Search

To accelerate the convergence rate of high-dimensional optimization problems, inspired by the cooperative hunting process of spider colonies named Anelosimus eximius, a new A. eximius colony algorithm (AECA) was proposed to solve combinatorial optimization problems. In the AECA, a certain direction component of the problem solution is represented as a certain direction in which a spider travels, so that a high-dimensional optimization problem can be transformed into multiple low-dimensional optimization problems. The AECA includes two intelligent behaviors: the random walk of spiders and the summoning of the initiator. The random walk of spiders ensures the diversity of spider colonies, whereas the summoning of the initiator can accelerate the convergence rate. We theoretically proved that the AECA is globally convergent. The inversion method of asteroid spectrum reflectance template can be used to solve the problem that the measured planetary spectrum is affected by the asteroid absorption effect and improves the accuracy of celestial Doppler difference velocimetry, which uses celestial spectrum to provide the information of velocity measurement for navigation. The essence of this method is the optimal combination problem of intrinsic mode functions (IMFs). We applied the AECA to the inversion of the planetary spectrum reflectance template. Experimental results show that, compared with genetic algorithms (GAs), the AECA can obtain the optimal combination of spectrum reflectance templates faster. In addition, to verify the universality of the AECA, for the classical knapsack problem, the AECA has a better optimization effect, faster convergence rate, and higher stability than other swarm intelligence algorithms such as GA, discrete particle swarm optimization, and the quantum genetic algorithm. [ABSTRACT FROM AUTHOR]

This paper presents a new valve positioning algorithm (VPA) for water network pressure reduction. The proposed algorithm is a graph theory-based algorithm combined with EPANET2.2 to position pressure-reducing valves (PRVs) at the most effective locations, having the most effect on downstream pressure reduction, and then calculates the setpoint for locally controlled valves. Each algorithm solution positions one valve on the edge with the highest-pressure reduction indicator calculated using the depth-first search algorithm. The setpoint is then calculated according to downstream pressure differences to the minimum service pressure to be supplied. The PRV location and setpoint found by the algorithm may be used to install and set locally controlled PRVs or serve as a guide for positioning remote-controlled PRVs. The algorithm is demonstrated on a simple example network using demand-driven analysis (DDA), pressure-driven analysis (PDA), and genetic algorithms (GA) and on a medium and a large example application (DDA). Any number of PRVs may be installed using the algorithm, which returns stable results and very short solution times while maintaining minimum service pressure requirements to the critical consumers. [ABSTRACT FROM AUTHOR]

This paper presents a coupled self-adaptive multiobjective differential evolution and network flow algorithm for the optimal operation of complex multipurpose reservoir systems. The developed algorithm (i.e., self-adaptive multiobjective differential evolution) is compared to nondominated sorting genetic algorithm II using a set of common test problems and a real-world case study. An out-of- kilter method for minimal-cost flow problems is used to optimize the water resource system from self-adaptive multiobjective differential evolution inputs driven by the evolutionary process. Self-adaptive multiobjective differential evolution is then used to evaluate objective functions based on the outputs from out-of-kilter algorithm and the process continues until the stop criterion is met. The advantages of the proposed approach include (1) flexible evolutionary algorithms for solving highly complex objective function, and (2) efficient network flow method for dealing with large and highly constrained problems. The case study includes one part of a complex water supply system located in southwestern Brazil that provides water for almost 20 million people in Sao Paulo metropolitan area. The objectives of the case study include minimization of demand shortage (the difference between demand for water and available water supply), maximization of water quality (or minimization of the deviation from the water quality standards), and minimization of pumping cost. The coupled model is applied to the case study using one inflow scenario representing a drought period with inflows below historical average. Multiobjective analyses are performed by comparing two pairs of objective functions, as follows: (1) minimization of demand shortage versus minimization of pumping cost, and (2) minimization of demand shortage versus minimization of the deviation from the water quality standards. The problem constraints include reservoir capacity, capacity of tunnels, channel flow limitations, and minimum downstream release for all reservoirs within the system. The proposed coupled model (self-adaptive multiobjective differential evolution and out-of-kilter) is outperforming both pure self-adaptive multiobjective differential evolution and nondominated sorting genetic algorithm II, as it requires significantly smaller number of generations to derive the Pareto front. In addition, the proposed approach is capable of handling larger problems without major computational burden. The coupled model and self-adaptive multiobjective differential evolution also converge closer to, and provide better coverage of the true Pareto front than, nondominated sorting genetic algorithm II. [ABSTRACT FROM AUTHOR]

An effective method for optimizing high-performance concrete mixtures can significantly benefit the construction industry. However, traditional proportioning methods are not sufficient because of their expensive costs, limitations of use, and inability to address nonlinear relationships among components and concrete properties. Consequently, this research introduces a novel genetic algorithm (GA)-based evolutionary support vector machine (GA-ESIM), which combines the K-means and chaos genetic algorithm (KCGA) with the evolutionary support vector machine inference model (ESIM). This model benefits from both complex input-output mapping in ESIM and global solutions with faster convergence characteristics in KCGA. In total, 1,030 data points from concrete strength experiments are provided to demonstrate the application of GA-ESIM. According to the results, the newly developed model successfully produces the optimal mixture with minimal prediction errors. Furthermore, a graphical user interface is utilized to assist users in performing optimization tasks. [ABSTRACT FROM AUTHOR]

Ten stochastic optimization methods-adaptive simulated annealing (ASA), covariance matrix adaptation evolution strategy (CMAES), cuckoo search (CS), dynamically dimensioned search (DDS), differential evolution (DE), genetic algorithm (GA), harmony search (HS), pattern search (PS), particle swarm optimization (PSO), and shuffled complex evolution-University of Arizona (SCE-UA)-were used to calibrate parameter sets for three hydrological models on 10 different basins. Optimization algorithm performance was compared for each of the available basin-model combinations. For each model-basin pair, 40 calibrations were run with the 10 algorithms. Results were tested for statistical significance using a multicomparison procedure based on Friedman and Kruskal-Wallis tests. A dispersion metric was used to evaluate the fitness landscape underlying the structure on each test case. The trials revealed that the dimensionality and general fitness landscape characteristics of the model calibration problem are important when considering the use of an automatic optimization method. The ASA, CMAES, and DDS algorithms were either as good as or better than the other methods for finding the lowest minimum, with ASA being consistently among the best. The SCE-UA method performs better when the model complexity is reduced, whereas the opposite is true for DDS. Convergence speed was also studied, and the same three methods (CMAES, DDS, and ASA) were shown to converge faster than the other methods. The SCE-UA method converged nearly as fast as the best methods when the model with the smallest parameter space was used but was not as worthy in the higher-dimension parameter space of the other models. Convergence speed has little impact on algorithm efficiency. The methods offering the worst performance were DE, CS, GA, HS, and PSO, although they did manage to find good local minima in some trials. However, the other available methods generally outperformed these algorithms. [ABSTRACT FROM AUTHOR]

