filter by: Publication Year
(Descending) Articles
Stochastic Environmental Research And Risk Assessment (14363259) 39(4)pp. 1605-1621
One major characteristic of the Standardized Drought Indices is their dependence on one variable. However, different variables influence drought simultaneously. To address this issue, this study modifies and develops the Surface Water Supply Index (SWSI) to involve multiple aspects of droughts. Data on precipitation, runoff, reservoir volume, and discharge (instead of snow) over 21 years are used to modify the SWSI in Marun, Khuzestan Province, Iran. Standardized Precipitation Index (SPI), Standardized Runoff Index (SRI), Standardized Reservoir Storage Index (SRSI), and Standardized Discharge Index (SDI) are used as standard univariate indices to evaluate a new comprehensive index. The Shannon Entropy (SE) method is utilized innovatively to determine the weights of the comprehensive index, instead of deriving them depending on the weather experts. Additionally, a Modified-Surface Water Supply Index (M-SWSI) is also proposed to align it with the existing standard indices. For comparison, the weights are also calculated using the Proportioning Objective Procedure (POP) method, and presented in the POP-SWSI index. The results indicate that utilizing the SE method to determine weights provides an exceptional perspective on the meteorological and hydrological conditions of the drought-affected upstream region; while determining the weights using the POP method provides an insightful socio-economic and hydrological view on the drought-affected downstream region. In 2017, one of the most severe years, the M-SWSI index detected a drought event one month earlier than the POP-SWSI, with a drought duration value of 6 months close to the duration value of 5 months identified by POP-SWSI. Furthermore, the severity values were similar between the two indices, although the M-SWSI indicated lower drought severity than the univariate indices. Copulas are also employed for drought events analysis and to build the joint distribution function of drought severity (S) and duration (D) for the M-SWSI. Bivariate cumulative probability distribution functions are created and analyzed to determine the periodic “and” and “or” bivariate drought return periods. Additionally, Severity-Duration-Frequency (SDF) curves are established to evaluate the M-SWSI index. The Marun dam has been chosen as a case study to analyze the surface water supply under drought conditions, aiming to develop management policies for downstream decision-making. Consequently, the M-SWSI can be applied to any dam reservoir for similar analyses. This index involves various aspects of drought and can be utilized for reservoir management, assessing risks, and addressing flood and flood risk management challenges. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.
Results in Engineering (25901230) 25
Completing gaps in groundwater level (GWL) data is critical for reliable hydrological analysis and modeling. The irregularities and missing values often present in GWL measurements necessitate robust methods for infilling. In this study, an innovative approach is proposed to reconstruct the GWL time series by addressing data gaps. Historical GWL data spanning 20 years from 40 observation wells in the Lenjanat aquifer, Isfahan Province, Iran, are used. Three clustering methods—K-means, Fuzzy C-means (FCM), and Self-Organizing Map (SOM)—are applied to group the wells, and a novel metric, the Correlation-based Reliability Index (CRI), is introduced to identify the most suitable clustering method for GWL prediction. The selected cluster is analyzed using four machine learning and hybrid models, including support vector regression (SVR) with linear, polynomial, and radial basis function (RBF) kernels, genetic programming (GP), artificial neural networks (ANN), and a hybrid model combining SVR with the whale optimization algorithm (WOA) (WOA-SVR). Results reveals that the SVR model with an RBF kernel outperformed its counterparts with linear and polynomial kernels, while the hybrid WOA-SVR model shows superior performance compared to other models. The hybrid approach significantly improves the accuracy of GWL gap completion. The WOA-SVR model leads to average R2, RMSE, MAPE, and NS values of 0.81 (0.74), 0.55 m (0.95 m), 0.02 % (0.04 %), and 0.80 (0.72) for the training (test and validation) data, respectively. The results demonstrates that the proposed approach, integrating clustering, CRI, and machine learning models, can effectively fill GWL gaps and provide clean data for further hydrological modeling and groundwater management. © 2025 The Authors
Environment, Development and Sustainability (1387585X)
In this study, a novel approach is proposed in which the transition probability matrix (TPM) of stochastic dynamic programming (SDP) methods is determined based on the copula function (TPM-C) by calculating the conditional probability. The obtained results are compared with the TPM based on the Markov Chain method (TPM-M). Here, the Marun dam reservoir, in southwestern Iran, is selected as a case study. In addition, for the historical period, the best values of reliability, resilience, vulnerability, sustainability, a minimum of water deficit as an objective function are obtained, and the average reservoir storage value of TPM-C is better than TPM-M. Finally, to update the reservoir operation rule curves, three different scenarios are proposed depending on the historical and future conditions. For this purpose, the water inflow values into the dam reservoir are predicted using a Multi-Layer Perceptron (MLP) model depending on the predicted precipitation of the climate change model. Therefore, the inflows, reservoir storage volumes, and water demand values are used to simulate and forecast the water release values into the reservoir. The results show the superior performance of the proposed TPM-C compared to the TPM-M approach to determine the reservoir operation rule curves at uncertain future conditions. © The Author(s), under exclusive licence to Springer Nature B.V. 2025.
Journal of Water Resources Planning and Management - ASCE (07339496) 151(10)
Graph theory-based methods are widely used to partition water distribution networks (WDNs) into district metered areas (DMAs). In general, the Girvan-Newman (GN) algorithm partitions networks based solely on the edge betweenness, a purely topological criterion, without considering the intrinsic hydraulic characteristics of WDNs. To address this limitation, in this study, an improved approach, named the improved Girvan-Newman (IGN) algorithm, is proposed, which integrates hydraulic parameters into the partitioning process. Specifically, pressure (as a quantity parameter) and chlorine concentration (as a quality parameter) are incorporated into the algorithm. The IGN method involves modeling the WDN as a graph, simulating it using either the demand-driven simulation method or the head-driven simulation method during a 24-h extended period simulation (EPS), and assigning nodal weights based on hydraulic values. Edge scores are then calculated using these nodal weights, and the edge with the lowest score is iteratively removed, with corresponding links closed in the hydraulic model. Then, the WDN is reanalyzed to update the hydraulic parameters. This iterative process continues until the desired number of DMAs is achieved. Two case studies, a small-scale WDN, named Poulakis, and a large-scale real WDN of Baharestan city in Isfahan, Iran, are used to investigate the performance of the IGN algorithm. In Poulakis WDN, by using IGN, the average nodal pressure decreases by 1.6%, the chlorine concentration increases by 9.1%, and the hybrid reliability improves by 3.7% compared to the standard GN algorithm. In addition, in Baharestan WDN, the related values are 5.1%, 3.4%, and 4.2%, respectively. The IGN method also enables flexible and time-dependent DMA configurations during EPS, in which the final configuration is selected based on a floating index. Here, a novel integration of hydraulic features into the GN algorithm is proposed, offering a more effective and reliable approach to WDN partitioning and management. © 2025 American Society of Civil Engineers.
