Forecasting hydrological parameters for reservoir system utilizing artificial intelligent models and exploring their influence on operation performance

Mohammed Falah Allawi, Othman Jaafar, Firdaus Mohamad Hamzah, Suhana Binti Koting, Nuruol Syuhadaa Binti Mohd, Ahmed El-Shafie

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Obtaining successful operation rules for dam and reservoir systems is crucial for improving water management to meet the increase in agricultural, domestic and industrial activities. Several research efforts have been developed to generate optimal operation rules for dam and reservoir systems utilizing different optimization algorithms. The main purpose of an operation rule is to minimize the gap between water supply and water demand patterns. To examine the optimized model performance, the simulation of a dam and reservoir system is usually carried out for a particular period utilizing the generated operation rule. During the simulation procedure, although reservoir inflow and evaporation are stochastic variables that are required to be forecasted during simulation, they are considered deterministic variables. This study attempts to integrate a forecasting model for reservoir inflow and evaporation with the operation rules generated from optimization models during the simulation procedure. The present study employs several optimization models to generate an optimal operation rule and two different forecasting models for reservoir inflow and reservoir evaporation. The three different optimization algorithms used in this study are the genetic algorithm (GA), particle swarm optimization (PSO) algorithm and shark machine learning algorithm (SMLA). Two different forecasting models have been developed for reservoir inflow and evaporation using the radial basis function neural network (RBF-NN) and support vector regression (SVR). It is necessary to analyze the proposed simulation procedure for examining the operation rule to comprehend the analysis under different optimal operation rules and levels of accuracy for both hydrological variables. The suggested models have been applied to generate optimal operation policies and reservoir inflow and evaporation forecasts for the Timah Tasoh dam (TTD) located in Malaysia. The results show that the major findings regarding the model performance during the simulation period indicate the necessity to pay attention to evaluating the optimized model performance by considering the results of the forecasting model for both the hydrological variables of reservoir inflow and reservoir evaporation rather than the deterministic values.

Original languageEnglish
Pages (from-to)907-926
Number of pages20
JournalKnowledge-Based Systems
Volume163
DOIs
Publication statusPublished - 1 Jan 2019

Fingerprint

Evaporation
Dams
Water management
Water supply
Simulation
Particle swarm optimization (PSO)
Learning algorithms
Learning systems
Genetic algorithms
Neural networks
Water
Optimization model

Keywords

  • Hydrological parameters
  • Reservoir system
  • Tropical region

ASJC Scopus subject areas

  • Software
  • Management Information Systems
  • Information Systems and Management
  • Artificial Intelligence

Cite this

Forecasting hydrological parameters for reservoir system utilizing artificial intelligent models and exploring their influence on operation performance. / Allawi, Mohammed Falah; Jaafar, Othman; Mohamad Hamzah, Firdaus; Koting, Suhana Binti; Mohd, Nuruol Syuhadaa Binti; El-Shafie, Ahmed.

In: Knowledge-Based Systems, Vol. 163, 01.01.2019, p. 907-926.

Research output: Contribution to journalArticle

@article{b46635188c5d490d8f54a3ecf06cac83,
title = "Forecasting hydrological parameters for reservoir system utilizing artificial intelligent models and exploring their influence on operation performance",
abstract = "Obtaining successful operation rules for dam and reservoir systems is crucial for improving water management to meet the increase in agricultural, domestic and industrial activities. Several research efforts have been developed to generate optimal operation rules for dam and reservoir systems utilizing different optimization algorithms. The main purpose of an operation rule is to minimize the gap between water supply and water demand patterns. To examine the optimized model performance, the simulation of a dam and reservoir system is usually carried out for a particular period utilizing the generated operation rule. During the simulation procedure, although reservoir inflow and evaporation are stochastic variables that are required to be forecasted during simulation, they are considered deterministic variables. This study attempts to integrate a forecasting model for reservoir inflow and evaporation with the operation rules generated from optimization models during the simulation procedure. The present study employs several optimization models to generate an optimal operation rule and two different forecasting models for reservoir inflow and reservoir evaporation. The three different optimization algorithms used in this study are the genetic algorithm (GA), particle swarm optimization (PSO) algorithm and shark machine learning algorithm (SMLA). Two different forecasting models have been developed for reservoir inflow and evaporation using the radial basis function neural network (RBF-NN) and support vector regression (SVR). It is necessary to analyze the proposed simulation procedure for examining the operation rule to comprehend the analysis under different optimal operation rules and levels of accuracy for both hydrological variables. The suggested models have been applied to generate optimal operation policies and reservoir inflow and evaporation forecasts for the Timah Tasoh dam (TTD) located in Malaysia. The results show that the major findings regarding the model performance during the simulation period indicate the necessity to pay attention to evaluating the optimized model performance by considering the results of the forecasting model for both the hydrological variables of reservoir inflow and reservoir evaporation rather than the deterministic values.",
keywords = "Hydrological parameters, Reservoir system, Tropical region",
author = "Allawi, {Mohammed Falah} and Othman Jaafar and {Mohamad Hamzah}, Firdaus and Koting, {Suhana Binti} and Mohd, {Nuruol Syuhadaa Binti} and Ahmed El-Shafie",
year = "2019",
month = "1",
day = "1",
doi = "10.1016/j.knosys.2018.10.013",
language = "English",
volume = "163",
pages = "907--926",
journal = "Knowledge-Based Systems",
issn = "0950-7051",
publisher = "Elsevier",