Reservoir storage prediction is essential to the operation and management of reservoirs. In this paper, a genetic algorithm (GA)-based support vector machine (SVM) model was developed for the prediction of monthly reservoir storage of Miyun Reservoir (the only surface drinking water source for Beijing city) over the period of 1995 to 2011. At the same time, two other SVM-based models that combine grid search and particle swarm optimization methods respectively for the parameter optimization, were used for comparison. The results showed that the developed GA-SVM model had the best performance in calibration and prediction. Owing to its high accuracy, the GA-SVM model would be popularized to the prediction of reservoir storage in other regions. [ABSTRACT FROM AUTHOR]

A noncrossover dither creeping mutation-based genetic algorithm (CMBGA) for pipe network optimization has been developed and is analyzed in this paper. This CMBGA differs from the classic genetic algorithm (GA) optimization in that it does not utilize the crossover operator; instead, it only uses selection and a proposed dither creeping mutation operator. The creeping mutation rate in the proposed dither creeping mutation operator is randomly generated in a range throughout a GA run, rather than being set to a fixed value. In addition, the dither mutation rate is applied at an individual chromosome level rather than at the generation level. The dither creeping mutation probability is set to take values from a small range that is centered about (where = number of decision variables of the optimization problem being considered). This is motivated by the fact that a mutation probability of approximately previously has been demonstrated to be an effective value and is commonly used for the GA. Two case studies are used to investigate the effectiveness of the proposed CMBGA. An objective of this paper is to compare the performance of the proposed CMBGA with four other GA variants and other published results. The results show that the proposed CMBGA exhibits considerable improvement over the considered GA variants, and comparable performance with respect to other previously published results. Two big advantages of the CMBGA are its simplicity and the fact that it requires the tuning of fewer parameters compared with other GA variants. [ABSTRACT FROM AUTHOR]

A computational framework is proposed as an automated design cycle for the optimal seismic design of steel frames with self-centering connections. This paper demonstrates the approach by considering steel frames retrofitted with posttensioned energy dissipating (PTED) connections. A multiphase genetic algorithm is applied for discrete optimization to determine robust steel moment-resisting frame (MRF) designs incorporating PTED connections. Nonlinear dynamic time history finite-element analyses are employed to evaluate potential designs. For the case studies in this paper, results indicate that the performance of the MRF with optimal PTED connections exceeds that of MRFs with conventional moment-resisting connections for a specified seismic environment. This suggests that the PTED connections are a promising alternative to conventional welded moment-resisting connections in seismic regions. Furthermore, the developed computational framework is shown to provide an attractive approach for the design of MRFs with PTED connections and may be employed for the optimal design of other self-centering systems. [ABSTRACT FROM AUTHOR]

A hybrid algorithm that combines an improved genetic algorithm (GA) and the Gauss-Newton method (GNM) is proposed for the parameter estimation of the groundwater flow model. GA is capable of searching the whole finite space for nonlinear optimization problems, but it may require a large computational time and has low precision in obtaining the optimal solution. On the other hand, GNM has the advantages of a local search if its initial value is properly assigned. Using the advantages of the two methods, an improved GA is introduced to find a feasible initial solution for GNM, and afterward the global optimal solution is given by GNM. Two examples of two-dimensional (2D) and three-dimensional (3D) unsteady flow models are used to verify the stability and efficiency of the hybrid algorithm. The results demonstrate that the global solution can be found with high precision and fast convergence and that the selection criterion of the GNM for a suitable initial value is feasible. This hybrid algorithm can be applied to solve the parameter estimation of the groundwater flow model as well as other engineering optimization problems. [ABSTRACT FROM AUTHOR]

This paper presents a case study on the application of a dynamic framework for the intelligent control of flooding in the Boise River system in Idaho. This framework couples a robust and numerically efficient hydraulic routing approach with the popular multi-objective nondominated sorting genetic algorithm II (NSGA-II). The novelty of this framework is that it allows for controlled flooding when the conveyance capacity of the river system is exceeded or is about to exceed. Controlled flooding is based on weight factors assigned to each reach of the system, depending on the amount of damage that would occur, should a flood occur. For example, an urban setting would receive a higher weight factor than a rural or agricultural area. The weight factor for a reach does not need to be constant as it can be made a function of the flooding volume (or water stage) in the reach. The optimization algorithm minimizes flood damage by favoring low-weighted floodplain areas (e.g., rural areas) rather than high-weighted areas (e.g., urban areas) for the overbank flows. The proposed framework has the potential to improve water management and use of flood-prone areas in river systems, especially of those systems subjected to frequent flooding. This work is part of a long-term project that aims to develop a reservoir operation model that combines short-term objectives (e.g., flooding) and long-term objectives (e.g., hydropower, irrigation, water supply). The scope of this first paper is limited to the application of the proposed framework to flood control. Results for the Boise River system show a promising outcome in the application of this framework for flood control. [ABSTRACT FROM AUTHOR]

This paper examines a linked simulation-optimization procedure based on the combined application of an artificial neural network (ANN) and genetic algorithm (GA) with the aim of developing an efficient model for the multiobjective management of groundwater lenses in small islands. The simulation-optimization methodology is applied to a real aquifer in Kish Island of the Persian Gulf to determine the optimal groundwater-extraction while protecting the freshwater lens from seawater intrusion. The initial simulations are based on the application of SUTRA, a variable-density groundwater numerical model. The numerical model parameters are calibrated through automated parameter estimation. To make the optimization process computationally feasible, the numerical model is subsequently replaced by a trained ANN model as an approximate simulator. Even with a moderate number of input data sets based on the numerical simulations, the ANN metamodel can be efficiently trained. The ANN model is subsequently linked with GA to identify the nondominated or Pareto-optimal solutions. To provide flexibility in the implementation of the management plan, the model is built upon optimizing extraction from a number of zones instead of point-well locations. Two issues are of particular interest to the research reported in this paper are: (1) how the general idea of minimizing seawater intrusion can be effectively represented by objective functions within the framework of the simulation-optimization paradigm, and (2) the implications of applying the methodology to a real-world small-island groundwater lens. Four different models have been compared within the framework of multiobjective optimization, including (1) minimization of maximum salinity at observation wells, (2) minimization of the root mean square (RMS) change in concentrations over the planning period, (3) minimization of the arithmetic mean, and (4) minimization of the trimmed arithmetic mean of concentration in the observation wells. The latter model can provide a more effective framework to incorporate the general objective of minimizing seawater intrusion. This paper shows that integration of the latest innovative tools can provide the ability to solve complex real-world optimization problems in an effective way. [ABSTRACT FROM AUTHOR]

