Application of multi-objective evolutionary algorithms for the rehabilitation of storm sewer pipe networks

J. Yazdi, A. Sadollah, E. H. Lee, D. Yoo, Joong Hoon Kim

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

In recent decades, evolutionary optimisation algorithms have been used successfully for a wide variety of water resources engineering problems and their applications are still increasing. In this research work, a hybrid harmony search algorithm, 'Non-dominated Sorting Harmony Search' algorithm is developed and compared with two state-of-the-art multi-objective evolutionary algorithms - the non-dominated sorting genetic algorithm (NSGA)-II and multi-objective particle swarm optimisation (MOPSO) algorithms - for assigning optimal rehabilitation plans for sewer pipe networks. The algorithms considered were validated using some standard test functions reported in the literature and compared with each other in terms of several metrics. These algorithms were then linked to the SWMM-EPA hydraulic model and applied to a storm sewer pipe network case study in Seoul, South Korea, to obtain the best rehabilitation plans for pipe replacements. The results showed that the algorithms considered have different behaviours in solving the benchmark tests and rehabilitation problem. The proposed hybrid multi-objective harmony search algorithm provides better optimal solutions in terms of different metrics and clearly outperforms the other two algorithms for the rehabilitation of the storm sewer pipe networks.

Original languageEnglish
JournalJournal of Flood Risk Management
DOIs
Publication statusAccepted/In press - 2015

Fingerprint

Storm sewers
Evolutionary algorithms
Patient rehabilitation
rehabilitation
pipe
Pipe
Sorting
sorting
Hydraulic models
Sewers
Water resources
research work
Particle swarm optimization (PSO)
genetic algorithm
South Korea
Genetic algorithms
replacement
water resource

Keywords

  • MOPSO
  • Multi-objective optimisation
  • NSGA-II
  • NSHS
  • Sewer pipe network
  • Urban drainage system

ASJC Scopus subject areas

  • Safety, Risk, Reliability and Quality
  • Environmental Engineering
  • Water Science and Technology
  • Geography, Planning and Development

Cite this

Application of multi-objective evolutionary algorithms for the rehabilitation of storm sewer pipe networks. / Yazdi, J.; Sadollah, A.; Lee, E. H.; Yoo, D.; Kim, Joong Hoon.

In: Journal of Flood Risk Management, 2015.

Research output: Contribution to journalArticle

@article{b1b0bb3d7ad2452dabb6b94a9581966c,
title = "Application of multi-objective evolutionary algorithms for the rehabilitation of storm sewer pipe networks",
abstract = "In recent decades, evolutionary optimisation algorithms have been used successfully for a wide variety of water resources engineering problems and their applications are still increasing. In this research work, a hybrid harmony search algorithm, 'Non-dominated Sorting Harmony Search' algorithm is developed and compared with two state-of-the-art multi-objective evolutionary algorithms - the non-dominated sorting genetic algorithm (NSGA)-II and multi-objective particle swarm optimisation (MOPSO) algorithms - for assigning optimal rehabilitation plans for sewer pipe networks. The algorithms considered were validated using some standard test functions reported in the literature and compared with each other in terms of several metrics. These algorithms were then linked to the SWMM-EPA hydraulic model and applied to a storm sewer pipe network case study in Seoul, South Korea, to obtain the best rehabilitation plans for pipe replacements. The results showed that the algorithms considered have different behaviours in solving the benchmark tests and rehabilitation problem. The proposed hybrid multi-objective harmony search algorithm provides better optimal solutions in terms of different metrics and clearly outperforms the other two algorithms for the rehabilitation of the storm sewer pipe networks.",
keywords = "MOPSO, Multi-objective optimisation, NSGA-II, NSHS, Sewer pipe network, Urban drainage system",
author = "J. Yazdi and A. Sadollah and Lee, {E. H.} and D. Yoo and Kim, {Joong Hoon}",
year = "2015",
doi = "10.1111/jfr3.12143",
language = "English",
journal = "Journal of Flood Risk Management",
issn = "1753-318X",
publisher = "Blackwell Publishing",

}

TY - JOUR

T1 - Application of multi-objective evolutionary algorithms for the rehabilitation of storm sewer pipe networks

AU - Yazdi, J.

AU - Sadollah, A.

AU - Lee, E. H.

AU - Yoo, D.

AU - Kim, Joong Hoon

PY - 2015

Y1 - 2015

N2 - In recent decades, evolutionary optimisation algorithms have been used successfully for a wide variety of water resources engineering problems and their applications are still increasing. In this research work, a hybrid harmony search algorithm, 'Non-dominated Sorting Harmony Search' algorithm is developed and compared with two state-of-the-art multi-objective evolutionary algorithms - the non-dominated sorting genetic algorithm (NSGA)-II and multi-objective particle swarm optimisation (MOPSO) algorithms - for assigning optimal rehabilitation plans for sewer pipe networks. The algorithms considered were validated using some standard test functions reported in the literature and compared with each other in terms of several metrics. These algorithms were then linked to the SWMM-EPA hydraulic model and applied to a storm sewer pipe network case study in Seoul, South Korea, to obtain the best rehabilitation plans for pipe replacements. The results showed that the algorithms considered have different behaviours in solving the benchmark tests and rehabilitation problem. The proposed hybrid multi-objective harmony search algorithm provides better optimal solutions in terms of different metrics and clearly outperforms the other two algorithms for the rehabilitation of the storm sewer pipe networks.

AB - In recent decades, evolutionary optimisation algorithms have been used successfully for a wide variety of water resources engineering problems and their applications are still increasing. In this research work, a hybrid harmony search algorithm, 'Non-dominated Sorting Harmony Search' algorithm is developed and compared with two state-of-the-art multi-objective evolutionary algorithms - the non-dominated sorting genetic algorithm (NSGA)-II and multi-objective particle swarm optimisation (MOPSO) algorithms - for assigning optimal rehabilitation plans for sewer pipe networks. The algorithms considered were validated using some standard test functions reported in the literature and compared with each other in terms of several metrics. These algorithms were then linked to the SWMM-EPA hydraulic model and applied to a storm sewer pipe network case study in Seoul, South Korea, to obtain the best rehabilitation plans for pipe replacements. The results showed that the algorithms considered have different behaviours in solving the benchmark tests and rehabilitation problem. The proposed hybrid multi-objective harmony search algorithm provides better optimal solutions in terms of different metrics and clearly outperforms the other two algorithms for the rehabilitation of the storm sewer pipe networks.

KW - MOPSO

KW - Multi-objective optimisation

KW - NSGA-II

KW - NSHS

KW - Sewer pipe network

KW - Urban drainage system

UR - http://www.scopus.com/inward/record.url?scp=84923684409&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84923684409&partnerID=8YFLogxK

U2 - 10.1111/jfr3.12143

DO - 10.1111/jfr3.12143

M3 - Article

AN - SCOPUS:84923684409

JO - Journal of Flood Risk Management

JF - Journal of Flood Risk Management

SN - 1753-318X

ER -