Improving dam and reservoir operation rules using stochastic dynamic programming and artificial neural network integration model

Sabah Saadi Fayaed, Seef Saadi Fiyadh, Wong Jee Khai, Ali Najah Ahmed, Haitham Abdulmohsin Afan, Rusul Khaleel Ibrahim, Chow Ming Fai, Suhana Koting, Nuruol Syuhadaa Mohd, Wan Zurina Binti Jaafar, Lai Sai Hin, Ahmed El-Shafie

Research output: Contribution to journalArticle

Abstract

The simulation elevation-surface area-storage interrelationship of a reservoir is a crucial task in developing ideal water release policies for reservoir and dam operations. In this study, an inclusive (stochastic dynamic programming-artificial neural network (SDP-ANN)) model was established and applied to obtain an ideal reservoir operation strategy for Sg. Langat reservoir in Malaysia. The problems associated with the management of water resources mostly relate to uncertainty and the stochastic nature of the reservoir inflow, and the SDP-ANN model is meant to consider uncertainty in the input parameters such as reservoir inflow and reservoir evaporation losses. The performance of the SDP-ANN model was compared to that of the stochastic dynamic programming-autoregression (AR) model. The primary aim of the model is to decrease the squared deviation from the desired water release, which we determined by comparing the SDP-AR and SDP-ANN model performances. The results indicate that the SDP-ANN model demonstrated greater resilience and reliability with a lower supply deficit. Consequently, the case study results confirm that the SDP-ANN model performs better than the SDP-AR model in obtaining the best parameters for the reservoir operation. Specifically, a comparison of the models shows that the proposed Model 2 increased the reliability and resilience of the system by 7.5% and 6.3%, respectively.

Original languageEnglish
Article number5367
JournalSustainability (Switzerland)
Volume11
Issue number19
DOIs
Publication statusPublished - 01 Oct 2019

Fingerprint

Dynamic programming
neural network
artificial neural network
Dams
programming
dam
Neural networks
water
resilience
inflow
uncertainty
Water resources
performance
Malaysia
Water
deficit
Evaporation
surface area
evaporation
water resource

All Science Journal Classification (ASJC) codes

  • Geography, Planning and Development
  • Renewable Energy, Sustainability and the Environment
  • Management, Monitoring, Policy and Law

Cite this

Fayaed, S. S., Fiyadh, S. S., Khai, W. J., Ahmed, A. N., Afan, H. A., Ibrahim, R. K., ... El-Shafie, A. (2019). Improving dam and reservoir operation rules using stochastic dynamic programming and artificial neural network integration model. Sustainability (Switzerland), 11(19), [5367]. https://doi.org/10.3390/su11195367
Fayaed, Sabah Saadi ; Fiyadh, Seef Saadi ; Khai, Wong Jee ; Ahmed, Ali Najah ; Afan, Haitham Abdulmohsin ; Ibrahim, Rusul Khaleel ; Fai, Chow Ming ; Koting, Suhana ; Mohd, Nuruol Syuhadaa ; Binti Jaafar, Wan Zurina ; Hin, Lai Sai ; El-Shafie, Ahmed. / Improving dam and reservoir operation rules using stochastic dynamic programming and artificial neural network integration model. In: Sustainability (Switzerland). 2019 ; Vol. 11, No. 19.
@article{9326185528104a3fb1dcc5604b06f482,
title = "Improving dam and reservoir operation rules using stochastic dynamic programming and artificial neural network integration model",
abstract = "The simulation elevation-surface area-storage interrelationship of a reservoir is a crucial task in developing ideal water release policies for reservoir and dam operations. In this study, an inclusive (stochastic dynamic programming-artificial neural network (SDP-ANN)) model was established and applied to obtain an ideal reservoir operation strategy for Sg. Langat reservoir in Malaysia. The problems associated with the management of water resources mostly relate to uncertainty and the stochastic nature of the reservoir inflow, and the SDP-ANN model is meant to consider uncertainty in the input parameters such as reservoir inflow and reservoir evaporation losses. The performance of the SDP-ANN model was compared to that of the stochastic dynamic programming-autoregression (AR) model. The primary aim of the model is to decrease the squared deviation from the desired water release, which we determined by comparing the SDP-AR and SDP-ANN model performances. The results indicate that the SDP-ANN model demonstrated greater resilience and reliability with a lower supply deficit. Consequently, the case study results confirm that the SDP-ANN model performs better than the SDP-AR model in obtaining the best parameters for the reservoir operation. Specifically, a comparison of the models shows that the proposed Model 2 increased the reliability and resilience of the system by 7.5{\%} and 6.3{\%}, respectively.",
author = "Fayaed, {Sabah Saadi} and Fiyadh, {Seef Saadi} and Khai, {Wong Jee} and Ahmed, {Ali Najah} and Afan, {Haitham Abdulmohsin} and Ibrahim, {Rusul Khaleel} and Fai, {Chow Ming} and Suhana Koting and Mohd, {Nuruol Syuhadaa} and {Binti Jaafar}, {Wan Zurina} and Hin, {Lai Sai} and Ahmed El-Shafie",
year = "2019",
month = "10",
day = "1",
doi = "10.3390/su11195367",
language = "English",
volume = "11",
journal = "Sustainability",
issn = "2071-1050",
publisher = "MDPI AG",
number = "19",