This paper demonstrates the application of particle swarm optimization (PSO) to the programming of pavement maintenance activities at the network level. Furthermore, the application of the PSO technique and its relevance to solving the programming problem in a pavement management system (PMS) is discussed. The robustness and quick search capability of PSO enables it to effectively handle the highly constrained problem of pavement management activities programming, which has an extremely large solution space of astronomical scale. Examples are presented to highlight the versatility of PSO in accommodating different forms of objective functions and comparing the results with the genetic algorithm (GA). This paper compares PSO and GA with respect to rate of convergence and accuracy of modeling PMS using an example problem. The results of this paper confirmed the potential of PSO to successfully model the PMS. [ABSTRACT FROM AUTHOR]

Optimal design of water distribution networks (WDN) involves an evaluation of both consumers' pressure benefits and investors' economic objectives. The aforementioned objectives often conflict, so finding the optimal solution for one of those objectives reduces the other objective's utility. In such situations, there are many nondominated solutions, each solution denoting an alternative that cannot be preferred over another in terms of both objectives. Thus, an appropriate alternative to fulfill both objectives and satisfy decision makers' criteria and meet the design purposes within a desirable range necessitates the use of bargaining models that are called conflict-resolution models. This paper considers two urban WDN optimization design problems having different objectives, including initial costs and hydraulic performance improvement of the network by satisfying given hydraulic constraints. First, a set of alternatives are drawn out by a fast messy genetic algorithm (FMGA), then the appropriate alternative design is achieved by using Nash's and Young's bargaining models. Thus, the methodology presented in this paper can be employed by designers of WDNs to simultaneously consider the utilities of both consumers and investors that are the main beneficiaries of such infrastructures. Results show that in almost all the alternatives obtained by the proposed methodology, at least 80% of the most probable utility of both beneficiaries is obtained at the same time, which indirectly indicates the low vulnerability of the design alternative by the considered methodology in meeting the goals of each beneficiary. Moreover, results also indicate that when using the same utility functions, decision points obtained from the two models coincide. [ABSTRACT FROM AUTHOR]

As a first endeavor, the differential quadrature method in conjunction with the genetic algorithms (GAs) is applied to obtain the optimum (maximum) buckling temperature of laminated composite skew plates. The material properties are assumed to be temperature dependent and the governing equations are based on the first-order shear deformation plate theory. After discretizing the governing equations and the related boundary conditions, a direct iterative method in conjunction with GAs is used to determine the optimum fiber orientation for the maximum buckling temperature. The applicability, rapid rate of convergence, and high accuracy of the method are established by solving various examples and by comparing the results with those in the existing literature. Then, the effects of the temperature dependence of the material properties, boundary conditions, length-to-thickness ratio, number of layers, and skew angle on the maximum buckling temperature of the laminated skew plates are presented. [ABSTRACT FROM AUTHOR]

A parameter identification method based on genetic algorithm (GA) is presented to solve the multimodel parameters identification problem for the main steam temperature of ultra-supercritical (USC) units. Linear ranking selection, nonuniform linear crossover, and Gaussian mutation are employed in the algorithm design to enhance the convergence speed and the accuracy of the identification. Besides, the uniform design method is executed to initialize the population and the sigmoid function with adaptation is applied to adjust the probabilities of crossover and mutation. Simulations carried out with the field operation data from Haimen USC units, including two processes-parameters identification and model verification. The simulation results show that the improved genetic algorithm performs well in global parameters searching and the proposed identification methodology offers good results for the multimodel parameters identification. [ABSTRACT FROM AUTHOR]

This paper reports the use of many-objective optimization for water distribution system (WDS) design or rehabilitation problems. The term many-objective optimization refers to optimization with four or more objectives. The increase in the number of objectives brings new challenges for both optimization and visualization. This study uses a multiobjective evolutionary algorithm termed the epsilon Nondominated Sorted Genetic Algorithm II (-NSGAII) and interactive visual analytics to reveal and explore the tradeoffs for the Anytown network problem. The many-objective formulation focuses on a suite of six objectives, as follows: (1) capital cost, (2) operating cost, (3) hydraulic failure, (4) leakage, (5) water age, and (6) fire-fighting capacity. These six objectives are optimized based on decisions related to pipe sizing, tank siting, tank sizing, and pump scheduling under five different loading conditions. Solving the many-objective formulation reveals complex tradeoffs that would not be revealed in a lower-dimensional optimization problem. Visual analytics are used to explore these complex tradeoffs and identify solutions that simultaneously improve the overall WDS performance but with reduced capital and operating costs. This paper demonstrates that a many-objective visual analytics approach has clear advantages and benefits in supporting more informed, transparent decision-making in the WDS design process. [ABSTRACT FROM AUTHOR]

This work proposed a model for transit schedule design by integrating the spatial-equity considerations into the slack-time setting problem. The proposed model can help to design a transit service for more equitable reliability of all stops distributed along the route. The transit operators' risk taking attitudes are also taken into consideration by introducing the travel-time budget (TTB) and mean-excess travel time (METT) as two risk measures. The proposed model can be formulated as a stochastic optimization problem and solved by a subsequently designed Monte Carlo (MC) simulation based genetic algorithm (GA) procedure. Scenario-based numerical examples from a real bus route in Beijing city of China are presented to demonstrate the characteristics of the model. The sensitivity of the parameters setting are also taken into consideration as well, which reflects the impact on the schedule setting of various factors including actual travel-time variability, risk-taking attitudes of transit operators, the bus drivers' adjustment, and bus-frequency setting. [ABSTRACT FROM AUTHOR]