}

TY - JOUR

T1 - Forecasting hydrological parameters for reservoir system utilizing artificial intelligent models and exploring their influence on operation performance

AU - Allawi, Mohammed Falah

AU - Jaafar, Othman

AU - Mohamad Hamzah, Firdaus

AU - Koting, Suhana Binti

AU - Mohd, Nuruol Syuhadaa Binti

AU - El-Shafie, Ahmed

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Obtaining successful operation rules for dam and reservoir systems is crucial for improving water management to meet the increase in agricultural, domestic and industrial activities. Several research efforts have been developed to generate optimal operation rules for dam and reservoir systems utilizing different optimization algorithms. The main purpose of an operation rule is to minimize the gap between water supply and water demand patterns. To examine the optimized model performance, the simulation of a dam and reservoir system is usually carried out for a particular period utilizing the generated operation rule. During the simulation procedure, although reservoir inflow and evaporation are stochastic variables that are required to be forecasted during simulation, they are considered deterministic variables. This study attempts to integrate a forecasting model for reservoir inflow and evaporation with the operation rules generated from optimization models during the simulation procedure. The present study employs several optimization models to generate an optimal operation rule and two different forecasting models for reservoir inflow and reservoir evaporation. The three different optimization algorithms used in this study are the genetic algorithm (GA), particle swarm optimization (PSO) algorithm and shark machine learning algorithm (SMLA). Two different forecasting models have been developed for reservoir inflow and evaporation using the radial basis function neural network (RBF-NN) and support vector regression (SVR). It is necessary to analyze the proposed simulation procedure for examining the operation rule to comprehend the analysis under different optimal operation rules and levels of accuracy for both hydrological variables. The suggested models have been applied to generate optimal operation policies and reservoir inflow and evaporation forecasts for the Timah Tasoh dam (TTD) located in Malaysia. The results show that the major findings regarding the model performance during the simulation period indicate the necessity to pay attention to evaluating the optimized model performance by considering the results of the forecasting model for both the hydrological variables of reservoir inflow and reservoir evaporation rather than the deterministic values.

AB - Obtaining successful operation rules for dam and reservoir systems is crucial for improving water management to meet the increase in agricultural, domestic and industrial activities. Several research efforts have been developed to generate optimal operation rules for dam and reservoir systems utilizing different optimization algorithms. The main purpose of an operation rule is to minimize the gap between water supply and water demand patterns. To examine the optimized model performance, the simulation of a dam and reservoir system is usually carried out for a particular period utilizing the generated operation rule. During the simulation procedure, although reservoir inflow and evaporation are stochastic variables that are required to be forecasted during simulation, they are considered deterministic variables. This study attempts to integrate a forecasting model for reservoir inflow and evaporation with the operation rules generated from optimization models during the simulation procedure. The present study employs several optimization models to generate an optimal operation rule and two different forecasting models for reservoir inflow and reservoir evaporation. The three different optimization algorithms used in this study are the genetic algorithm (GA), particle swarm optimization (PSO) algorithm and shark machine learning algorithm (SMLA). Two different forecasting models have been developed for reservoir inflow and evaporation using the radial basis function neural network (RBF-NN) and support vector regression (SVR). It is necessary to analyze the proposed simulation procedure for examining the operation rule to comprehend the analysis under different optimal operation rules and levels of accuracy for both hydrological variables. The suggested models have been applied to generate optimal operation policies and reservoir inflow and evaporation forecasts for the Timah Tasoh dam (TTD) located in Malaysia. The results show that the major findings regarding the model performance during the simulation period indicate the necessity to pay attention to evaluating the optimized model performance by considering the results of the forecasting model for both the hydrological variables of reservoir inflow and reservoir evaporation rather than the deterministic values.

KW - Hydrological parameters

KW - Reservoir system

KW - Tropical region

UR - http://www.scopus.com/inward/record.url?scp=85055549505&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055549505&partnerID=8YFLogxK

U2 - 10.1016/j.knosys.2018.10.013

DO - 10.1016/j.knosys.2018.10.013

M3 - Article

VL - 163

SP - 907

EP - 926

JO - Knowledge-Based Systems

JF - Knowledge-Based Systems

SN - 0950-7051

ER -