Results in Engineering (25901230) 25
Due to the sensitivity of water quality to all types of pollution (intentional and unintentional), monitor of drinking Water distribution networks (WDNs) is necessary. Therefore, the optimal location of quality sensors should be defined to increase the sensors coverage of consumption nodes in the WDN. For this purpose, in this research, the best location and the number of sensors are determined by modeling it as optimization. Three benchmark problems are used. Here, the Dragonfly Algorithm (DA) is used to solve optimization problem considering different scenarios for three case studies, including Lee and Deininger and the second and the third EPANET networks. The obtained results are compared with genetic algorithm (GA). For the Lee and Deininger network, by using the DA, the nodal coverage values are increased by 8.34 %, 8.33 %, 2.5 %, and 17.5 % compared to GA, for the first, second, third and forth scenarios, respectively. In addition, for the second (third) network example of EPANET software, by using DA, the nodal coverage values are increased by 83.03 % (17.22 %) and 93.36 % (71.33 %) compared to GA, for first and second scenarios, respectively. © 2025 The Author(s)
Applied Water Science (21905495) 15(2)
To satisfy the consumer demand, urban infrastructures are generally designed. The water distribution network (WDN) is one of the most important urban infrastructures in which optimal design and operation of it is essential during the operation period. For this purpose, in this research, artificial intelligence and data mining methods, including genetic programming (GP), gene expression programming (GEP), artificial neural network (ANN), and discrete wavelet transform function, are used to predict the daily drinking water consumption values of WDN. For this purpose, a dataset of temperature, precipitation, humidity, and daily water value of Najaf-Abad city in Iran is used during year 2014 to 2019. Here, hybrid models named W-GEP, W-GP, W-ANN, are proposed by equipping GEP, GP, and ANN with a wavelet transform function. In addition, two formulations are proposed for each model. Performance of proposed methods is investigated by determining R2, RMSE, and NSE statistical indices. For the training data of the W-GP model, the RMSE, NSE, and R2 values are 2810.46 (m3/day), 0.85, and 0.85, respectively, while for test and validation data these values are 2638.92 (m3/day), 0.87, and 0.87, respectively. Results show the good performance of proposed methods. In addition, the discrete wavelet transform function improves the models’ performance, in which the best results obtained by using the W-GEP model. © The Author(s) 2025.
Varshabi n., ,
Moeini, R. ,
Mousavizadeh s.r., S.R. International Journal of Environmental Science and Technology (17351472) 22(13)pp. 12307-12316
In this research, temperature and nitrate values at the outlet of the ZayandehRoud dam reservoir are simulated and predicted using a genetic programming (GP) model. Initially, the CE-QUAL-W2 model is applied to simulate the water quality condition of the dam reservoir from autumn 2016 to the end of summer 2021 for calibration and from autumn 2021 to the end of summer 2022 for the validation process. In addition, the genetic programming (GP) model is also used to reduce the simulation computation costs, and the results are presented and compared with the artificial neural network (ANN) model. For temperature simulation using GP, the best RMSE values of the training and validation process are 1.800 and 1.925 °C, respectively, compared to related values of 1.405 and 1.932 °C using ANN. Furthermore, for nitrate simulation of GP, the best RMSE values of the training and validation process are 0.383 and 0.536 mgL−1, respectively, compared to related values of 0.362 and 0.711 mgL−1, respectively, using the ANN model. The results demonstrate the GP model’s good performance in simulating the dam reservoir’s quality conditions. © The Author(s) under exclusive licence to Iranian Society of Environmentalists (IRSEN) and Science and Research Branch, Islamic Azad University 2025.
Soft Computing (14327643) 28(3)pp. 1989-2014
In this research, the problem of optimal conjunctive operation of surface and groundwater systems is investigated by proposing a cyclic storage approach. This problem is solved here using mathematical programming and some efficient Meta heuristic algorithms. For this purpose, the mathematical model of this system is defined and first solved by the nonlinear programming (NLP) method. In addition, the performance of the artificial bee colony (ABC) algorithm, genetic algorithm (GA), gravitational search algorithm (GSA) and, particle swarm optimization (PSO) algorithms are also studied to solve this problem. Here, two case studies, meaning a hypothetical benchmark system and conjunctive use of Buchan dam reservoir and Miandoab aquifer located in the catchment area of Urmia Lake (ZarrinehRoud catchment area) as a real problem, are considered to study the performance of proposed methods. In other words, for the hypothetical benchmark system, the results show that the optimal operating cost and related computational time are equal to 5.2428 Billion Rials and 5400 s, respectively, obtained by using the NLP method. In addition, in comparison with the result of the NLP method, the operation costs increased by 26.36%, 26.1%, 44.91% and, 21.28% using ABC, GA, GSA and, PSO algorithms, respectively. However, the computational time is extremely decreased in comparison with the related value of the NLP method using these algorithms for a particular case. In other words, for the real benchmark system, the results show that the optimal operating cost and related computational time are equal to 139.0145 Billion Rials and 259,200 s, respectively, obtained by using the NLP method. In addition, in comparison with the result of the NLP method, the operation costs increased by 43.74%, 32.32%, and 50.57% using ABC, GA and, PSO algorithms, respectively. However, by using this algorithm, the computational time is extremely decreased in comparison with the related value of the NLP method for a particular case. Furthermore, in both case studies, the water demands are fully stratified using the proposed methods. Therefore, the obtained results show the efficiency and effectivity of the proposed methods to solve this complex optimization problem considering a cyclic storage approach. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.
Ain Shams Engineering Journal (20904479) 15(5)
In general, partitioning networks into district metered areas (DMA) is known as a practical method to manage the pressure and reduce water leakage in Water Distribution Networks (WDNs). Different methods such as engineering judgment, optimization techniques, and graph theory are proposed to determine the DMA. The graph theory is a traditional method for partitioning networks including several algorithms. One of these algorithms is the Girvan-Newman (GN) algorithm which is based on the mathematical parameters without considering the characteristics of networks. In other words, the hydraulic quality and quantity condition of WDNs are not used for DMA determination. Therefore, in this research, a new method is proposed to improve the performance of the GN algorithm for DMA determination considering the quantities of water networks. For this purpose, the average values of nodal pressure and residual chlorine concentration are calculated and used simultaneously for the junction's weight determination. Then, the edge scores are calculated based on the junction's weights, and the edges with the maximum scores are removed until to reach the desired number of DMAs. For comparison purposes, here, the Demand-Driven Simulation Method (DDSM) and Head-Driven Simulation Method (HDSM) analyses are used for the analysis of the Poulakis WDN, selected as a case study. A comparison of the results shows that by using the proposed method, the average pressure values are decreased and the average residual chlorine concentration values are increased. In other words, the pressure values are decreased from 16.32% to 26.23% and the average residual chlorine concentration values are increased from 2.5% to 18.37% in comparison with the results of the standard form of the GN algorithm using both DDSM and HDSM analyses. Furthermore, by using the proposed method, in all scenarios, the hybrid reliability values increase in comparison with the GN algorithm. The results indicate the unique performance of the proposed method in comparison with the standard form of the GN algorithm for DMA determination of WDNs. © 2024 THE AUTHORS
Water Resources Management (09204741) 38(11)pp. 4137-4159
A key issue for effective management and operating of dam reservoirs is predicting the water inflow values into dam reservoir. To address this subject, here, genetic programming (GP) is used by proposing two cases. In the first case, water inflow values are predicted separately for each month. However, in the second case, these values are predicted simultaneously for all months. Furthermore, for each case, two approaches are proposed here. In the first approach, the hybrid method, called the ANN-NGSA-II method, is proposed to find proper input data sets. However, in the second approach, the useful input data sets are found automatically using the GP method. For comparison purpose, the ANN and SARIMA models are also used, to predict the water inflow values. As a case study, in this research, the Zayandehroud dam reservoir is selected. The results indicate that the ANN model outperforms both results of the GP and SARIMA methods. In other words, correlation coefficient (R2), Nash Sutcliffe (NS), and root means square error (RMSE) values of ANN are 0.97, (0.88), 0.954 (0.87), and 17.19 (30.54) million cubic meters, respectively, for training (test) data set. © The Author(s), under exclusive licence to Springer Nature B.V. 2024.