Selecting approaches to managing nonpoint source pollution is challenging due to the complex generation and transport processes that influence the quantity of pollutant that eventually reaches a receiving water. Pollutant transport is influenced by land surface characteristics along the transport path, and these effects should be considered when optimizing management approaches for nonpoint source pollution. A fully distributed sediment-generation and transport watershed model is presented within an optimization framework to enable the development of spatially precise solutions to sediment-trapping best management practice (BMP) placement at the watershed scale. To focus on the BMP-siting problem, a stylized representation of a BMP is assumed to be capable of reducing sediment mass by a fixed fraction, and optimal arrangements of this assumed BMP type are developed with a genetic algorithm. The results suggest that the optimal location for sediment mass reduction is not necessarily at locations of only high mass generation or at locations of only high transport capacity. The results also suggest that there are efficient locations for management that produce a relatively large reduction in storm sediment load. [ABSTRACT FROM AUTHOR]

The purpose of this research is to investigate the capability of a real genetic algorithm (GA) to remove a heavy-metal pollutant plume from an aquifer. The real genetic algorithm has been used in conjunction with proven and accepted finite-difference analysis to reach an efficient solution. It also illustrates the interaction between the real GA optimizer and the finite-difference technique. Two scenarios regarding the well positions, number of wells, pumping rate at each well, and total cost were determined for the purpose. A new system has been developed for removing heavy metals [mercury (Hg) and cadmium (Cd)] from groundwater in a real problem and proved to be optimal. Real-coding GAs proved to be a practical means of optimizing engineering solutions to problems related to groundwater quality management, in particular those involving discontinuous functions. The real GA can be used with accredited finite-difference methods toward an optimal solution. The developed application of a combined simulation-optimization method for cleanup of contamination from a real landfill in a coastal area of Syria can also be used in other water-resource quality applications. [ABSTRACT FROM AUTHOR]

Line-of-balance (LOB) methodology produces a work schedule in which resource allocation is automatically performed to provide a continuous and uninterrupted use of resources, but the distribution of resources could be further improved by resource leveling even if multiple resources are involved. The objective of this study is to develop a genetic algorithm (GA)-based multiresource leveling model for schedules that are established by LOB. The proposed model postulates that the production rate and duration of an activity are governed by the resource that requires the longest duration in completing a unit. Once the LOB schedule is established, resource leveling is performed according to the principle of optimum crew size that makes use of a utility data curve, which shows that productivity will suffer if the crew size is different than the optimum crew size, and the principle of natural rhythm that allows shifting the start times of an activity forward or backward at different units of production by changing the number of crews employed. The duration of an activity in any one unit and the precedence relationships between activities do not change during the leveling procedure. When applied to the LOB schedule of a pipeline project that was used to illustrate the model, it was observed that the proposed multiresource leveling model provided a smoother resource utilization histogram while maintaining optimum productivity. [ABSTRACT FROM AUTHOR]

The light weight deflectometer (LWD) is a portable, nondestructive testing device that can estimate pavement layer parameters, namely moduli. Conventional backcalculation of layer parameters from LWD deflections is formulated as an inverse problem where predicted vertical deflections are matched to observed vertical deflections using a gradient search algorithm. In this paper, we present an LWD backcalculation scheme to recover layer parameters, including top-layer thickness, of a two-layer earthwork system. Our approach resolves the problem using a dynamic finite-element (FE) model for the forward calculation of LWD deflection data and implements a genetic algorithm (GA) as the inverse solver. The objective function we minimize is formulated as a measure of the data misfit between predicted and observed data, normalized by the peak deflections, and it includes 180 data points from the dynamic deflection time history. The objective function contains multiple local minima that can potentially trap gradient search algorithms, thus validating application of GA as a global search technique for this problem. The GA is applied to both synthetic and experimental data, and we demonstrate that the recovered top-layer thickness, top-layer modulus, and underlying modulus for the experimental data compare favorably with expected values. [ABSTRACT FROM AUTHOR]

Civil infrastructure assets require continuous renewal actions to modernize inventory and sustain operability. However, allocating limited renewal funds among numerous asset components represents a complex optimization problem. Earlier efforts using genetic algorithms (GAs) optimized medium-sized problems, yet exhibited steep performance degradation as problem size increased. In this research, data compression is first used to cluster and abstract the large data of a network-level problem. Optimizing compressed models, however, did not result in high quality solutions. To address large size problems, a GA with segmentation approach was introduced. Segmentation breaks down a large-scale network-level problem into segments, allocates budget based on the relative criticality of the segment, and combines the results of all segment optimizations. The proposed GA with segmentation mechanism has been tested on different sized problems and was able to optimize very large problems with no performance degradation. The proposed GA with segmentation method is simple and logical; furthermore, it can be used on variety of asset types to improve fund allocation for infrastructure renewal. [ABSTRACT FROM AUTHOR]

Currently, the genetic algorithm (GA) technique has been used in finance-based scheduling to devise critical path method (CPM) schedules exhibiting cash flows of periodical finance needs below preset cash constraints. The chromosomes of the schedules that violate this condition are referred to as finance-infeasible chromosomes. Infeasibility related to finance is peculiar to finance-based scheduling problems. In scheduling problems, chromosomes that are infeasible based on precedence relationships are typically penalized. This paper introduces a repair algorithm for the finance-infeasible chromosomes generated within the GA systems. The repair algorithm identifies the periods exhibiting finance needs that exceed the constrained cash, calculates the amounts of finance needs above the constraints, identifies the ongoing activities, selects randomly an activity for delaying its start time, determines the impact of the delay on the finance needs, and repeats the procedure until finance feasibility is attained. A 13-activity project was used to demonstrate the proposed repair algorithm. The performance of the repaired-chromosome GA system is evaluated through comparison against replaced-chromosome and penalized-chromosome GA systems using a fairly big project of 210 activities. Finally, the results that were validated using the integer programming technique proved the superior performance of the repaired-chromosome GA in terms of the computational cost and quality of solutions. [ABSTRACT FROM AUTHOR]

Multicropping is the practice of growing two or more crops in the same space during a single growing season. Planning rules are mathematical equations that use previous experiences of a water resource system to balance the system's water supply and demand, and calculate multicrop areas in various periods. In this paper, linear and nonlinear planning rules are developed for optimal multicrop irrigation areas associated with reservoir operation policies in a reservoir-irrigation system. Reservoir operations are related to water allocations to each irrigated area by considering inflow and storage volume of the reservoir as the water supply in a monthly operation period. Evolutionary algorithms (EAs) can determine optimal multicropping patterns planning rules by considering various mathematical patterns. In this paper, three EAs, namely, (1) genetic algorithm (GA), (2) particle swarm optimization (PSO), and (3) shuffled frog leaping algorithm (SFLA) are employed and compared to maximize the total net benefit of the water resource system by supplying irrigation water for a proposed multicropping pattern over the planning horizon. Results show that the SFLA achieves the best solution, with the maximum value of the objective function in both linear and nonlinear planning rules compared to the GA and PSO. Moreover, the best yield of nonlinear rules is 45.52% better (higher) than that obtained by linear rules. [ABSTRACT FROM AUTHOR]

