A hybrid bat–swarm algorithm for optimizing dam and reservoir operation

Zaher Mundher Yaseen, Mohammed Falah Allawi, Hojat Karami, Mohammad Ehteram, Saeed Farzin, Ali Najah Ahmed, Suhana Binti Koting, Nuruol Syuhadaa Mohd, Wan Zurina Binti Jaafar, Haitham Abdulmohsin Afan, Ahmed El-Shafie

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

One of the major challenges and difficulties to generate optimal operation rule for dam and reservoir operation are how efficient the optimization algorithm to search for the global optimal solution and the time-consume for convergence. Recently, evolutionary algorithms (EA) are used to develop optimal operation rules for dam and reservoir water systems. However, within the EA, there is a need to assume internal parameters at the initial stage of the model development, such assumption might increase the ambiguity of the model outputs. This study proposes a new hybrid optimization algorithm based on a bat algorithm (BA) and particle swarm optimization algorithm (PSOA) called the hybrid bat–swarm algorithm (HB-SA). The main idea behind this hybridization is to improve the BA by using the PSOA in parallel to replace the suboptimal solution generated by the BA. The solutions effectively speed up the convergence procedure and avoid the trapping in local optima caused by using the BA. The proposed HB-SA is validated by minimizing irrigation deficits using a multireservoir system consisting of the Golestan and Voshmgir dams in Iran. In addition, different optimization algorithms from previous studies are investigated to compare the performance of the proposed algorithm with existing algorithms for the same case study. The results showed that the proposed HB-SA algorithm can achieve minimum irrigation deficits during the examined period and outperforms the other optimization algorithms. In addition, the computational time for the convergence procedure is reduced using the HB-SA. The proposed HB-SA is successfully examined and can be generalized for several dams and reservoir systems around the world.

Original languageEnglish
Pages (from-to)8807-8821
Number of pages15
JournalNeural Computing and Applications
Volume31
Issue number12
DOIs
Publication statusPublished - 01 Dec 2019

Fingerprint

Dams
Irrigation
Evolutionary algorithms
Particle swarm optimization (PSO)

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

Yaseen, Z. M., Allawi, M. F., Karami, H., Ehteram, M., Farzin, S., Ahmed, A. N., ... El-Shafie, A. (2019). A hybrid bat–swarm algorithm for optimizing dam and reservoir operation. Neural Computing and Applications, 31(12), 8807-8821. https://doi.org/10.1007/s00521-018-3952-9
Yaseen, Zaher Mundher ; Allawi, Mohammed Falah ; Karami, Hojat ; Ehteram, Mohammad ; Farzin, Saeed ; Ahmed, Ali Najah ; Koting, Suhana Binti ; Mohd, Nuruol Syuhadaa ; Jaafar, Wan Zurina Binti ; Afan, Haitham Abdulmohsin ; El-Shafie, Ahmed. / A hybrid bat–swarm algorithm for optimizing dam and reservoir operation. In: Neural Computing and Applications. 2019 ; Vol. 31, No. 12. pp. 8807-8821.
@article{3740bf06dc844850bef2d4161c8f3ae9,
title = "A hybrid bat–swarm algorithm for optimizing dam and reservoir operation",
abstract = "One of the major challenges and difficulties to generate optimal operation rule for dam and reservoir operation are how efficient the optimization algorithm to search for the global optimal solution and the time-consume for convergence. Recently, evolutionary algorithms (EA) are used to develop optimal operation rules for dam and reservoir water systems. However, within the EA, there is a need to assume internal parameters at the initial stage of the model development, such assumption might increase the ambiguity of the model outputs. This study proposes a new hybrid optimization algorithm based on a bat algorithm (BA) and particle swarm optimization algorithm (PSOA) called the hybrid bat–swarm algorithm (HB-SA). The main idea behind this hybridization is to improve the BA by using the PSOA in parallel to replace the suboptimal solution generated by the BA. The solutions effectively speed up the convergence procedure and avoid the trapping in local optima caused by using the BA. The proposed HB-SA is validated by minimizing irrigation deficits using a multireservoir system consisting of the Golestan and Voshmgir dams in Iran. In addition, different optimization algorithms from previous studies are investigated to compare the performance of the proposed algorithm with existing algorithms for the same case study. The results showed that the proposed HB-SA algorithm can achieve minimum irrigation deficits during the examined period and outperforms the other optimization algorithms. In addition, the computational time for the convergence procedure is reduced using the HB-SA. The proposed HB-SA is successfully examined and can be generalized for several dams and reservoir systems around the world.",
author = "Yaseen, {Zaher Mundher} and Allawi, {Mohammed Falah} and Hojat Karami and Mohammad Ehteram and Saeed Farzin and Ahmed, {Ali Najah} and Koting, {Suhana Binti} and Mohd, {Nuruol Syuhadaa} and Jaafar, {Wan Zurina Binti} and Afan, {Haitham Abdulmohsin} and Ahmed El-Shafie",
year = "2019",
month = "12",
day = "1",
doi = "10.1007/s00521-018-3952-9",
language = "English",
volume = "31",
pages = "8807--8821",
journal = "Neural Computing and Applications",
issn = "0941-0643",
publisher = "Springer London",
number = "12",

