Publication detail

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

JAROŠ, J. MAREK, J. MENŠÍK, P.

Original Title

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

Type

conference paper

Language

English

Original 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.

Keywords

Differential evolution, water management system, GPU-acceleration, optimisation

Authors

JAROŠ, J.; MAREK, J.; MENŠÍK, P.

RIV year

2015

Released

10. 12. 2015

Publisher

IEEE Computer Society

Location

Cape Town

ISBN

978-1-4799-7560-0

Book

Proceedings - 2015 IEEE Symposium Series on Computational Intelligence, SSCI 2015

Pages from

1727

Pages to

1734

Pages count

8

URL

BibTex

@inproceedings{BUT119882,
  author="Jiří {Jaroš} and Jan {Marek} and Pavel {Menšík}",
  title="Optimisation of Water Management Systems Using a GPU-Accelerated Differential Evolution",
  booktitle="Proceedings - 2015 IEEE Symposium Series on Computational Intelligence, SSCI 2015",
  year="2015",
  pages="1727--1734",
  publisher="IEEE Computer Society",
  address="Cape Town",
  doi="10.1109/SSCI.2015.266",
  isbn="978-1-4799-7560-0",
  url="https://www.fit.vut.cz/research/publication/10926/"
}