Streams and their associated biological communities are among our most valuable natural resources. Humans rely on the environmental services provided by streams in a myriad of ways. However, in some areas, excessive groundwater pumping exacerbates the already critical pressure on streamflow and must be managed through effective planning. Based on economic and hydrogeological concepts, this study estimates the quantity of streamflow depletion that is attributable to groundwater pumping and the negative impact on the socioeconomic system if groundwater pumping must be constrained to restore streamflow. The primary objective of this paper is to develop a multiobjective nonlinear optimization model to simulate the tradeoffs between streamflow restoration and economic welfare loss in a Chicago suburban county, McHenry County. The multiobjective optimization was conducted at both county and municipality levels. An evolutionary algorithm, the nondominated sorting genetic algorithm, was used to solve the optimization model and to identify the tradeoff curve (Pareto frontier). Comparing municipal Pareto frontiers shows spatially heterogeneous costs of preserving streamflow through various shadow prices and also the different capacities of restoring streamflow. The results include discussion of the shapes of the Pareto frontier, the sensitivity of the pumping boundary constraints, and return flow coefficients. It is concluded that the multiobjective optimization model provides a useful framework to consider conflicting objectives in a typical environmental management and planning process, and that the findings can help decision-makers and planners to formulate effective groundwater pumping strategies. [ABSTRACT FROM AUTHOR]

This work presents a postoptimization methodology for refining the solutions found by adaptive search algorithms used in the design of large water distribution networks. The approach uses two heuristics to search for an optimal combination of pipes that, after a reduction of their diameters, will maximize cost savings while continuing to meet design constraints. Adaptive search methods are often used to design urban water distribution networks when the number of pipes in the network is insignificant. For complex, real-world networks, however, such methods are computationally demanding, and they have difficulty finding near-global optima. To identify a solution as close to the global optimum (and in which no pipe can be reduced without violating pressure constraint), requires a high-speed computer potentially running for a long time and also probably some good fortune. The postoptimization approach presented in this paper is shown to be an efficient complement to heuristic search algorithms used in the design of real-world networks. In a network created with the aid of a genetic algorithm, the proposed heuristics found that 4.37% of the pipes with a diameter greater than the minimum could be further reduced without causing hydraulic failure. [ABSTRACT FROM AUTHOR]

A hierarchical optimization method is presented for an assessment of the potential maximum energy output of the Three Gorges Project and Gezhouba cascade hydropower stations in China. The optimization incorporates a detailed description of daily load dispatching among different types of hydropower units. The optimization method is divided into three levels to render feasible the computation of the global optimization problem. In levels 1 and 2, a genetic algorithm is applied to optimize discharge and water head distribution between the upstream and downstream reservoirs. Level 1 selects the water levels at the beginning of each month in a year. Level 2 selects the water levels at the beginning of each day in a month. Level 3 solves a linear programming problem for allocation of water among the heterogeneous types of hydropower generation. Hydrological data of the years 2004 and 2005 are used to perform an optimized power generation process within the operating rules. The maximal annual energy production could be approximately 61 and 87 MWh higher than the actual recorded energy production in 2004 and 2005, respectively. [ABSTRACT FROM AUTHOR]

The allocation of water resources has long been recognized as a critical optimization problem. In this study, a bilevel programming model with fuzzy random variables is developed for tackling a regional water resources allocation problem on the basis of water rights distribution in a river basin. The bilevel programming model takes the optimal total benefit of the society and the optimal economic benefit of each subarea as the upper and lower targets, respectively. In contrast to previous studies, the balance of the satisfactory degree between the upper and lower decision makers is considered in the bilevel optimization for ensuring the equity of the water resource allocation. To deal with inherent uncertainties, the fuzzy random variables are first transformed into trapezoidal fuzzy numbers, and by taking advantage of the expected value operation, the trapezoidal fuzzy numbers are subsequently defuzzified. For solving the complex and nonlinear bilevel programming model, an interactive fuzzy programming technique and an entropy-Boltzmann selection-based genetic algorithm are designed as a combined solution method. Finally, the results and comparisons analysis of a case study are presented to demonstrate the practicality and efficiency of the optimization method. [ABSTRACT FROM AUTHOR]

The process of urbanization transforms natural landscape into impervious land cover, affecting the ecosystem health of receiving water bodies and downstream communities by changing the timing and volumes of the natural flow regime. Best management practices (BMP) and low impact development (LID) are a set of mitigating measures that can be considered for watershed management to mitigate the hydrologic consequences of urbanization. This research develops a methodology to select sites for placing LID technologies, namely rainwater harvesting and permeable pavements, to reduce hydrologic impacts, measured as alterations to the peak flow while meeting a prespecified budget. A simulation-optimization methodology couples a genetic algorithm with a hydrologic model, a hydraulic model, and curve number-based models of LID technologies. The trade-off between costs and peak flow alteration is explored by optimizing LID placement under varying budget constraints. Strategies that combine a detention pond and LID are explored and optimized for a spectrum of design storms, including 2-, 10-, and 100-year events. Trade-offs among management strategies that are designed to control storms of different sizes are analyzed. The simulation-optimization framework and methodology is applied for a small watershed on the Texas A&M University campus. [ABSTRACT FROM AUTHOR]

Flow diversion head works are constructed across rivers to divert flow into irrigation, navigation, or power generation channels. Hydraulic structures, such as weirs or barrages, are integral parts of these diversion head works. The optimal design of these hydraulic structures is generally obtained by considering the deterministic values of hydrogeological parameters. However, there is a high degree of local soil variability and imprecision in the determination of soil parameters, such as the safe exit gradient. The seepage head also exhibits a high degree of variability, depending on complex hydrological and metrological factors. This work considers the hydrogeological parameters safe exit gradient and seepage head as imprecise or uncertain. An optimization-based methodology is presented to incorporate uncertainty in the safe exit gradient and seepage head in the optimization formulation and obtain the optimum structural dimensions that minimize the total cost. The subsurface flow consideration is embedded in the optimization formulation. The nonlinear optimization formulation (NLOF) solution procedure using a genetic algorithm (GA) is implemented to demonstrate the characterization of uncertainty in design and hence, overall cost from the uncertain safe exit gradient and seepage head. The limited evaluation shows the potential applicability of the proposed methodology. [ABSTRACT FROM AUTHOR]

