Suitable Optimization Method Research Articles

Enhancement of bioethanol production by a waste biomass-based adsorbent from enzymatic hydrolysis

Alkaline pretreatment is an efficient method to destroy the lignocellulose structure of rice straw for bioethanol production. This process generates various toxic compounds, such as ferulic acid, which could inhibit bioethanol production. In this study, a waste biomass-based adsorbent from the enzymatic hydrolysis of rice straw (AEPA250) was used for ferulic acid detoxification in the alkali-pretreated hydrolysate. The AEPA250 detoxification process was first optimized by response surface methodology to increase ferulic acid removal, while reducing glucose loss. This optimization of detoxification resulted in 99.268% ferulic acid removal coupled with 3.028% glucose loss. The fermentation processing parameters and bioethanol production for different fermentation systems were evaluated after adopting the optimal AEPA250 detoxification conditions to select the most suitable optimization method. The result revealed that optimized detoxified fermentation with AEPA250 filtration (ODF) system was more suitable for bioethanol production than optimized detoxified fermentation containing AEPA250 (ODFA) system followed by non-detoxified fermentation (NDF) system. A logistic model was applied to further compare the yeast growth kinetics of the ODF and NDF systems. The ODF system had a maximum specific growth rate (μmax) of 0.532 h−1, indicating that the ODF system possessed greater bioethanol fermentation potential. Metabonomics and transcriptomics analyses were used to identify differentially expressed metabolites and functional genes that contribute to detoxification by the ODF system. AEPA250 was produced by the enzymatic hydrolysis of biomass waste of rice straw in the bioethanol production process, and a self-sufficient bioethanol production system could be established by in-situ AEPA250 detoxification using the ODF system. These results pave the way for the realization of a cleaner bioethanol production process by reducing environmental waste production, exogenous adsorbent use, and the cost of enzymatic hydrolysis residue treatment.

A Kriging-Assisted Multi-Objective Constrained Global Optimization Method for Expensive Black-Box Functions

The kriging optimization method that can only obtain one sampling point per cycle has encountered a bottleneck in practical engineering applications. How to find a suitable optimization method to generate multiple sampling points at a time while improving the accuracy of convergence and reducing the number of expensive evaluations has been a wide concern. For this reason, a kriging-assisted multi-objective constrained global optimization (KMCGO) method has been proposed. The sample data obtained from the expensive function evaluation is first used to construct or update the kriging model in each cycle. Then, kriging-based estimated target, RMSE (root mean square error), and feasibility probability are used to form three objectives, which are optimized to generate the Pareto frontier set through multi-objective optimization. Finally, the sample data from the Pareto frontier set is further screened to obtain more promising and valuable sampling points. The test results of five benchmark functions, four design problems, and a fuel economy simulation optimization prove the effectiveness of the proposed algorithm.

An Optimal Allocation Method of Power Multimodal Network Resources Based on NSGA‐II

Basic services for power business were provided by the power multimodel network providers. However, because the power multimodal network is usually complex and changeable, the service of power business is often unstable. This problem can be solved by a suitable network resource optimization method. Therefore, how to design a network resource optimization method that seeks a compromise between multiple performance indicators that achieve the normal operation of power multimode networks is still extremely challenging. An optimal allocation method of power multimodal network resources based on NSGA‐II was proposed by this paper. Firstly, the power multimodal network‐resource model is established, and the problems existing in the resource optimization process are analyzed. Secondly, preprocessing technology and indirect coding technology are applied to NSGA‐II, which solves the coding problem and convergence problem of the application of genetic algorithm to the optimization of network resource allocation. Finally, the simulation results show that, compared with the control algorithm, this method has further optimized the various indicators of the resource allocation of the power multimodal network, and the performance has been improved by more than 6%.