}

Fayaed, SS, Fiyadh, SS, Khai, WJ, Ahmed, AN, Afan, HA, Ibrahim, RK, Fai, CM, Koting, S, Mohd, NS, Binti Jaafar, WZ, Hin, LS & El-Shafie, A 2019, 'Improving dam and reservoir operation rules using stochastic dynamic programming and artificial neural network integration model', Sustainability (Switzerland), vol. 11, no. 19, 5367. https://doi.org/10.3390/su11195367

Improving dam and reservoir operation rules using stochastic dynamic programming and artificial neural network integration model. / Fayaed, Sabah Saadi; Fiyadh, Seef Saadi; Khai, Wong Jee; Ahmed, Ali Najah; Afan, Haitham Abdulmohsin; Ibrahim, Rusul Khaleel; Fai, Chow Ming; Koting, Suhana; Mohd, Nuruol Syuhadaa; Binti Jaafar, Wan Zurina; Hin, Lai Sai; El-Shafie, Ahmed.

In: Sustainability (Switzerland), Vol. 11, No. 19, 5367, 01.10.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Improving dam and reservoir operation rules using stochastic dynamic programming and artificial neural network integration model

AU - Fayaed, Sabah Saadi

AU - Fiyadh, Seef Saadi

AU - Khai, Wong Jee

AU - Ahmed, Ali Najah

AU - Afan, Haitham Abdulmohsin

AU - Ibrahim, Rusul Khaleel

AU - Fai, Chow Ming

AU - Koting, Suhana

AU - Mohd, Nuruol Syuhadaa

AU - Binti Jaafar, Wan Zurina

AU - Hin, Lai Sai

AU - El-Shafie, Ahmed

PY - 2019/10/1

Y1 - 2019/10/1

N2 - The simulation elevation-surface area-storage interrelationship of a reservoir is a crucial task in developing ideal water release policies for reservoir and dam operations. In this study, an inclusive (stochastic dynamic programming-artificial neural network (SDP-ANN)) model was established and applied to obtain an ideal reservoir operation strategy for Sg. Langat reservoir in Malaysia. The problems associated with the management of water resources mostly relate to uncertainty and the stochastic nature of the reservoir inflow, and the SDP-ANN model is meant to consider uncertainty in the input parameters such as reservoir inflow and reservoir evaporation losses. The performance of the SDP-ANN model was compared to that of the stochastic dynamic programming-autoregression (AR) model. The primary aim of the model is to decrease the squared deviation from the desired water release, which we determined by comparing the SDP-AR and SDP-ANN model performances. The results indicate that the SDP-ANN model demonstrated greater resilience and reliability with a lower supply deficit. Consequently, the case study results confirm that the SDP-ANN model performs better than the SDP-AR model in obtaining the best parameters for the reservoir operation. Specifically, a comparison of the models shows that the proposed Model 2 increased the reliability and resilience of the system by 7.5% and 6.3%, respectively.

AB - The simulation elevation-surface area-storage interrelationship of a reservoir is a crucial task in developing ideal water release policies for reservoir and dam operations. In this study, an inclusive (stochastic dynamic programming-artificial neural network (SDP-ANN)) model was established and applied to obtain an ideal reservoir operation strategy for Sg. Langat reservoir in Malaysia. The problems associated with the management of water resources mostly relate to uncertainty and the stochastic nature of the reservoir inflow, and the SDP-ANN model is meant to consider uncertainty in the input parameters such as reservoir inflow and reservoir evaporation losses. The performance of the SDP-ANN model was compared to that of the stochastic dynamic programming-autoregression (AR) model. The primary aim of the model is to decrease the squared deviation from the desired water release, which we determined by comparing the SDP-AR and SDP-ANN model performances. The results indicate that the SDP-ANN model demonstrated greater resilience and reliability with a lower supply deficit. Consequently, the case study results confirm that the SDP-ANN model performs better than the SDP-AR model in obtaining the best parameters for the reservoir operation. Specifically, a comparison of the models shows that the proposed Model 2 increased the reliability and resilience of the system by 7.5% and 6.3%, respectively.

UR - http://www.scopus.com/inward/record.url?scp=85073418129&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073418129&partnerID=8YFLogxK

U2 - 10.3390/su11195367

DO - 10.3390/su11195367

M3 - Article

AN - SCOPUS:85073418129

VL - 11

JO - Sustainability

JF - Sustainability

SN - 2071-1050

IS - 19

M1 - 5367

ER -