Augmentation of an artificial neural network and modified stochastic dynamic programing model for optimal release policy

Sabah S. Fayaed, Ahmed El-Shafie, Humod Mosad Alsulami, Othman Jaafar, Muhammad Mukhlisin, Amr El-Shafie

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, a comprehensive modified stochastic dynamic programing with artificial neural network (MSDP-ANN) model is developed and applied to derive optimal operational strategies for a reservoir. Most water resource problems involve uncertainty. To show that the MSDP-ANN model addresses uncertainty in the input variable, the result of the MSDP-ANN model is compared with the performance of a detailed conventional stochastic dynamic programing with regression analysis (CSDP-RA) model. The computational time of the CSDP-ANN model is modified with concave objective functions by deriving a monotonic relationship between the reservoir storage and optimal release decision, and an algorithm is proposed to improve the computational efficiency of reservoir operation. Various indices (i.e. reliability, vulnerability, and resiliency) were calculated to assess the model performance. After comparing the performance of the CSDP-RA model with that of the MSDP-ANN model, it was observed that the MSDP-ANN model produces a more reliable and resilient model and a smaller supply deficit. Thus, it can be concluded that the MSDP-ANN model performs better than the CSDP-RA model in deriving the optimal operating policy for the reservoir.

Original languageEnglish
Pages (from-to)689-704
Number of pages16
JournalHydrology Research
Volume46
Issue number5
DOIs
Publication statusPublished - 2015

Fingerprint

artificial neural network
regression analysis
policy
vulnerability
water resource

Keywords

  • Artificial neural network
  • Modified stochastic dynamic programing
  • Optimization technique
  • Reservoir operation policy

ASJC Scopus subject areas

  • Water Science and Technology

Cite this

Augmentation of an artificial neural network and modified stochastic dynamic programing model for optimal release policy. / Fayaed, Sabah S.; El-Shafie, Ahmed; Alsulami, Humod Mosad; Jaafar, Othman; Mukhlisin, Muhammad; El-Shafie, Amr.

In: Hydrology Research, Vol. 46, No. 5, 2015, p. 689-704.

Research output: Contribution to journalArticle

Fayaed, Sabah S. ; El-Shafie, Ahmed ; Alsulami, Humod Mosad ; Jaafar, Othman ; Mukhlisin, Muhammad ; El-Shafie, Amr. / Augmentation of an artificial neural network and modified stochastic dynamic programing model for optimal release policy. In: Hydrology Research. 2015 ; Vol. 46, No. 5. pp. 689-704.
@article{7d5a4d38a0ee46948f55e0efdec1389b,
title = "Augmentation of an artificial neural network and modified stochastic dynamic programing model for optimal release policy",
abstract = "In this paper, a comprehensive modified stochastic dynamic programing with artificial neural network (MSDP-ANN) model is developed and applied to derive optimal operational strategies for a reservoir. Most water resource problems involve uncertainty. To show that the MSDP-ANN model addresses uncertainty in the input variable, the result of the MSDP-ANN model is compared with the performance of a detailed conventional stochastic dynamic programing with regression analysis (CSDP-RA) model. The computational time of the CSDP-ANN model is modified with concave objective functions by deriving a monotonic relationship between the reservoir storage and optimal release decision, and an algorithm is proposed to improve the computational efficiency of reservoir operation. Various indices (i.e. reliability, vulnerability, and resiliency) were calculated to assess the model performance. After comparing the performance of the CSDP-RA model with that of the MSDP-ANN model, it was observed that the MSDP-ANN model produces a more reliable and resilient model and a smaller supply deficit. Thus, it can be concluded that the MSDP-ANN model performs better than the CSDP-RA model in deriving the optimal operating policy for the reservoir.",
keywords = "Artificial neural network, Modified stochastic dynamic programing, Optimization technique, Reservoir operation policy",
author = "Fayaed, {Sabah S.} and Ahmed El-Shafie and Alsulami, {Humod Mosad} and Othman Jaafar and Muhammad Mukhlisin and Amr El-Shafie",
year = "2015",
doi = "10.2166/nh.2015.186",
language = "English",
volume = "46",
pages = "689--704",
journal = "Nordic Hydrology",
issn = "0029-1277",
publisher = "Nordic Association for Hydrology",
number = "5",

}

TY - JOUR

T1 - Augmentation of an artificial neural network and modified stochastic dynamic programing model for optimal release policy

AU - Fayaed, Sabah S.

AU - El-Shafie, Ahmed

AU - Alsulami, Humod Mosad

AU - Jaafar, Othman

AU - Mukhlisin, Muhammad

AU - El-Shafie, Amr

PY - 2015

Y1 - 2015

N2 - In this paper, a comprehensive modified stochastic dynamic programing with artificial neural network (MSDP-ANN) model is developed and applied to derive optimal operational strategies for a reservoir. Most water resource problems involve uncertainty. To show that the MSDP-ANN model addresses uncertainty in the input variable, the result of the MSDP-ANN model is compared with the performance of a detailed conventional stochastic dynamic programing with regression analysis (CSDP-RA) model. The computational time of the CSDP-ANN model is modified with concave objective functions by deriving a monotonic relationship between the reservoir storage and optimal release decision, and an algorithm is proposed to improve the computational efficiency of reservoir operation. Various indices (i.e. reliability, vulnerability, and resiliency) were calculated to assess the model performance. After comparing the performance of the CSDP-RA model with that of the MSDP-ANN model, it was observed that the MSDP-ANN model produces a more reliable and resilient model and a smaller supply deficit. Thus, it can be concluded that the MSDP-ANN model performs better than the CSDP-RA model in deriving the optimal operating policy for the reservoir.

AB - In this paper, a comprehensive modified stochastic dynamic programing with artificial neural network (MSDP-ANN) model is developed and applied to derive optimal operational strategies for a reservoir. Most water resource problems involve uncertainty. To show that the MSDP-ANN model addresses uncertainty in the input variable, the result of the MSDP-ANN model is compared with the performance of a detailed conventional stochastic dynamic programing with regression analysis (CSDP-RA) model. The computational time of the CSDP-ANN model is modified with concave objective functions by deriving a monotonic relationship between the reservoir storage and optimal release decision, and an algorithm is proposed to improve the computational efficiency of reservoir operation. Various indices (i.e. reliability, vulnerability, and resiliency) were calculated to assess the model performance. After comparing the performance of the CSDP-RA model with that of the MSDP-ANN model, it was observed that the MSDP-ANN model produces a more reliable and resilient model and a smaller supply deficit. Thus, it can be concluded that the MSDP-ANN model performs better than the CSDP-RA model in deriving the optimal operating policy for the reservoir.

KW - Artificial neural network

KW - Modified stochastic dynamic programing

KW - Optimization technique

KW - Reservoir operation policy

UR - http://www.scopus.com/inward/record.url?scp=84943259020&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84943259020&partnerID=8YFLogxK

U2 - 10.2166/nh.2015.186

DO - 10.2166/nh.2015.186

M3 - Article

AN - SCOPUS:84943259020

VL - 46

SP - 689

EP - 704

JO - Nordic Hydrology

JF - Nordic Hydrology

SN - 0029-1277

IS - 5

ER -