we demonstrated its benefits for a complex workflow application from the domain of multiscale materials modeling. Because of its generic architecture and wide standards conformity the framework can be deployed as grid or cloud middleware for various other domains of computational science to enable rapid development of complex workflow applications.

引用

页码：1087 / 1096

页数：10