This paper presents a resource sharing-based construction equipment allocation problem with multiple stages under a fuzzy environment. A multiobjective multistage decision-making model is established in which the equipment failure rate is regarded as a fuzzy variable. In contrast to traditional assignment problems, the principle of resource sharing modes including space and time sharing is considered to be based on the project practice. In addition, a dynamic programming-based genetic algorithm is developed to find feasible solutions and a dynamic programming-based initialization, and crossover and mutation are designed to avoid infeasible solutions. Finally, the Jinping-I Hydropower Project is used as a practical example to demonstrate the practicality and efficiency of the model. The comparisons and analysis of results are presented to highlight the performance of the optimization method, which is proved to be more effective and efficient than the standard genetic algorithm. [ABSTRACT FROM AUTHOR]

In modem civilization, water distribution network has a substantial role in preserving the desired living standard. It has different components such as pipe, pump, and control valve to convey water from the supply source to the consumer withdrawal points. Among these elements, optimal sizing of pipes has great importance because more than 70% of the project cost is incurred on it. Unfortunately, optimal pipe sizing falls in the category of nonlinear polynomial time hard (NP-hard) problems. Hence, solid research activities march on because of two facts, namely, importance and complexity of the problem. The literature revealed that the stochastic optimization algorithms are successful in exploring the combination of least-cost pipe diameters from the commercially available discrete diameter set, but with the expense of significant computational effort. The hybrid model PSO-GA, presented in this paper aimed to effectively utilize local and global search capabilities of particle swarm optimization (PSO) and genetic algorithm (GA), respectively, to reduce the computational burden. The analyses on different water distribution networks uncover that the proposed hybrid model is capable of exploring the optimal combination of pipe diameters with minimal computational effort. [ABSTRACT FROM AUTHOR]

This paper presents a procedure to identify the damage of multistory shear structure from sparse modal information. Practically, it is difficult and expensive to measure modal response at many locations. A method has been proposed to compute the full modal information of a particular mode simply by knowing the frequency value of that mode. Then the concept of the residual force vector along with genetic algorithm has been implemented to get the location and extent of damage. Frequencies at different number of modes with and without corresponding partial mode shape is used as input to the model and results are compared to find out minimum number of modal information and their locations required for the best result. Experimental data are simulated numerically by solving eigen value problem of the damaged structure with inclusion of random noise on the vibration characteristics. Reliability of the procedure has been shown by various examples of multistory structure with different damaged situations. The model is also validated with some published results in this area to show the efficacy of the methodology. [ABSTRACT FROM AUTHOR]

The increased interest in the development and application of large-scale or regional microsimulation transportation models has brought to the forefront the challenges associated with estimating the dynamic demand information needed to run such models. This paper develops a computational-based approach for estimating or adjusting dynamic origin-destination matrices for regional microsimulation models on the basis of hourly traffic counts. The proposed approach, while based on genetic algorithms (GA), includes a special module, called Plan Analyzer, to guide the search process in an intelligent way. This results in a customized algorithm for the problem that can be regarded as an example of a guided genetic algorithm (GGA). To cut down on execution time, a distributed implementation of the algorithm is adopted, and several software design procedures are developed to deal with the demanding memory requirements of the problem. To demonstrate the effectiveness of the algorithm, the Transportation Analysis and Simulation System (TRANSIMS) model, a microsimulation platform designed for regional simulations, is used to model two test networks, a synthetic grid network and a realistic regional model of Chittenden County, Vermont. The GGA is then utilized to estimate the dynamic demand for those two models on the basis of hourly traffic count information. The results clearly demonstrate the effectiveness of the GGA in dramatically reducing the average absolute error (AAE) between the simulated and field counts, and in closely estimating the 'true' demand, which was known in this research by virtue of how the case studies were designed. The results also show that the developed GGA significantly outperforms standard GAs. [ABSTRACT FROM AUTHOR]

The fast-track method is one of the most recognized methodologies for reducing construction project schedules. However, due to the lack of definitive research to date pertaining to the effects of fast-track application in terms of time and cost, it has been difficult for project owners to determine its correct application. This paper presents the time and cost optimized decision support (TACTICS) model, and it was developed based on the fast-track methodology and genetic algorithms (GAs). TACTICS was applied to two case studies, and the results indicated that the fast-track method could be expected to deliver more efficient projects compared with using the traditional method. In particular, (1) the average reduction in project duration by applying the fast-track method was 40.48% (Case I) and 18.59% (Case II) compared with using the traditional method, and (2) the average project costs were reduced by as much as 0.39% (Case I) and 4.48% (Case II). Consequently, TACTICS could be expected to help in making a decision regarding the fast-track application and further contribute to the project scheduling expertise in the construction engineering and management body of knowledge. [ABSTRACT FROM AUTHOR]

An integrated hydrological well field model (WELLNES) that predicts the water level and energy consumption in the production wells of a waterworks is used to optimize the management of a waterworks with the speed of the pumps as decision variables. The two-objective optimization problem of minimizing the risk of contamination from a nearby contaminated site and minimizing the energy consumption of the waterworks is solved by genetic algorithms. In comparison with historical values, significant improvements in both objectives can be obtained. If the existing on/off pumps are changed to new variable-speed pumps, it is possible to save 42% of the specific energy consumption and at the same time improve the risk objective function. The payback period of investing in new variable speed pumps is only 3.1 years, due to the large savings in electricity. The case study illustrates the efficiency and applicability of the developed modeling framework. [ABSTRACT FROM AUTHOR]

Bus priority strategy has widely been recognized as an effective countermeasure in the practical field of urban traffic congestion mitigation. This study proposes a bi-level programming model to comprehensively analyze the combinational optimization problem of exclusive bus lanes (EBLs) with variable bus frequencies (BFs) in multi-modal transportation networks. The objective function is to minimize the sum of the road users' travel costs and the transit operating costs. The upper level model is an optimal decision-making program for setting up EBLs and BFs, and the lower level is a multi-modal transportation network equilibrium model. An efficient genetic algorithm is designed to solve the problem. The results of the numerical analysis show that the combinatorial optimization scheme of EBLs and BFs performs well with regard to the objective function in the model. The outperformance of combinatorial optimization scheme becomes greater with increased traffic demand, whereas oversetting of EBLs can result in reduced operating efficiency of the transportation system. [ABSTRACT FROM AUTHOR]