Hull geometry optimisation of wave energy converters: On the choice of the optimisation algorithm and the geometry definition

It is key in the development of wave energy systems to aim at designing economically competitive solutions that enable maximal annual energy production. Previous studies identify the Wave Energy Converter (WEC) structure, i.e. the hull, to have one of the largest cost reduction potentials. Due to this potential, geometry optimisation of WECs has been previously considered, however, most of these studies have been limited by the simplicity of the employed geometrical shapes and the lack of accurate cost models. It is, therefore, important to include an adaptable geometry definition capable of generating diverse WEC shapes, and to account for other factors that can have an effect on costs. These considerations result in a more challenging optimisation problem, and a more complex objective function. The goal of this study is to address the challenge of finding a suitable and efficient optimisation method for WEC geometry design. In this paper, different geometry definitions, such as using simple shapes or B-spline surfaces, and different meta-heuristic optimisation algorithms, such as genetic algorithms or particle swarm optimisation are applied to this problem to find the most suitable choices. Results show an improvement in final objective function values of up to 224% when using an adaptable geometry definition and up to 11% when employing the most suitable optimisation algorithm compared to previous results. In conclusion, the choice of the different elements of the optimisation formulation have a large impact on the quality of the optimisation results and should be based on preliminary studies as presented here.

OPTIMAL FREQUENCY CONTROL IN MICROGRID SYSTEM USING FRACTIONAL ORDER PID CONTROLLER USING KRILL HERD ALGORITHM

Abstract. This paper investigates the use of fractional order Proportional, Integral and Derivative (FOPID) controllers for the frequency and power regulation in a microgrid power system. The proposed microgrid system composes of renewable energy resources such as solar and wind generators, diesel engine generators as a secondary source to support the principle generators, and along with different energy storage devices like fuel cell, battery and flywheel. Due to the intermittent nature of integrated renewable energy like wind turbine and photovoltaic generators, which depend on the weather conditions and climate change this affects the microgrid stability by considered fluctuation in frequency and power deviations which can be improved using the selected controller. The fractional-order controller has five parameters in comparison with the classical PID controller, and that makes it more flexible and robust against the microgrid perturbation. The Fractional Order PID controller parameters are optimized using a new optimization technique called Krill Herd which selected as a suitable optimization method in comparison with other techniques like Particle Swarm Optimization. The results show better performance of this system using the fractional order PID controller-based Krill Herd algorithm by eliminates the fluctuations in frequency and power deviation in comparison with the classical PID controller. The obtained results are compared with the fractional order PID controller optimized using Particle Swarm Optimization. The proposed system is simulated under nominal conditions and using the disconnecting of storage devices like battery and Flywheel system in order to test the robustness of the proposed methods and the obtained results are compared.

SYNTHESIS, CHARACTERIZATION, AND OPTIMIZATION OF BIODEGRADABLE PCL-PEG-PCL TRIBLOCK COPOLIMERIC MICELLES AS NANOCARRIERS FOR HYDROPHOBIC DRUG SOLUBILITY ENHANCER

Objective: This study aims to synthesize, characterize, and optimize biodegradable polycaprolactone-polyethylene glycol-polycaprolactone (PCL-PEG-PCL) triblock copolimeric micelles as a nanocarrier for hydrophobic drug solubility enhancer of ketoprofen (K).
 Methods: PCL-PEG-PCL (PCEC) triblock copolymers was obtained from the synthesis of ɛ-caprolactone (ɛ-CL) and PEG by ring opening polymerization (ROP) method at different PCL: PEG ratio (2-5:1). The K-loaded PCEC triblock copolymeric micelles was obtained by solvent evaporation method. Optimization of PCEC triblock copolymers and analysis of the effect of PCL: PEG ratio factors on the responses toward particle size (PS), polydispersity index (PdI), and entrapment efficiency (EE), were carried out through the design of experiments (DoE) approach of the 22 full factorial design method using the Design-Expert software to obtain the optimum formula.
 Results: The higher the PCL: PEG ratio, the ZP value tends to be smaller while the PS, PdI, EE, and drug solubility may be increased, but the addition of hydrophobic blocks to some extent does not affect the EE and drug solubility. The optimum K-loaded PCEC triblock copolymeric micelles with a PCL: PEG 2.0:1 ratio has a zeta potential (ZP) of-24.07±0.35 mV, the particle size of 235.70±6.03 nm, polydispersity index of 0.30±0.06, entrapment efficiency of 87.08±0.06%, and the solubility of the K increases by 10.60 times.
 Conclusion: The 22full factorial design has been proven to be the suitable optimization method to determine the optimum condition that yields to the optimum results of the PS, PdI, and EE of the of the K-loaded PCEC triblock copolymer micelles.