Results in Engineering (25901230) 23
Accessing reliable quantitative and qualitative drinking water is one of the requirements of human society. Therefore, the water distribution network is designed to distribute reliable drinking water to consumers. In general, the entrance of any unintentional and intentional contamination reduces the reliability of this network. Therefore, it is necessary to monitor the water distribution network using quality sensors to minimize the amount of contaminated water. In this research, three benchmarks of the Lee and Denninger network and the second and third network examples of EPANET software are selected as case studies. Here, by defining different scenarios, the optimal locations of quality sensors are determined using the dragonfly algorithm (DA) and the results are compared with the genetic algorithm (GA). This algorithm is a binary (zero-one) algorithm that has not any hyperparameters leading to reliable results. In addition, this algorithm is not used in the fields of quality monitoring of water distribution networks and therefore it is used here. The results showed the efficiency of the DA to solve this problem. In other words, for the Lee and Deninger network, the amount of contaminated water is reduced by 4.98 %, considering one sensor and consumption pattern one, 26.69 %, considering at least two sensors and consumption pattern one, 27.52 %, considering one sensor and consumption pattern two, and 19.76 %, considering least two sensors and consumption pattern two, using the DA. In addition, for the second network example of EPANET, the amount of contaminated water is reduced by 32.09 %, considering the 24-h consumption pattern and one sensor, and 20.8 %, considering the 24-h consumption pattern and at least two sensors. Finally, for the third network example of EPANET, the amount of contaminated water is reduced by 0.122 %, considering the 24 h consumption pattern and one sensor, and 0.345 %, considering the 24-h consumption pattern and at least two sensors. © 2024 The Authors
Agricultural Water Management (18732283) 277
Investigating the quantity and quality interaction of the surface and groundwater resources plays an essential role in the integrated management of the surface and groundwater resources. In this study, to estimate the discharge and nitrate concentration of the interaction between the Chadegan aquifer and the Zayandeh-Roud reservoir, a quantitative-qualitative simulation model is developed using MODFLOW and MT3DMS codes. Here, the model is calibrated using the data from the beginning of winter 2011 to the end of winter 2014, and validated for spring 2014 to summer 2020. For the quantitative calibration, in the steady and unsteady conditions, the RMSE values of the water level are 0.74 m and 1.84 m, respectively, and for the qualitative calibration, the measured nitrate concentration values is 1.89 mg/L. In addition, for the validation state of the proposed model, the values of RMSE for the water levels and nitrate concentrations are 3.76 m and 2.85 mg/L, respectively. The results indicate that the aquifer has always been recharged by the reservoir during this time. In addition, the exchange nitrate concentration value is between 39.56 and 48.85 mg/L. The decreasing trend of the water level and the increase in the nitrate concentration, which exceed the permissible limit in some areas, indicate the necessity of adopting the immediate managerial policies. Five managerial scenarios are proposed and the effect on the aquifer conditions in terms of increase in the water level and the decrease of nitrate concentration is investigated. The results indicate that the 20% gradual reduction of the agricultural water consumption and simultaneously a 20% gradual reduction in nitrate fertilizers consumption and completing the urban wastewater treatment systems is the most effective quantitative-qualitative scenario for this region, with a 0.24% increase in the average water level and a 11.36% decrease in the average concentration of the nitrate in the aquifer by the end of the forecasting period. © 2022 The Authors
Iranian Journal Of Science And Technology, Transactions Of Civil Engineering (22286160) 47(5)pp. 3123-3136
Urban water distribution networks are the most essential and costly network in each city. Major part of the urban water distribution network costs are related to the purchase of water distribution network accessories. Therefore, the cost of the water distribution network can be reduced by reducing this part. For this purpose, the design of water distribution network should be defined as an optimization model and solved it using an efficient method. Nowadays, meta-heuristics algorithms are the most efficient methods for solving optimization models. In this research, three benchmark problems, mean two-loop, New York, and Go Yang networks, are modeled in EPANET software and the optimization model is solved using an improved version of the artificial bee colony algorithm that is called in MATLAB software. To evaluate the efficiency of the proposed algorithm, the results are presented and compared with the standard version of the artificial bee colony algorithm and other available results. The results show that by using an improved artificial bee colony algorithm for two-loop network, New York, and Go Yang network, the objective function values (construction costs) and computational costs are 419,000 unit, 38.13 M$, and 175.78 MWon and 2500, 3600, and 2600, respectively. In addition, comparison of the results shows that the construction and computational costs are reduced compared with the result of the standard version. © 2023, The Author(s), under exclusive licence to Shiraz University.
Ain Shams Engineering Journal (20904479) 14(5)
Finding critical points of the wastewater network by rebuilding the infrastructure is cheaper than repairing it after occurring failure. This task can be done by using predictive approaches. Therefore, in this study, a new method is proposed to predict the number of pipe failures per length of wastewater network. For this purpose, genetic programming (GP) is used to predict the pipe failure of sewer network in Isfahan region 2 using the data from year 2014 to 2017.The obtained results are compared with the results of corresponding artificial neural network (ANN) model. For this purpose, three different approaches are proposed. In the first approach named GA-CLU-T, the number of pipe failures is predicted using all data. However, in the second ones named GA-CLU-Y, the models are created and trained using the data of year 2014 and the obtained model is used to predict the number of pipe failure for other years in future. Finally, the third ones named GA-CLU-R is proposed to determine the number of pipe failures in other regions. Here, two different models are proposed for each approaches using GP method. The result shows that the best RMSE (R2) values of first, second and third approaches for test data set are 0.00316 (0.966), 0.00074 (0.996) and 0.00075 (0.997), respectively. The results show that the result accuracy of GP models is better than the corresponding ANN models. © 2022
PFG - Journal of Photogrammetry, Remote Sensing and Geoinformation Science (25122819) 91(5)pp. 391-404
Snow cover is an informative indicator of climate change and surface hydrological cycles. Despite its essential accurate dynamic measurement (i.e., accumulation, erosion, and runoff), it is poorly known, particularly in mountainous regions. Since passive microwave sensors can contribute to obtaining information about snowpack volume, microwave brightness temperatures (BT) have long been used to assess spatiotemporal variations in snow water equivalent (SWE). However, SWE is greatly influenced by geographic location, terrain parameters/covers, and BT differences, and thus, the low spatial resolution of existing SWE products (i.e., the coarse resolution of AMSR-based products) leads to less satisfactory results, especially in regions with complex terrain conditions, strong seasonal transitions and, great spatiotemporal heterogeneity. A novel multifactor SWE downscaling algorithm based on the support vector regression (SVR) technique has been developed in this study for the Zayandehroud River basin. Thereby, passive microwave BT, location (latitude and longitude), terrain parameters (i.e., elevation, slope, and aspect), and vegetation cover serve as model input data. Evaluation of downscaled SWE estimates against ground-based observations demonstrated that when moving into higher spatial resolution, not only was there no significant decrease in accuracy, but a 4% increase was observed. In addition, this study suggests that integrating passive microwave remote sensing data with other auxiliary data can lead to a more efficient and effective algorithm for retrieving SWE with appropriate spatial resolution over various scales. © 2023, Deutsche Gesellschaft für Photogrammetrie, Fernerkundung und Geoinformation (DGPF) e.V.
