L. Pearlman, C. Kesselman, S. Gullapalli, B. Spencer, J. Futrelle, K. Ricker, Ian T Foster, P. Hubbard, C. Severance
{"title":"Distributed hybrid earthquake engineering experiments: experiences with a ground-shaking grid application","authors":"L. Pearlman, C. Kesselman, S. Gullapalli, B. Spencer, J. Futrelle, K. Ricker, Ian T Foster, P. Hubbard, C. Severance","doi":"10.1109/HPDC.2004.11","DOIUrl":null,"url":null,"abstract":"Earthquake engineers have traditionally investigated the behavior of structures with either computational simulations or physical experiments. Recently, a new hybrid approach has been proposed that allows tests to be decomposed into independent substructures that can be located at different test facilities, tested separately, and integrated via a computational simulation. We describe a grid-based architecture for performing such novel distributed hybrid computational/physical experiments. We discuss the requirements that underlie this extremely challenging application of grid technologies, describe our architecture and implementation, and discuss our experiences with the application of this architecture within an unprecedented earthquake engineering test that coupled large-scale physical experiments in Illinois and Colorado with a computational simulation. Our results point to the remarkable impacts that grid technologies can have on the practice of engineering, and also contribute to our understanding of how to build and deploy effective grid applications.","PeriodicalId":446429,"journal":{"name":"Proceedings. 13th IEEE International Symposium on High performance Distributed Computing, 2004.","volume":"112 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2004-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"60","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings. 13th IEEE International Symposium on High performance Distributed Computing, 2004.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/HPDC.2004.11","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 60
Abstract
Earthquake engineers have traditionally investigated the behavior of structures with either computational simulations or physical experiments. Recently, a new hybrid approach has been proposed that allows tests to be decomposed into independent substructures that can be located at different test facilities, tested separately, and integrated via a computational simulation. We describe a grid-based architecture for performing such novel distributed hybrid computational/physical experiments. We discuss the requirements that underlie this extremely challenging application of grid technologies, describe our architecture and implementation, and discuss our experiences with the application of this architecture within an unprecedented earthquake engineering test that coupled large-scale physical experiments in Illinois and Colorado with a computational simulation. Our results point to the remarkable impacts that grid technologies can have on the practice of engineering, and also contribute to our understanding of how to build and deploy effective grid applications.