Optimizing Models for Sustainable Drilling Operations Using Genetic Algorithm for the Optimum ANN

ABSTRACTIn the present study, Artificial Neural Network (ANN) approaches were adopted for the prediction of thrust force (Fz) and torque (Mz) during drilling of St60 workpiece, according to important cutting parameters such as cutting velocity, feed rate, and cutting tool diameter. During the setup of an ANN, some essential difficulties like the determination of network architecture, the determination of weight coefficients and the selection of training algorithm should be addressed. A combination of genetic algorithm and neural networks (GA-ANN) formulates those difficulties as an optimization problem and resolve it by the help of a suitable optimization method. Finally, a comparison between ANN with network architecture determined by a simple trial and error approach and ANN with architecture determined by a GA-ANN approach is conducted. The comparison of the models showed clearly that adopting genetic algorithm (GA) equals to the improvement of the efficiency of the network performance.

Reduction of IL-2 fragmentation during manufacturing of a novel immunocytokine by DoE process optimization.

Interleukin-2 (IL-2) is a potent molecule in cancer therapy. Clinical application, however, is limited due to its strong side effects during the treatment. We developed an IL-2 variant (IL-2v) immunocytokine to circumvent the drawbacks of the current IL-2 therapy. During the production of the IL-2v immunocytokine in Chinese hamster ovary (CHO) cells, molecules with fragmented IL-2v and therefore reduced cytokine activity can be observed. To control product fragmentationdifferent production process conditions were investigated. By shifting temperature or pH after the cell growth phase to lower values, fragmented species can be reduced from 10% to 12% to about 4%. However, with the adopted process conditions, the effective titer is decreased concomitantly. Moreover, fermentation length and inoculation cell density are parameters to adjust fragmentation and effective titer. A suitable method for efficient process optimization is the design of experiment approach. With this procedure, novel optimal values for temperature, pH value, harvest day, and inoculation cell densities were proposed and tested subsequently. In comparison to the former process, the improved process reduces fragmentation by 66% while keeping the effective titer comparable. In summary, these findings will help to control fragmentation in CHO production processes of different IL-2v or IL-2 containing therapeutic proteins.

Genetic algorithms applied to integration and optimization of billing and picking processes

This article intends to provide a computational tool that integrates and provides optimized solutions to two interdependent problems called Optimized Billing Sequencing (OBS) and Optimized Picking Sequence (OPS). These problems are addressed separately by the existing literature and refer respectively to the optimization of billing and picking processes in a typical warehouse with low-level picker-to-parts system. Integration literature is, therefore, limited and there is a demand for more robust OBS/OPS optimization methods. This approach will deal with practical dilemmas that have not been addressed by researchers yet to propose an extension to the OBS model by Pinto et al. (J Intell Manuf 29(2):405–422, 2018) along with a specific variation of the Order Batching and Sequencing Problem. The premise is to prove to managers the possibility of making more consistent decisions about the trade-off between the level of customer service and the warehouse efficiency. The proposed tool is formulated by the integration of two Genetic Algorithms called GA-OBS and GA-OPS where GA-OBS maximizes the order portfolio billing and generates the picking order to the OPS, whereas GA-OPS comprises the iteration of batch and routing algorithms to minimize picking total time and cost to the OPS. Experiments with problems with different complexity levels showed that the proposed tool produces solutions of satisfactory quality to OBS/OPS. The approach proposed fills a gap in the literature and makes innovative contributions to the development of more suitable optimization methods to the reality of warehouses.