Sustainable Computing: Informatics and Systems (22105379) 35
In this research, simple and practical methods have been proposed to determine the reservoir operation rule curves considering uncertain water inflow values at future conditions based on the concept of comparative reservoirs management. For this purpose, two methods are proposed. In the first method named His-Inf, by considering the historical water inflow values, a mathematical optimization model is proposed for defining the reservoir operation rule curves determination problem and solved using nonlinear programming (NLP) method. However, in the second method, three different approaches named Pre-Inf1, Pre-Inf2 and Pre-Inf3 are proposed. In the Pre-Inf1 method, at first, water inflow values into the dam reservoir are predicted using neural network (ANN) model. Then, the predicted water inflow values are used to determine and update the reservoir operation rule curves using NLP method. In the Pre-Inf2 method, the ANN model is used to simulate and update the constant coefficients of the reservoir operation rule curves considering the water demand, water inflow values into the reservoir, water release values form reservoir and time index (T) as data set. For this purpose, two different framework and structure are proposed for sorting and providing data set leading to two different cases. Finally, in the Pre-Inf3 method, at first, water inflow values, reservoir storage volumes, water demand values and time index (T) are used to simulate and predict water releases values from the reservoir. Then, the linear regression method is used to determine the reservoir operation rule curves and policies. Here, both static and dynamic ANN models are used for simulating and predicting the water inflow values and reservoir operation rule curves and policies. In order to investigate the performance of proposed methods, here, the Sefidrood dam reservoir is considered as a case study in which it is located at the intersection of the QezelOzan River and Shahroud River near the city of Manjil in the north of Iran. Finally, the obtained results are presented and compared by calculating the reliability, residency, vulnerability and sustainability indexes. Comparison of the result indicates the superiority of the proposed Pre-Inf3 method for determining the reservoir operation rule curves at uncertain future condition in which the results of the His-Inf, Pre-Inf1 and Pre-Inf2 methods are almost similar. In other words, the sustainability index of His-Inf, Pre-Inf1, Pre-Inf2 and Pre-Inf3 are 63%, 63%, 63% and 74%, respectively, in which the corresponding value of Pre-Inf3 is 17.5% bigger than other proposed methods. © 2022 Elsevier Inc.
Pishgah hadiyan, P. ,
Moeini, R. ,
Ehsanzadeh, E. ,
Karvanpour, M. Water Resources Management (09204741) 36(8)pp. 2703-2723
Nowadays, the use of artificial intelligence is extended to various scientific and engineering fields including water management and planning. This study investigates the performance of dynamic artificial neural network (ANN) models in prediction of water inflow into the Sefidruod dam reservoir (Iran). For this purpose, first, the discharge time series of tributaries of the Sefidruod dam were analyzed for trends for a 47 year time period (1967 to 2014) using parametric regression and non-parametric Mann–Kendall tests considering independence, short-term, and long-term persistence assumptions. Also, the homogeneity of the data was investigated using three statistical tests including Cumulative Deviations, Worsley's Likelihood Ratio, and Bayesian inference. Then, the inflow discharges into the reservoir of Sefidruod dam from GhezelOzan and Shahroud tributaries were simulated using dynamic Nonlinear Auto-Regressive (NAR) and Nonlinear Auto-Regressive with exogenous input (NARX) models. Further, water inflow values of both rivers were predicted for the next 5 years in future using dynamic NAR and NARX models. Finally, the simulated results were tested for trends. Obtained results showed a significant decreasing trend in both rivers. Results also showed a continuous downward trend for the following 5-year period predicted by NAR and NARX models. In addition, it was found that the results obtained by the NARX model were less accurate compared to those by the NAR model. © 2022, The Author(s), under exclusive licence to Springer Nature B.V.
Soft Computing (14327643) 25(22)pp. 14081-14108
One of the most important and effective works of water resource planning and management is determining the specific, applicable, regulated operating policies of the Zayandehroud dam reservoir, as a case study, in which it should be user-friendly and straightforward for the operator. For this purpose, different methods have been proposed in which each of them has its limitations. Due to the unique capabilities of the genetic programming (GP) model, here, this method is used to determine the operating rule curves and policies of the dam reservoir. For this purpose, here, two cases are proposed in which, in the first case, each month is individually simulated and modeled. However, in the second case, all months are simulated simultaneously. A second case is proposed here to determine simple and more applicable operation rule curves. In addition, two approaches are suggested for each case in which in the first approach, the influential input variables are selected by presenting the hybrid method. In the proposed hybrid method, the artificial neural network (ANN) model is equipped with non-dominated sorting genetic (NSGA-II) algorithm leading to a hybrid method named the ANN-NSGA-II method. However, in the second approach, the influential input variables are selected automatically using the GP method. Here, the hybrid method is proposed and used to overcome the limitations of existing usual method. In other words, it is proposed to reduce the number of influential input variables of data-driven methods and select the effective ones. The obtained results of all proposed cases and approaches are presented and compared with the standard operation policy method, stochastic dynamic programming, ANN model, and NLP method. Comparison of the results shows the acceptable performance of the proposed cases and approaches. In other words, the best-obtained values of (stability index) SI index and water deficit (objective function value) are 49.3% and 32, respectively. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.
Ain Shams Engineering Journal (20904479) 12(1)pp. 423-435
In this research, a new method named minimal pumping (MP) method has been proposed. In this proposed method, the required time for damaged pipe repairing is minimized using up stream pipes and manholes capacities, and therefore pumping cost required for diversion is reduced. Generally, wastewater bypass is necessary for repairing the wastewater pipelines using some trenchless repair methods. As a result, upstream of the damaged pipe is plugged with plug and packer and the wastewater is pumped to downstream of damaged pipe. If repair time is long, bypassing would be very expensive and therefore, here, the MP method is proposed in which it significantly reduces the repair cost. In this research, as a case study, the wastewater pipelines of Mirzakouchek Khan Boulevard in Isfahan and wastewater network of Ardekan city are selected to apply the proposed method. Furthermore, in the second case study, the effect of repair time duration and starting time of repair in real condition are also studied using the extended period condition for analyzing. The results show the compatibility of the proposed method in reducing the repair costs of underground wastewater pipelines in urban areas. In other words, the required pumping time and related cost is reduced 70 to 85% and 70 to 100% for Mirzakouchek Khan Boulevard and Ardekan city wastewater network, respectively, using the proposed method. © 2020 Ain Shams University
Sustainable Computing: Informatics and Systems (22105379) 27
Accurate forecasting of reservoir inflow is of great importance in water resources planning and management and it can highly affect decisions and policies of reservoir operation with respect to flood control, drought management, water supply, and hydropower generation. In this study, different models of static and dynamic artificial neural networks (ANN) including static feed forward neural network (FFNN), non-linear autoregressive (NAR), and nonlinear autoregressive with exogenous inputs (NARX) are employed in order to forecast Sefidroud Dam reservoir inflows. The capability of studied networks with a range of different input variables in predicting reservoir inflows are then compared. All employed models are trained using inflow discharge and precipitation data with different time delays and an optimum number of neurons in the hidden layers are obtained. In addition, the time index (T) is also employed as the input data to the proposed models in order to increase the accuracy of the estimates. The obtained results indicate that NAR dynamic neural network has a better performance in comparison with FFNN and NARX models. Furthermore, using 12 time delays for inflow discharges and precipitation data leads to the best accessible results where adding time index (T) increases the accuracy. The results obtained from this study provide useful information for reservoir inflow simulation. In other words, these results are critical for water resources management and planning particularly in the field of dam reservoir operation which is crucial under reported water crisis in Iran. © 2020 Elsevier Inc.
