Publication Details

Optimisation of Water Management Systems Using a GPU-Accelerated Differential Evolution

JAROŠ Jiří, MAREK Jan and MENŠÍK Pavel. Optimisation of Water Management Systems Using a GPU-Accelerated Differential Evolution. In: Proceedings of 2015 IEEE Symposium Series on Computational Intelligence. Cape Town: IEEE Computer Society, 2015, pp. 1727-1734. ISBN 978-1-4799-7560-0.
Czech title
Optimalizace systému vodních děl pomocí diferenciální evoluce akcelerované na GPU
Type
conference paper
Language
english
Authors
Jaroš Jiří, doc. Ing., Ph.D. (DCSY FIT BUT)
Marek Jan, Ing. (FBM BUT)
Menšík Pavel, Ing., Ph.D. (FCE BUT)
Keywords
Differential evolution, water management system, GPU-acceleration, optimisation
Abstract
The aim of this paper is to present a tool that could optimise water levels in dams to provide the inhabitants and industry with enough fresh water while keeping a reasonable flood protection and river navigability. Since the water systems may be quite complicated and the outflow plans have to be precise, we developed a GPU-accelerated algorithm based on the differential evolution to solve this task. The experimental results show that a high quality annual outflow plans can be obtained within a minute, almost 18 times faster than on a hex-core CPU.
Published
2015
Pages
1727-1734
Proceedings
Proceedings of 2015 IEEE Symposium Series on Computational Intelligence
Conference
IEEE Symposium Series on Computational Intelligence 2015, Cape Town, ZA
ISBN
978-1-4799-7560-0
Publisher
IEEE Computer Society
Place
Cape Town, ZA
DOI
BibTeX
@INPROCEEDINGS{FITPUB10926,
   author = "Ji\v{r}\'{i} Jaro\v{s} and Jan Marek and Pavel Men\v{s}\'{i}k",
   title = "Optimisation of Water Management Systems Using a GPU-Accelerated Differential Evolution",
   pages = "1727--1734",
   booktitle = "Proceedings of 2015 IEEE Symposium Series on Computational Intelligence",
   year = 2015,
   location = "Cape Town, ZA",
   publisher = "IEEE Computer Society",
   ISBN = "978-1-4799-7560-0",
   doi = "10.1109/SSCI.2015.266",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/10926"
}
Files
Back to top