Simultaneous optimization of shape and topology of free-form shells based on uniform parameterization model

In current optimization methods for free-form shells, the shape and topology are usually optimized separately. These methods are based on the assumption that the shape and topology of a shell influence each other only slightly, but this is not always correct. Moreover, different parameterization models are used in the shape optimization and topology optimization of free-form shells, which brings difficulties to carry out the integrated optimization. To solve this problem, an integrated method is proposed for simultaneously optimizing shape and topology for free-form shells. A uniform parameterization model based on NURBS solids is established to parameterize the free-form shells. In this model, only a small number of variables are used to describe both the shape and topology of the shell. In this way, the integrated optimization problem can be simplified, thus decrease the computational complexity. The integrated optimization of shape and topology is a complicated and large-scale optimization problem. Solving this problem requires a suitable optimization method. In this paper, the Method of Moving Asymptotes (MMA) is adopted. Finally, numerical examples are presented to address the importance of the optimization sequences and show the effectiveness and application of the proposed method.

Structural optimization using multi-objective modified adaptive symbiotic organisms search

Multiple objective structural optimization is a challenging problem in which suitable optimization methods are needed to find optimal solutions. Therefore, to answer such problems effectively, a multi-objective modified adaptive symbiotic organisms search (MOMASOS) with two modified phases is planned along with a normal line method as an archiving technique for designing of structures. The proposed algorithm consists of two separate improved phases including adaptive mutualism and modified parasitism phases. The probabilistic nature of mutualism phase of MOSOS lets design variables to have higher exploration and higher exploitation simultaneously. As search advances, a stability between the global search and a local search has a significant effect on the solutions. Therefore, an adaptive mutualism phase is added to the offer MOASOS. Also, the parasitism phase of MOSOS offers over exploration which is a major issue of this phase. The over exploration results in higher computational cost since the majority of the new solutions gets rejected due to inferior objective functional values. In consideration of this issue, the parasitism phase is upgraded to a modified parasitism phase to increase the possibility of getting improved solutions. In addition, the proposed changes are comparatively simple and do not need an extra parameter setting for MOSOS.For the truss problems, mass minimization and maximization of nodal deflection are considered as objective functions, elemental stresses are considered as behavior constraints and (discrete) elemental sections are considered as side constraints. Five truss optimization problems validate the applicability of the considered meta-heuristics to solve complex engineering. Also, four constrained benchmark engineering design problems are solved to demonstrate the effectiveness of MOMASOS. The results confirmed that the proposed adaptive mutualism phase and modified parasitism phase with a normal line method as an archiving technique provide superior and competitive results than the former obtained results.

5-Dimensional Definition for a Manufacturing Digital Twin

The Digital Twin is a recently developed innovative technology in Industry 4.0. The cyber-physical system (CPS) is a concept closely connected with Industry 4.0 that can form a basis for creating a Digital Twin. In this paper, a comprehensive model of a Digital Twin approach for a manufacturing environment and related production processes is proposed. The presented model is based on combining a 5-Dimensional definition for the Digital Twin and cloud-based CPS (C2PS) architecture. The model consists of five layers to replicate the physical object as a virtual object and to collect and convert data. Analysis of the virtual model for prediction of future development, decision-making, re-configuration, what-if analysis, and understanding of the effect of changes in the real time process is performed in the fourth layer. The user interface layer is the connection between the virtual and physical model. Use of a Digital Twin in manufacturing enables improvement in the effectiveness of Lean Manufacturing, leading to savings in resources such as cost and time. Uncertainties inherent in manufacturing processes mean that the Digital Twin approach is a more suitable method for optimization of the overall process and the sub-processes than pure simulation. An accurate Digital Twin model can improve safety, save costs, speed up manufacturing of new products and implementation of new processes, and provide global optimization results. In practice, however, provision of data is a challenge to use of the Digital Twin approach because modern manufacturing uses a variety of data in different formats with different owners. Access to all required data and information and obtaining permission for its use in creation of a Digital Twin is a topic for future research.