Water and Environment Journal (17476585) 34(S1)pp. 468-480
In this paper, the improved artificial bee colony (IABC) and improved particle swarm optimisation (IPSO) have been used for the optimal design of stepped spillway with the minimisation of construction cost as the energy dissipater structure for a dam project. Generally, the construction cost of this structure is the most expensive part of the project. However, traditional designing methods of stepped spillway such as the Vittal and Porey (VP) approach cannot find optimal dimensions of the stepped spillway with minimum cost. Therefore, the optimisation methods such as meta-heuristic algorithms have been used. As a case study, Tehri dam’s stepped spillway in India has been considered here and the optimal dimensions of this spillway have been obtained using IPSO, IABC algorithms and the results have been compared with VP approach and other available results. Comparison of the results shows that when the three-stepped spillway is considered, the results of IABC and IPSO algorithms are improved by 17.72% in comparison with VP results. In addition, when the four-stepped spillway is considered, the results of IABC, IPSO algorithms are, respectively, improved by 16.47% and 16.53% in comparison with the VP results. © 2020 CIWEM
Journal of Hydroinformatics (14647141) 22(2)pp. 263-280
In this paper, one of the newest meta-heuristic algorithms, named artificial bee colony (ABC) algorithm, is used to solve the single-reservoir operation optimization problem. The simple and hydropower reservoir operation optimization problems of Dez reservoir, in southern Iran, have been solved here over 60, 240, and 480 monthly operation time periods considering two different decision variables. In addition, to improve the performance of this algorithm, two improved artificial bee colony algorithms have been proposed and these problems have been solved using them. Furthermore, in order to improve the performance of proposed algorithms to solve large-scale problems, two constrained versions of these algorithms have been proposed, in which in these algorithms the problem constraints have been explicitly satisfied. Comparison of the results shows that using the proposed algorithm leads to better results with low computational costs in comparison with other available methods such as genetic algorithm (GA), standard and improved particle swarm optimization (IPSO) algorithm, honey-bees mating optimization (HBMO) algorithm, ant colony optimization algorithm (ACOA), and gravitational search algorithm (GSA). Therefore, the proposed algorithms are capable algorithms to solve large reservoir operation optimization problems. 263 © IWA Publishing 2020
Journal of Environmental Informatics (17262135) 36(2)pp. 70-81
In this paper the proposed constrained gravitational search algorithm (CGSA) is extended and used to solve multi-reservoir operation optimization problem. Tow constrained versions of GSA named partially constrained GSA (PCGSA) and fully constrained GSA (FCGSA) are outlined to solve this optimization problem. In the PCGSA, the problem constraints are partially satisfied, h owever, in the FCGSA, all the problem constraints are implicitly satisfied by providing the search space for each agent which contain s only fea-sible solution and hence leading to smaller search space for each agent. These proposed constrained versions of GSA are very useful when they are applied to solve large scale multi-reservoir operation optimization problem. The constrained versions of GSA are formu-lated here for both possible variables of the problem means considering water release or storage volumes as the decision variables of the problem and therefore first and second formulations of these algorithms are proposed. The proposed algorithms are used to sol ve the well-known four and ten reservoir operation optimization problems and the results are presented and compared with those of original form of the GSA and any available results in the literature. The results indicate the superiority of the proposed algorithms and especially FCGSA over existing methods to optimally solve large scale multi-reservoir operation optimization problem. © 2020 ISEIS All rights reserved.
Applied Soft Computing (15684946) 95
In this paper, new hybrid methods have been proposed to solve reservoir operation optimization problem for uncertain water inflows condition by equipping improved particle swarm optimization (IPSO) algorithm with support vector machine (SVM) method. The constrained version of IPSO algorithm (CIPSO) has been used here to improve the efficiency of the IPSO algorithm. In CIPSO algorithm, the problem constraints have been explicitly satisfied leading to smaller search space and finally smaller computational cost. Two approaches have been considered to propose the hybrid methods. In the first approach, named SVM-CIPSO1, water inflows into the dam reservoir have been predicted using SVM model and these predicted values have been used to solve reservoir operation optimization problem using CIPSO algorithm. However, in the second approach, named SVM-CIPSO2, at first, the CIPSO algorithm has been applied to solve reservoir operation optimization problem using the historical data and finally the optimal water release values have been used as input and output data to create a SVM model for predicting optimal water release from reservoir for the future condition. For comparison purpose, the ANN model has been also used to predict the water inflow or release values for the future condition and the standard form of IPSO algorithm has been also used to solve the optimization problem. Here, to evaluate the proposed approaches, the optimal water release values form Zayandehroud dam reservoir have been obtained using proposed methods and the reliability, resiliency, vulnerability and sustainability indexes have been computed. Comparison of the results indicates the capability of the proposed methods to predict the optimal water release values for future condition with acceptable accuracy. In other words, the RMSE values of SVM model for test, validation and training processes are 9.7104 (23. 56196), 11.2553 (42.69093), and 7.9556 (47.9346) MCM, respectively, which are obtained using second (first) approach. In addition, the best reliability, resiliency, vulnerability and sustainability index values are 51.95% (45.45%), 45.95% (38.10%), 3.539 (0.0041) MCM and 62.02% (55.74%), respectively, which are obtained using SVM-CIPSO2 (SVM-CIPSO1) method. © 2020 Elsevier B.V.
Environmental Engineering and Management Journal (15829596) 19(4)pp. 687-700
In the present research, four meta-heuristic algorithms named Genetic Algorithm (GA), Gravitational Search Algorithm (GSA), Particle Swarm Optimization (PSO), and Artificial Bee Colony (ABC) have been used for optimal design of cascade spillway to minimize the construction cost. Usually, the traditional design methods such as Vittal and Porey (VP) method or experimental modeling are used to solve this problem leading to infeasible or near optimal solution. The main novelty of this paper is to use effective methods to solve this complex highly constrained problem. Therefore, due to unique features of meta-heuristic algorithms, these algorithms are used here to minimize the construction cost of cascade spillway as the energy dissipater structure. As the case study, cascade spillway of Tehri dam in India had been chosen. The algorithms results have been compared together and with the VP results. Comparison of the results show the effectiveness and affectivity of these algorithms to solve this optimization problem. In other words, when three-stepped spillway are considered, the results are improved with 16.16%, 16.4%, 17.73% and 17.63% respectively using GA, GSA, PSO and ABC algorithms and in the same manner, for four-stepped spillway, the results are improved 14.5%, 16.1%, 16.45% and 16.05% respectively using GA, GSA, PSO and ABC algorithms in comparison with the VP results. © 2020 Gheorghe Asachi Technical University of Iasi, Romania. All rights reserved.
Soft Computing (14327643) 24(14)pp. 10739-10754
In this research, a new meta-heuristic algorithm, named artificial bee colony (ABC) algorithm, is used to solve multi-reservoir operation optimization problem. For this purpose, two improved versions of ABC are proposed by modifying the structure of original standard form of ABC algorithm. Furthermore, in order to increase the performance of proposed algorithms for solving large-scale problems, the constrained versions of original and improved form of ABC algorithms have been proposed in which the problem constraints are explicitly satisfied. Two benchmark text examples, including four- and ten-reservoir operation optimization problems, are solved here using proposed algorithms, and the results are presented and compared. In order to solve these problems, here, two formulations are also proposed in which in the first formulation, the water releases from the reservoir and in the second one the water storage volumes of the reservoir are considered as the decision variables of the problem. Comparison of the results shows that by using the improved ABC algorithm, the better results are obtained with less computational effort in comparison with the original form of ABC algorithm in which the result improvement is notable when the proposed constrained version of the algorithms is used. © 2019, Springer-Verlag GmbH Germany, part of Springer Nature.
Environmental Engineering and Management Journal (15829596) 18(5)pp. 957-971
In this paper, four different kinds of the Ant Colony Optimization Algorithm (ACOA) are used to find optimal solution for sewer network design optimization problem proposing two different formulations for each of them. In both proposed formulations, the decision variables of the problem are cover depths of sewer network nodes. In the second formulation, the constrained version of ACOA is used to find optimal cover depths of the sewer network nodes. The constrained version of ACOA is used here to satisfy slope constraints explicitly leading to reduction of search space of the problem. The Ant System, Elitist Ant System, Elitist-Rank Ant System and Max-Min Ant System are used here to solve two benchmark test examples and the results are presented and compared with other available results. The results show the superiority of the Max-Min Ant System over than other ACOAs in which the trade-off between the two contradictory search characteristic of exploration and exploitation is managed better using this algorithm. Furthermore, best results are obtained with second proposed formulation in comparison with other available results in which they are shown the capability of the proposed formulation to find optimal solution for sewer network design optimization. In other words, the second formulation of Max-Min Ant System has been able to produce results 0.3% and 0.15% cheaper than those obtained by first formulation of Max-Min Ant System for the first and second benchmark test examples, respectively. Furthermore, the average solution cost value of second formulation of Max-Min Ant System is reduced 10.6% (8.1%), 0.43% (0.6%) and 0.34% (0.02%) in comparison with second formulation of Ant System, Elitist Ant System and Elitist-Rank Ant System for first (second) benchmark test examples, respectively. © 2019, Gheorghe Asachi Technical University of Iasi, Romania. All rights reserved.