The simulation of U-turns is currently of great interest to many transportation professionals due to the widespread use of indirect driveway left-turn treatments. In this study, a procedure was proposed to help transportation professionals model U-turn movements at unsignalized intersections with nontraversable median cross sections in the traffic simulation program VISSIM. The behavioral features of U-turning drivers, such as the priority rule, lane selection, and turning speed of U-turns, were determined using data collected from 13 different locations. A procedure based on a genetic algorithm was proposed to calibrate and validate the VISSIM simulation model. The simulation results of the calibrated VISSIM model were compared to field measured capacity and to the capacity estimated using gap acceptance models developed in previous studies. The calibrated VISSIM simulation model yields mean absolute percent errors of 17.6 and 20.7% for four-lane and six-lane streets, respectively. The results show that VISSIM provides reasonable capacity estimates for U-turns at unsignalized intersections with raised median cross sections, after crucial parameters are properly defined and calibrated. [ABSTRACT FROM AUTHOR]

Designing baseline or vertical alignment in railways greatly depends on the designer's experience. An inaccurate design imposes unreasonable costs during construction and operations. This paper presents a program to find the best vertical alignment for a track with a given horizontal layout. First, the vertical alignment is formulated using mathematical equations, and then an algorithm is developed to produce its geometric configuration. Construction and operating costs, which are sensitive to gradient changes, are expressed as vertical alignment variables and included in the model. A direct search method is employed to solve the objective function, and a genetic algorithm encodes solution algorithms in a program, whereas certain heuristic operators are utilized to cover operational situations. The program also provides railway engineers and planners with practical information on the resulting alignment such as time and speed graph, total traction force, and block capacity. Moreover, the model is evaluated using a real example to verify the algorithms' ability to find the optimal alignment. [ABSTRACT FROM AUTHOR]

This study introduces a new search method for box-constrained optimization problems called the search method for box optimization (SMBO). SMBO is a population heuristic-based search methodology that solves global optimization problems. SMBO represents the population as a probability density function (PDF) inside the problem bounds. The PDF shape is dynamically adapted during the process to guide to a 'good' search domain. The applicability and the efficiency of the method are demonstrated using two benchmark sets, which include unimodal, multimodal, expanded, and hybrid composition functions. The performance of SMBO is compared with several genetic algorithms (GAs); the first benchmark compares it with nine codes of traditional/classic GAs, and the second compares SMBO with two recent variants of genetic algorithms. The results show that SMBO performs as well as or better than the GAs in both comparisons. The method is demonstrated on a nonlinear model for management of a water supply system (WSS), and the results are compared with the commercial GA toolbox of matrix laboratory (MATLAB). [ABSTRACT FROM AUTHOR]

In a highway asset maintenance management system involving more than one highway asset type, identifying an equitable optimal allocation of available budget to individual asset systems is a major challenge. This is because the following outcomes are desirable: (1) the maintenance needs of all assets are adequately addressed, (2) the objectives of individual asset systems are optimally satisfied in an equitable manner, and (3) the objectives of the overall highway asset system are achieved optimally. To achieve these desirable outcomes, this paper proposes a two-stage approach in solving the dual-level multiasset, multiobjective pavement network maintenance optimal budget allocation problem. Stage I of the approach analyzes the individual multiobjective asset systems independently to establish for each a family of optimal Pareto solutions. Minimization of maintenance cost is selected as a common objective for the individual asset systems. This serves as the link for interaction with the Stage II analysis. Stage II adopts an optimal algorithm to allocate budget to individual assets by performing a cross-asset trade-off to achieve the optimal budget solution for the given overall system-level objectives. By defining a minimum performance threshold level for each asset type, the Stage II optimization analysis aims to achieve an equitable allocation of budget by maintaining equivalent amounts of performance improvements for the individual asset systems above their respective minimum threshold levels. The conceptual framework of the proposed approach is presented in this paper with a numerical example to illustrate the detailed working of the procedure. [ABSTRACT FROM AUTHOR]

Concrete beams reinforced with glass-fiber reinforced polymer (GFRP) bars exhibit large deflections in comparison with steel-reinforced concrete beams because of the low modulus of elasticity of GFRP bars. This paper proposes new equations for estimating the effective moment of inertia of FRP-reinforced concrete beams on the basis of the genetic algorithm and experimental results. Genetic algorithm is used to optimize the error function between experimental and analytical responses. In the experimental part of the study, nine beam specimens were manufactured and tested. In addition, the results of 55 beam specimens tested by other researchers were also used. The effects of elastic modulus of FRP bars, reinforcement ratio, and the level of loading on the effective moment of inertia are taken into account. The proposed equations are compared with different code provisions and previous models for predicting the deflection of FRP-reinforced concrete beams. The values calculated using the proposed equations are also compared with different test results. The experimental results correlated well with the values predicted using the proposed equations, especially in the cases of high reinforcement ratios and high levels of loading. [ABSTRACT FROM AUTHOR]

Facility layout design (FLD) presents a particularly interesting area of study because of its relatively high level of attention to aesthetics and usability qualities, in addition to common engineering objectives such as cost and performance. However, FLD present a difficult combinatorial optimization problem for engineers. Swarm intelligence (SI), an approach to decision making that integrates collective social behavior models such as the bee algorithm (BA) and particle swarm optimization, is being increasingly used to resolve various complex optimization problems. This study proposes a new optimization hybrid swarm algorithm, the particle bee algorithm (PBA), which imitates the intelligent swarming behavior of honeybees and birds. This study also proposes a neighborhood-windows (NW) technique for improving searching efficiency and a self-parameter-updating (SPU) technique for preventing trapping into a local optimum in high-dimensional problems. This study compares the performance of PBA with that of genetic algorithm (GA), differential evolution (DE), bee algorithm, and particle swarm optimization for multidimensional benchmark function problems. Additionally, this study compares PBA performance against bee algorithm and particle swarm optimization (PSO) performance in practical FLD problems. Results show that PBA performance is comparable to those of the mentioned algorithms in the benchmark functions and can be efficiently employed to solve practical FLD problem with high dimensionality. [ABSTRACT FROM AUTHOR]