A PSO based approach: Scout particle swarm algorithm for continuous global optimization problems

AbstractIn the literature, most studies focus on designing new methods inspired by biological processes, however hybridization of methods and hybridization way should be examined carefully to generate more suitable optimization methods. In this study, we handle Particle Swarm Optimization (PSO) and an efficient operator of Artificial Bee Colony Optimization (ABC) to design an efficient technique for continuous function optimization. In PSO, velocity and position concepts guide particles to achieve convergence. At this point, variable and stable parameters are ineffective for regenerating awkward particles that cannot improve their personal best position (Pbest). Thus, the need for external intervention is inevitable once a useful particle becomes an awkward one. In ABC, the scout bee phase acts as external intervention by sustaining the resurgence of incapable individuals. With the addition of a scout bee phase to standard PSO, Scout Particle Swarm Optimization (ScPSO) is formed which eliminates the most important handicap of PSO. Consequently, a robust optimization algorithm is obtained.ScPSO is tested on constrained optimization problems and optimum parameter values are obtained for the general use of ScPSO. To evaluate the performance, ScPSO is compared with Genetic Algorithm (GA), with variants of the PSO and ABC methods, and with hybrid approaches based on PSO and ABC algorithms on numerical function optimization. As seen in the results, ScPSO results in better optimal solutions than other approaches. In addition, its convergence is superior to a basic optimization method, to the variants of PSO and ABC algorithms, and to the hybrid approaches on different numerical benchmark functions. According to the results, the Total Statistical Success (TSS) value of ScPSO ranks first (5) in comparison with PSO variants; the second best TSS (2) belongs to CLPSO and SP-PSO techniques. In a comparison with ABC variants, the best TSS value (6) is obtained by ScPSO, while TSS of BitABC is 2. In comparison with hybrid techniques, ScPSO obtains the best Total Average Rank (TAR) as 1.375, and TSS of ScPSO ranks first (6) again. The fitness values obtained by ScPSO are generally more satisfactory than the values obtained by other methods. Consequently, ScPSO achieve promising gains over other optimization methods; in parallel with this result, its usage can be extended to different working disciplines.Highlights PSO parameters are ineffective to regenerate the awkward particle that cannot improve its pbest. An external intervention is inevitable once a particle becomes an awkward one. ScPSO is obtained with the addition of scout bee phase into the PSO. So an evolutionary method eliminating the most important handicap of PSO is gained. ScPSO is compared with the variants and with hybrid versions of PSO and ABC methods. According to the experiments, ScPSO results in better optimal solutions. The fitness values of ScPSO are generally more satisfactory than the others. Consequently, ScPSO achieve promising gains over other optimization methods. In parallel with this, its usage can be extended to different working disciplines.

Comparative analysis and optimization of Mixed Model assembly line using Genetic Algorithm

Line balancing aims at arrangement of different facilities like workstation, machines, tool, and operator in an adequate manner in order to obtain most efficient balancing of assembly line, its capabilities, flow of product and services. Various methods are proposed in the literature to optimize these parameters hence this research effort starts with the review of the various methods developed and to compare main features of few of them for their relative assets and limitation to allow choose the most suitable method for optimization of line balancing. The researchers used the average times of the tasks of the models as the timings of the tasks of the combined assembly line model while designing the assembly line which is an approximate method of dealing with the data. Hence, in this paper, the design of the assembly line of the models is done simultaneously for all the models using their original task times. Such an attempt gives a realistic design of the mixed-model assembly line using genetic algorithm for the balancing of this mixed model assembly line problem. A new methodology of balancing the assembly line has been adopted and the output is compared with conventional methods of line balancing. The optimization of assembly line using cyclic multipoint crossover method of genetic algorithm has been performed to obtained real offspring and the best chromosome is selected to find out the efficiency of assembly line. The superiority of this approach is demonstrated using a numerical example. The multi-objective genetic algorithm with cyclic crossover and with individual task times of the models is a unique contribution. Although the RPW method also gives better results other than any conventional methods of line balancing however when the population size (assembly lines) of the system increase and number of workstation are more than genetic algorithm method is suitable and gives better result and this research paper presents the comparative analysis of mixed model assembly line balancing methods and tries to find out the best possible solution in order to minimize no. of workstation, ideal time, bottleneck and increase the efficiency of plant