Water Resources Management (09204741) 33(6)pp. 2203-2218
Inflow prediction of reservoirs is of considerable importance due to its application in water resources management related to downstream water release planning and flood protection. Therefore, in this research, different new input patterns for predicting inflow to Zayandehroud dam reservoir is proposed employing artificial neural network (ANN) and support vector machine (SVM) models. Nine different models with different patterns of input data such as inflow to the dam reservoir considering time duration lags, time index, and monthly rainfall of Ghaleh-Shahrokh station have been proposed to predict the inflow to the dam reservoir. Comparison of the results indicates that the ninth proposed model has the least error for inflow prediction in which the results of SVM model outperform those of ANN model. That is, the least error has been obtained using the ninth SVM (ANN) model with correlation coefficient (R) values of 0.8962 (0.89296), 0.9303 (0.92983) and 0.9622 (0.95333) and root mean squared error (RMSE) values of 47.9346 (48.5441), 42.69093 (43.748) and 23.56193 (28.5125) for training, validation and test data, respectively. © 2019, Springer Nature B.V.
Water Environment Research (10614303) 91(4)pp. 300-321
The ant colony optimization algorithm (ACOA) is hybridized with nonlinear programming (NLP) for the optimal design of sewer networks. The resulting problem is a highly constrained mixed integer nonlinear problem (MINLP) presenting a challenge even to the modern heuristic search methods. In the proposed hybrid method, The ACOA is used to determine pipe diameters while the NLP is used to determine the pipe slopes of the network by proposing two different formulations. In the first formulation, named ACOA-NLP1, a penalty method is used to satisfy the problem constraints while in the second one, named ACOA-NLP2, the velocity and flow depth constraints are expressed in terms of the slope constraints which are easily satisfied as box constraint of the NLP solver leading to a considerable reduction of the search space size. In addition, the assumption of minimum cover depth at the network inlets is used to calculate the nodal cover depths and the pump and drop heights at the network nodes, if required, leading to a complete solution. The total cost of the constructed solution is used as the objective function of the ACOA, guiding the ant toward minimum cost solutions. Proposed hybrid methods are used to solve three test examples, and the results are presented and compared with those produced by a conventional application of ACOA. The results indicate the effectiveness and efficiency of the proposed formulations and in particular the ACOA-NLP2 to optimally solve the sewer network design optimization problems. • Practitioner points • ACOA is hybridized with NLP for the effective optimal design of sewer networks. • Here, ACOA is used to determine pipe diameters and NLP is used to determine the network pipe slopes with predefined pipe diameters. • In ACOA-NLP1, a penalty method is used to enforce the problem constraints. • In ACOA-NLP2, velocity and flow depth constrains are expressed in terms of slope constraint. © 2019 Water Environment Federation.
International Journal of Operational Research (17457653) 33(4)pp. 512-537
In this paper, the efficiency of considering the constant and varying Manning coefficient for a hydraulic analysis model on the optimal solution of sewer network design optimisation problem is studied. To solve sewer network design optimisation problem, here, different formulations are proposed using genetic algorithm, discreet and continues ant colony optimisation algorithms. In all proposed formulations, the nodal cover depths of the sewer network are taken as decision variables of the problem. Furthermore, for both ant-based algorithms two different formulations are proposed using unconstrained and constrained versions of these algorithms. The constrained versions of these algorithms are proposed here for the explicit satisfaction of the minimum pipe slope constraint leading to smaller search space. Two benchmark test examples are solved here using proposed formulations and the results are presented and compared with other available results. Comparison of the results shows the superiority of considering varying Manning coefficient condition for hydraulic analysis model. Furthermore, the results show the superiority of continues ant colony optimisation algorithm and especially the constrained version of it to optimally solve the sewer network design optimisation problem. © 2018 Inderscience Enterprises Ltd.
Journal of Engineering Research (17266742) 15(1)pp. 42-60
In this paper, the Ant Colony Optimization Algorithm (ACOA) is applied to solve Water Distribution System design optimization problem proposing two different methods. Considering pipe diameters as decision variables of the problem, Ant System and Max-Min Ant System, referred to ACOA1 and ACOA2 respectively, are applied to determine pipe diameters. In proposed methods, the ant-based models are interfaced with EPANET as simulator for the hydraulic analysis. Three benchmark test examples are solved with proposed methods and the results are presented and compared with those obtained with other existing methods. The results show the capability of the proposed methods to optimally solve the design optimization problem in which best results are obtained with ACOA2 in comparison with other available results. Furthermore, the results show the superiority of the proposed ACOA2 over than the ACOA1 in which the trade-off between the two contradictory search characteristic of exploration and exploitation is managed better by using Max-Min Ant System. © 2018 Sultan Qaboos University.
Ain Shams Engineering Journal (20904479) 8(2)pp. 207-223
In this paper, constrained and unconstrained versions of a new formulation of Ant Colony Optimization Algorithm (ACOA) named Arc Based Ant Colony Optimization Algorithm (ABACOA) are augmented with the Tree Growing Algorithm (TGA) and used for the optimal layout and pipe size design of gravitational sewer networks. The main advantages offered by the proposed ABACOA formulation are proper definition of heuristic information, a useful component of the ant-based algorithms, and proper trade-off between the two conflicting search attributes of exploration and exploitation. In both the formulations, the TGA is used to incrementally construct feasible tree-like layouts out of the base layout. In the first formulation, unconstrained version of ABACOA is used to determine the nodal cover depths of sewer pipes while in the second formulation, a constrained version of ABACOA is used to determine the nodal cover depths of sewer pipes which satisfy the pipe slopes constraint. Three different methods of cut determination are also proposed to complete the construction of a tree-like network containing all base layout pipes, here. The proposed formulations are used to solve three test examples of different scales and the results are presented and compared with other available results in the literature. Comparison of the results shows that best results are obtained using the third cutting method in both the formulations. In addition, the results indicate the ability of the proposed methods and in particular the constrained version of ABACOA equipped with TGA to solve sewer networks design optimization problem. To be specific, the constrained version of ABACOA has been able to produce results 0.1%, 1% and 2.1% cheaper than those obtained by the unconstrained version of ABACOA for the first, second and the third test examples, respectively. © 2016 Faculty of Engineering, Ain Shams University
Scientia Iranica (23453605) 24(3)pp. 953-965
In this paper, Arc Based Ant Colony Optimization Algorithm (ABACOA) is used to solve sewer network design optimization problem with proposing two different formulations. In both of the proposed formulations, i.e. UABAC and CABAC, the cover depths of sewer network nodes are taken as decision variables of the problem. The constrained version of ABACOA (CABAC) is also proposed in the second formulation to optimally determine the cover depths of the sewer network nodes. The constrained version of ABACOA is proposed here to satisfy slope constraint explicitly leading to reduction of search space of the problem, which is compared with that by the unconstrained arc based ACOA (UABAC). The ABACOA has two significant advantages of efcient implementation of the exploration and exploitation features along with an easy and straightforward definition of the heuristic information for the ants over the alternative usual point based formulation. Two benchmark test examples are solved here using the proposed formulations, and the results are presented and compared with those obtained by alternative point-based formulation and other existing methods. The results show the superiority of the proposed ABACOA formulation, especially the constrained version of it, to optimally solve the sewer network design optimization. © 2017 Sharif University of Technology. All rights reserved.