}

Yaseen, ZM, Allawi, MF, Karami, H, Ehteram, M, Farzin, S, Ahmed, AN, Koting, SB, Mohd, NS, Jaafar, WZB, Afan, HA & El-Shafie, A 2019, 'A hybrid bat–swarm algorithm for optimizing dam and reservoir operation', Neural Computing and Applications, vol. 31, no. 12, pp. 8807-8821. https://doi.org/10.1007/s00521-018-3952-9

A hybrid bat–swarm algorithm for optimizing dam and reservoir operation. / Yaseen, Zaher Mundher; Allawi, Mohammed Falah; Karami, Hojat; Ehteram, Mohammad; Farzin, Saeed; Ahmed, Ali Najah; Koting, Suhana Binti; Mohd, Nuruol Syuhadaa; Jaafar, Wan Zurina Binti; Afan, Haitham Abdulmohsin; El-Shafie, Ahmed.

In: Neural Computing and Applications, Vol. 31, No. 12, 01.12.2019, p. 8807-8821.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A hybrid bat–swarm algorithm for optimizing dam and reservoir operation

AU - Yaseen, Zaher Mundher

AU - Allawi, Mohammed Falah

AU - Karami, Hojat

AU - Ehteram, Mohammad

AU - Farzin, Saeed

AU - Ahmed, Ali Najah

AU - Koting, Suhana Binti

AU - Mohd, Nuruol Syuhadaa

AU - Jaafar, Wan Zurina Binti

AU - Afan, Haitham Abdulmohsin

AU - El-Shafie, Ahmed

PY - 2019/12/1

Y1 - 2019/12/1

N2 - One of the major challenges and difficulties to generate optimal operation rule for dam and reservoir operation are how efficient the optimization algorithm to search for the global optimal solution and the time-consume for convergence. Recently, evolutionary algorithms (EA) are used to develop optimal operation rules for dam and reservoir water systems. However, within the EA, there is a need to assume internal parameters at the initial stage of the model development, such assumption might increase the ambiguity of the model outputs. This study proposes a new hybrid optimization algorithm based on a bat algorithm (BA) and particle swarm optimization algorithm (PSOA) called the hybrid bat–swarm algorithm (HB-SA). The main idea behind this hybridization is to improve the BA by using the PSOA in parallel to replace the suboptimal solution generated by the BA. The solutions effectively speed up the convergence procedure and avoid the trapping in local optima caused by using the BA. The proposed HB-SA is validated by minimizing irrigation deficits using a multireservoir system consisting of the Golestan and Voshmgir dams in Iran. In addition, different optimization algorithms from previous studies are investigated to compare the performance of the proposed algorithm with existing algorithms for the same case study. The results showed that the proposed HB-SA algorithm can achieve minimum irrigation deficits during the examined period and outperforms the other optimization algorithms. In addition, the computational time for the convergence procedure is reduced using the HB-SA. The proposed HB-SA is successfully examined and can be generalized for several dams and reservoir systems around the world.

AB - One of the major challenges and difficulties to generate optimal operation rule for dam and reservoir operation are how efficient the optimization algorithm to search for the global optimal solution and the time-consume for convergence. Recently, evolutionary algorithms (EA) are used to develop optimal operation rules for dam and reservoir water systems. However, within the EA, there is a need to assume internal parameters at the initial stage of the model development, such assumption might increase the ambiguity of the model outputs. This study proposes a new hybrid optimization algorithm based on a bat algorithm (BA) and particle swarm optimization algorithm (PSOA) called the hybrid bat–swarm algorithm (HB-SA). The main idea behind this hybridization is to improve the BA by using the PSOA in parallel to replace the suboptimal solution generated by the BA. The solutions effectively speed up the convergence procedure and avoid the trapping in local optima caused by using the BA. The proposed HB-SA is validated by minimizing irrigation deficits using a multireservoir system consisting of the Golestan and Voshmgir dams in Iran. In addition, different optimization algorithms from previous studies are investigated to compare the performance of the proposed algorithm with existing algorithms for the same case study. The results showed that the proposed HB-SA algorithm can achieve minimum irrigation deficits during the examined period and outperforms the other optimization algorithms. In addition, the computational time for the convergence procedure is reduced using the HB-SA. The proposed HB-SA is successfully examined and can be generalized for several dams and reservoir systems around the world.

UR - http://www.scopus.com/inward/record.url?scp=85059478098&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059478098&partnerID=8YFLogxK

U2 - 10.1007/s00521-018-3952-9

DO - 10.1007/s00521-018-3952-9

M3 - Article

AN - SCOPUS:85059478098

VL - 31

SP - 8807

EP - 8821

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 0941-0643

IS - 12

ER -