Flow diversion head works are constructed across rivers to divert flow into irrigation, navigation, or power generation channels. Hydraulic structures, such as weirs or barrages, are integral parts of these diversion head works. The optimal design of these hydraulic structures is generally obtained by considering the deterministic values of hydrogeological parameters. However, there is a high degree of local soil variability and imprecision in the determination of soil parameters, such as the safe exit gradient. The seepage head also exhibits a high degree of variability, depending on complex hydrological and metrological factors. This work considers the hydrogeological parameters safe exit gradient and seepage head as imprecise or uncertain. An optimization-based methodology is presented to incorporate uncertainty in the safe exit gradient and seepage head in the optimization formulation and obtain the optimum structural dimensions that minimize the total cost. The subsurface flow consideration is embedded in the optimization formulation. The nonlinear optimization formulation (NLOF) solution procedure using a genetic algorithm (GA) is implemented to demonstrate the characterization of uncertainty in design and hence, overall cost from the uncertain safe exit gradient and seepage head. The limited evaluation shows the potential applicability of the proposed methodology. [ABSTRACT FROM AUTHOR]

Although advanced technologies, such as detection techniques and controllers, have been incorporated within Advanced Traffic Management Systems (ATMS), pretimed signal control still plays an important role in traffic control and management. A wide variety of techniques were proposed to generate optimal or near-optimal solutions for signal optimization problems. However, only a limited research was devoted to the application of tabu search in the signal optimization problem. The characteristics of tabu search could provide accuracy and efficiency with the careful design of local search methods. This research applies a randomized meta-heuristic algorithm, greedy randomized tabu search (GRTS), for network-level signal optimization problems. With the flexibility of the GRTS, detailed representations of signal control settings could be added easily. To compare the performance of GRTS with other algorithms, genetic algorithm (GA) is chosen and implemented. The performance of the GRTS is investigated in numerical analysis in two networks, including a test network and a real city network. Numerical experiments on the test network are used in the comparison of the GA and GRTS algorithms. Numerical experiments on the real city network are conducted to illustrate possible benefits from the proposed approach. The results show that more than 25% reduction of travel time can be achieved for medium and high demand levels. [ABSTRACT FROM AUTHOR]

The fast-track method is one of the most recognized methodologies for reducing construction project schedules. However, due to the lack of definitive research to date pertaining to the effects of fast-track application in terms of time and cost, it has been difficult for project owners to determine its correct application. This paper presents the time and cost optimized decision support (TACTICS) model, and it was developed based on the fast-track methodology and genetic algorithms (GAs). TACTICS was applied to two case studies, and the results indicated that the fast-track method could be expected to deliver more efficient projects compared with using the traditional method. In particular, (1) the average reduction in project duration by applying the fast-track method was 40.48% (Case I) and 18.59% (Case II) compared with using the traditional method, and (2) the average project costs were reduced by as much as 0.39% (Case I) and 4.48% (Case II). Consequently, TACTICS could be expected to help in making a decision regarding the fast-track application and further contribute to the project scheduling expertise in the construction engineering and management body of knowledge. [ABSTRACT FROM AUTHOR]

This paper proposes a modified genetic algorithm (GA) for optimization of water distribution systems. A method of dynamically expanding the pipe-choice-table selections and reducing the number of decision variables is introduced, which occurs during a GA run. On the basis of the progressive selection, an initially reduced choice table for each decision variable is allowed to dynamically expand, and then the number of decision variables is gradually reduced. This process enables the GA search to concentrate on promising regions of the search space. The dynamically expanding choice-table genetic algorithm (GADECT) has been applied to a benchmark case study, the New York Tunnels Problem. The results obtained show that the GADECT yields a superior performance in terms of solution quality and computational efficiency. [ABSTRACT FROM AUTHOR]

A generalized genetic algorithm has been developed to find the global optimal reinforcement contents for a concrete solid structure subjected to a general three-dimensional (3D) stress field. Feasible solutions were examined based on the genetic algorithm, and the heterogeneous strategy used ensures that all of the local optimal regions are searched and the most optimal reinforcement content found. The effectiveness of the proposed approach has been validated by comparing the steel contents evaluated using the present method with those obtained from other available methods. A more economic design is achieved by the proposed algorithm. The method developed provides the designer with a valuable tool for the determination of reinforcements in complicated solid concrete structures. [ABSTRACT FROM AUTHOR]

Computational cost is a critical issue for large-scale water-resource optimization under uncertainty, since time-intensive Monte Carlo simulations are often required to evaluate over multiple parameter realizations. This paper presents an efficient approach for replacing most Monte Carlo simulations with surrogate models within a noisy genetic algorithm (GA). The surrogates are trained to predict the posterior expectations online on the basis of stochastic decision theory, using Monte Carlo simulation results created during the GA run. The surrogates, which in this application are neural networks, are adaptively updated to improve their prediction performance as the search progresses. A Latin hypercube sampling method is used to efficiently sample parameters for the Monte Carlo simulation, and the sampling results are archived so that the estimate of posterior expectation can be iteratively improved in an efficient manner. In addition, the GA is modified to incorporate hypothesis tests in its selection operator to account for sampling noise. The method is applied to a field-scale groundwater remediation design case study, whereas the primary source of uncertainty stems from hydraulic conductivity values in the aquifers. The results show that the method identified more reliable and cost-effective solutions with 86-90% less computational effort than the purely physically based noisy GA approach. [ABSTRACT FROM AUTHOR]

An accuracy-based learning classifier system (XCS), as described in a companion paper (Part I: Design), was developed and evaluated to produce operational rules for canal gate structures. The XCS was applied together with a genetic algorithm and an unsteady hydraulic simulation model, which was used to predict responses to gate operation rules. In the tested cases, from 100 to 2,000 XCS simulations, each involving thousands of hydraulic simulations, were required to produce satisfactory rules. However, the overall fitness of the set of rules increased monotonically as XCS simulations progressed. Initial fitness started at an arbitrary value, and rules increased in strength by better achieving operational objectives during the training process. Fewer XCS iterations were required to increase the fitness as the rule population evolved. Calculated water depths approached the respective target depths for variable water delivery demand through turnout structures in the simulated canal systems. The water depth achieved stabilization inside a dead band of ± 8% of the target depth after applying different turnout demand hydrographs to each reach. The calculated depth was inside the dead band 92% of the time in Reach 1, and 73% of the time in Reach 2 for the constant supply experiment. The water depth was inside the dead band 100% of the time in Reach 1, and 76% of the time in Reach 2 for the variable-supply experiment. [ABSTRACT FROM AUTHOR]