Engineering Applications of Artificial Intelligence (09521976) 62pp. 222-233
The gravitational search algorithm (GSA) is used in this paper to solve large scale reservoir operation optimization problem. Here, two constrained versions of GSA are proposed to solve this problem in which masses may be forced to satisfy problem constraints during solution building. This approach is very useful when attempting to solve large scale optimization problem as it will lead to a considerable reduction of the search space size. Here, in the second version of GSA, the storage volume bounds of the reservoir are modified prior to the main search to recognize the infeasible components of the search space and exclude from the search process before the main search starts. Two formulations are also proposed here for each proposed algorithm considering water releases or storage volumes at each operation time period as decision variable of the problem. Proposed algorithms are used to solve the simple and hydropower operation problem of “Dez” reservoir in Iran and the results are presented and compared with using original form of the GSA and any available results. The results indicate the ability of the proposed algorithm and especially the second constrained version of GSA to optimally solve the reservoir operation optimization problem. © 2017 Elsevier Ltd
Evolving Systems (18686486) 8(4)pp. 287-301
In this paper, the improved particle swarm optimization (IPSO) algorithm is used to solve large scale reservoir operation optimization problem proposing unconstrained and two constrained versions of this algorithm. In the two constrained versions proposed for the IPSO algorithm, named PCIPSO and FCIPSO, each particle may be forced to satisfy problem constraints during solution building. By considering water releases or storage volumes at each operation time period as decision variable of the problem, here, two formulations are proposed for each version. In the second proposed constrained version algorithm (FCIPSO), at first, the water storage volume bounds are modified in order to recognize the infeasible components of the search space and exclude from the search process before the main search starts. This mechanism leads to smaller search space size for the problem and finally better results. The simple and hydropower operation problems of “Dez” reservoir in the southern Iran over 60, 240 and 480 monthly operations time periods are solved here using both proposed formulations of theses algorithms and the results are presented and compared with other available results. The results show the capability of the proposed algorithms and especially the second constrained version of the IPSO algorithm, FCIPSO, to optimally solve the reservoir operation optimization problem. In other words, the results of both formulations of constrained IPSO and especially FCIPSO algorithm are improved significantly in comparison with unconstrained IPSO algorithm over all operations time periods of simple and hydropower operation of the reservoir. © 2017, Springer-Verlag GmbH Germany.
Scientia Iranica (23453605) 22(6)pp. 2069-2069
The authors regret that the affliation of the third author (R. Moeini) has been printed incorrectly as "Department of Civil Engineering, Faculty of Engineering, Isfahan University, Isfahan, Postal Cod: 81746-73441, Iran." and should be corrected as "Department of Civil Engineering, Faculty of Engineering, University of Isfahan, Isfahan, Postal Code: 81746-73441, Iran." The authors would like to appologize for any inconvenience caused. The main objective in the design of the sewer network problems is minimization of the construction and operation cost. The sewer network optimization problem can be divided in two problems of selection the network layout and sizing of network, determining the pipe diameters and slopes, for selected layout. These two problems, however, are not independent and should be handled simultaneously. © 2015 Sharif University of Technology. All rights reserved.
Urban Water Journal (17449006) 10(3)pp. 154-173
The incremental solution building capability of Ant Colony Optimisation Algorithm (ACOA) is used in this paper for the efficient layout and pipe size optimisation of sanitary sewer network. Layout and pipe size optimisation of sanitary sewer networks requires optimal determination of pipe locations, pipe diameters and pipe slopes leading to a highly constrained mixed-integer nonlinear programming (MINLP) problem presenting a challenge even to the modern heuristic search methods. A constrained version of ACOA equipped with a Tree Growing Algorithm (TGA) is proposed in this paper for the simultaneous layout and pipe size determination of sewer networks. The method is based on the assumption that a base layout including all possible links of the network is available. The TGA algorithm is used in an incremental manner to construct feasible tree-like layouts out of the base layout, while the constrained ACOA is used to optimally determine the cover depths of the constructed layout. Proposed formulation is used to solve three hypothetical test examples of different scales and the results are presented and compared with those produced by a conventional application of ACOA in which an ad-hoc engineering concept is used for layout determination. The results indicate the effectiveness and efficiency of the proposed method to optimally solve the problem of layout and size determination of sewer networks. © 2013 Copyright Taylor and Francis Group, LLC.
Journal of Hydroinformatics (14647141) 15(1)pp. 155-173
This paper extends the application of Constrained Ant Colony Optimization Algorithms (CACOAs) to optimal operation of multi-reservoir systems. Three different formulations of the constrained Ant Colony Optimization (ACO) are outlined here using Max-Min Ant System for the solution of multireservoir operation problems. In the first two versions, called Partially Constrained ACO algorithms, the constraints of the multi-reservoir operation problems are satisfied partially. In the third formulation, all the constraints of the underlying problem are implicitly satisfied by the provision of tabu lists to the ants which contain only feasible options. The ants are, therefore, forced to construct feasible solutions and hence the method is referred to as a Fully Constrained ACO algorithm. The proposed constrained ACO algorithms are formulated for both possible cases of taking storage/release volumes as the decision variables of the problem. The proposed methods are used to optimally solve the well-known problems of four- and ten-reservoir operations and the results are presented and compared with those of the conventional unconstrained ACO algorithm and existing methods in the literature. The results indicate the superiority of the proposed methods over conventional ACOs and existing methods to optimally solve large scale multi-reservoir operation problems. © IWA Publishing 2013.
Advances in Intelligent Systems and Computing (discontinued) (21945365) 227pp. 91-105
This paper presents an adaptation of the Ant Colony Optimization Algorithm (ACOA) for the efficient layout and pipe size optimization of sewer network. ACOA has a unique feature namely incremental solution building mechanism which is used here for this problem. Layout and pipe size optimization of sewer network is a highly constrained Mixed-Integer Nonlinear Programming (MINLP) problem presenting a challenge even to the modern heuristic search methods. ACOA equipped with a Tree Growing Algorithm (TGA) is proposed in this paper for the simultaneous layout and pipe size determination of sewer networks. The TGA is used in an incremental manner to construct feasible tree-like layouts out of the base layout, while the ACOA is used to optimally determine the cover depths of the constructed layout. Proposed formulation is used to solve three test examples of different scales and the results are presented and compared with other existing methods. The results indicate the efficiency of the proposed method to optimally solve the problem of layout and size determination of sewer network.
Advances in Engineering Software (18735339) 51pp. 49-62
The incremental solution building capability of ant algorithm is exploited in this paper for the efficient layout and pipe size optimization of sanitary sewer network. Layout and pipe size optimization of sewer networks requires that the pipe locations, pipe diameters and pipe slopes are optimally determined. This problem is a highly constrained Mixed-Integer Nonlinear Programming (MINLP) problem presenting a challenge even to the modern heuristic search methods. In this paper, the Ant Colony Optimization Algorithm (ACOA) is equipped with a Tree Growing Algorithm (TGA) to efficiently solve the sewer network layout and size optimization problem and its performance is compared with the conventional application of the ACOA. The method is based on the assumption that a base layout including all possible links of the network is available. The TGA is used to construct feasible tree-like layouts out of the base layout defined for the sewer network, while the ACOA is used to optimally determine the pipe diameters of the constructed layout. An assumption of sewer flow at maximum allowable relative depth is made allowing for the calculation of the optimal pipe slopes in the absence of any pump and drop in the network. Two different formulations are, therefore, proposed and their performances are tested against hypothetical problems. In the first formulation, ACOA is used in a conventional manner for pipe size optimization while an ad hoc engineering concept for the layout determination. In the second formulation, however, ACOA equipped with TGA is used to simultaneously determine both the layout and pipe sizes of the network. Proposed formulations are used to solve three hypothetical test examples of different scales and the results are presented and compared. The results indicate the ability of the proposed method to optimally solve the problem of layout and size determination of sewer networks. © 2012 Elsevier Ltd. All rights reserved.
Scientia Iranica (23453605) 19(2)pp. 242-248
In this paper, the Artificial Neural Network (ANN) and the Adaptive Neuro-Fuzzy Inference System (ANFIS) are used to predict the shear strength of Reinforced Concrete (RC) beams, and the models are compared with American Concrete Institute (ACI) and Iranian Concrete Institute (ICI) empirical codes. The ANN model, with Multi-Layer Perceptron (MLP), using a Back-Propagation (BP) algorithm, is used to predict the shear strength of RC beams. Six important parameters are selected as input parameters including: concrete compressive strength, longitudinal reinforcement volume, shear span-to-depth ratio, transverse reinforcement, effective depth of the beam and beam width. The ANFIS model is also applied to a database and results are compared with the ANN model and empirical codes. The first-order Sugeno fuzzy is used because the consequent part of the Fuzzy Inference System (FIS) is linear and the parameters can be estimated by a simple least squares error method. Comparison between the models and the empirical formulas shows that the ANN model with the MLP/BP algorithm provides better prediction for shear strength. In adition, ANN and ANFIS models are more accurate than ICI and ACI empirical codes in prediction of RC beams shear strength. © 2012 Sharif University of Technology. Production and hosting by Elsevier B.V. All rights reserved.
Canadian Journal of Civil Engineering (03151468) 38(7)pp. 811-824
This paper presents an arc-based formulation of hydropower reservoir operation problems for application to ant colony optimization algorithms (ACOAs). The search space of the hydropower reservoir operation problem is defined as a partially connected graph composed of a set of arcs connecting the nodes of the graph. Each arc is defined such that it represents a local operation policy of the reservoir. The advantages offered by the proposed formulation are twofold. First, the formulation allows for a straightforward definition of heuristic information, a useful component of the ant-based algorithms, which is not present in other possible formulations of the problem. Second and more importantly, the proposed formulation paves the way for the efficient exploitation of the incremental solution-building mechanism inherent in ant algorithms to explicitly enforce problem constraints. A series of constrained formulations of the ACOA are, therefore, developed and used for the solution of single and multi-reservoir operation problems. The results indicate the ability of the proposed methods, and in particular the constrained versions, to optimally solve large-scale hydropower reservoir operation problems.
Urban Water Journal (17449006) 8(2)pp. 93-102
In this paper, an optimisation procedure is developed for calibration of the both types of hydraulic simulation models, demand driven and pressure dependent analyses, by using genetic algorithm. Variables of pipe roughness coefficient, nodal demand and pipe diameter are investigated for calibration of the hydraulic models. Four scenarios of minimum, normal, maximum and fire consumption are considered for calibration. In addition, the leakage term is incorporated into the hydraulic equations to be able to evaluate the hydraulic situation more realistically in both demand driven analysis (DDA) and pressure dependent analysis (PDA) based models. The suggested calibration procedure is applied on a test network with different consumption scenarios and variables. It is found that the best results are obtained with fire consumption case and both variables of pipe roughness and nodal demand. Leakage consideration reduces the weaknesses of the low flow scenario and also PDA produces lower error values in comparison with DDA. © 2011 Taylor & Francis.
International Journal of Electrical Power and Energy Systems (01420615) 33(2)pp. 171-178
Real-time hydropower reservoir operation is a continuous decision-making process of determining the water level of a reservoir or the volume of water released from it. The hydropower operation is usually based on operating policies and rules defined and decided upon in strategic planning. This paper presents a fuzzy rule-based model for the operation of hydropower reservoirs. The proposed fuzzy rule-based model presents a set of suitable operating rules for release from the reservoir based on ideal or target storage levels. The model operates on an 'if-then' principle, in which the 'if' is a vector of fuzzy premises and the 'then' is a vector of fuzzy consequences. In this paper, reservoir storage, inflow, and period are used as premises and the release as the consequence. The steps involved in the development of the model include, construction of membership functions for the inflow, storage and the release, formulation of fuzzy rules, implication, aggregation and defuzzification. The required knowledge bases for the formulation of the fuzzy rules is obtained form a stochastic dynamic programming (SDP) model with a steady state policy. The proposed model is applied to the hydropower operation of "Dez" reservoir in Iran and the results are presented and compared with those of the SDP model. The results indicate the ability of the method to solve hydropower reservoir operation problems. © 2010 Elsevier Inc. All rights reserved.
Scientia Iranica (23453605) 16(4 A)pp. 273-285
This paper presents an application of the Max-Min Ant System for optimal operation of reservoirs using three different formulations. Ant colony optimization algorithms are a meta-heuristic approach initially inspired by the observation that ants can find the shortest path between food sources and their nest. The basic algorithm of Ant Colony Optimization is the Ant System. Many other algorithms, such as the Max-Min Ant System, have been introduced to improve the performance of the Ant System. The first step for solving problems using ant algorithms is to define the graph of the problem under consideration. The problem graph is related to the decision variables of problems. In this paper, the problem of optimal operation of reservoirs is formulated using two different sets of decision variable, i.e. storage volumes and releases. It is also shown that the problem can be formulated in two different graph forms when the reservoir storages are taken as the decision variables, while only one graph representation is available when the releases are taken as the decision variables. The advantages and disadvantages of these formulation are discussed when an ant algorithm, such as the Max-Min Ant System, is attempted to solve the underlying problem. The proposed formulations are then used to solve the problem of water supply and the hydropower operation of the "Dez" reservoir. The results are then compared with each other and those of other methods such as the Ant Colony System, Genetic Algorithms, Honey Bee Mating Optimization and the results obtained by Lingo software. The results indicate the ability of the proposed formulation and, in particular, the third formulation to optimally solve reservoir operation problems. © Sharif University of Technology, August 2009.
Water Resources Management (09204741) 22(12)pp. 1835-1857
This paper presents a constrained formulation of the ant colony optimization algorithm (ACOA) for the optimization of large scale reservoir operation problems. ACO algorithms enjoy a unique feature namely incremental solution building capability. In ACO algorithms, each ant is required to make a decision at some points of the search space called decision points. If the constraints of the problem are of explicit type, then ants may be forced to satisfy the constraints when making decisions. This could be done via the provision of a tabu list for each ant at each decision point of the problem. This is very useful when attempting large scale optimization problem as it would lead to a considerable reduction of the search space size. Two different formulations namely partially constrained and fully constrained version of the proposed method are outlined here using Max-Min Ant System for the solution of reservoir operation problems. Two cases of simple and hydropower reservoir operation problems are considered with the storage volumes taken as the decision variables of the problems. In the partially constrained version of the algorithm, knowing the value of the storage volume at an arbitrary decision point, the continuity equation is used to provide a tabu list for the feasible options at the next decision point. The tabu list is designed such that commonly used box constraints for the release and storage volumes are simultaneously satisfied. In the second and fully constrained algorithm, the box constraints of storage volumes at each period are modified prior to the main calculation such that ants will not have any chance of making infeasible decision in the search process. The proposed methods are used to optimally solve the problem of simple and hydropower operation of "Dez" reservoir in Iran and the results are presented and compared with the conventional unconstrained ACO algorithm. The results indicate the ability of the proposed methods to optimally solve large scale reservoir operation problems where the conventional heuristic methods fail to even find a feasible solution. © Springer Science+Business Media B.V. 2008.