Analysis of Artificial Neural Network Backpropagation Using Conjugate Gradient Fletcher Reeves In The Predicting Process

Backpropagation is a good artificial neural network algorithm used to predict, one of which is to predict the rate of Consumer Price Index (CPI) based on the foodstuff sector. While conjugate gradient fletcher reeves is a suitable optimization method when juxtaposed with backpropagation method, because this method can shorten iteration without reducing the quality of training and testing result. Consumer Price Index (CPI) data that will be predicted to come from the Central Statistics Agency (BPS) Pematangsiantar. The results of this study will be expected to contribute to the government in making policies to improve economic growth. In this study, the data obtained will be processed by conducting training and testing with artificial neural network backpropagation by using parameter learning rate 0,01 and target error minimum that is 0.001-0,09. The training network is built with binary and bipolar sigmoid activation functions. After the results with backpropagation are obtained, it will then be optimized using the conjugate gradient fletcher reeves method by conducting the same training and testing based on 5 predefined network architectures. The result, the method used can increase the speed and accuracy result.

How to compare performance of robust design optimization algorithms, including a novel method

AbstractThis paper proposes a method to compare the performances of different methods for robust design optimization of computationally demanding models. Its intended usage is to help the engineer to choose the optimization approach when faced with a robust optimization problem. This paper demonstrates the usage of the method to find the most appropriate robust design optimization method to solve an engineering problem. Five robust design optimization methods, including a novel method, are compared in the demonstration of the comparison method. Four of the five compared methods involve surrogate models to reduce the computational cost of performing robust design optimization. The five methods are used to optimize several mathematical functions that should be similar to the engineering problem. The methods are then used to optimize the engineering problem to confirm that the most suitable optimization method was identified. The performance metrics used are the mean value and standard deviation of the robust optimum as well as an index that combines the required number of simulations of the original model with the accuracy of the obtained solution. These measures represent the accuracy, robustness, and efficiency of the compared methods. The results of the comparison show that sequential robust optimization is the method with the best balance between accuracy and number of function evaluations. This is confirmed by the optimizations of the engineering problem. The comparison also shows that the novel method is better than its predecessor is.

Integrated Optimal Design of a Smart Microgrid With Storage

In this paper, we investigate a design approach aiming at simultaneously integrating the energy management and the sizing of a small microgrid with storage. We particularly underline the complexity of the resulting optimization problem and how it can be solved using suitable optimization methods in compliance with relevant models of the microgrid. We specifically show the reduction of the computational time allowing the microgrid simulation over long time durations in the optimization process in order to take seasonal variations into account. The developed approach allows performing many optimal designs in order to find the appropriate price context that could favor the installation of storage devices.

Estimation of Geological Data Using Assisted History Matching in the Pilot-scale CO2 Injection Site, Iwanohara, Japan

Assisted history matching using real field data from the Iwanohara project of CO2 storage was conducted. About one tonnes of CO2 was injected into a saline aquifer by one vertical well and observed by three vertical wells in the Iwanohara project.We developed the suitable optimization method for assisted reservoir history matching and verified it to apply to history matching of the Iwanohara project. Time lapse bottom-hole pressure data and CO2 arrival time at observation wells were selected as components of the objective function. The summation of their errors between the observed and simulated data was minimized to optimize primary variables: porosity, permeability and pore compressibility of the reservoir. Two cases of history matching including or excluding porosity distribution were conducted using Iterative Latin hypercube sampling as a global optimization algorithm.It was seen from the results of history matching that not only permeability but also porosity distribution are important parameters to predict stored CO2 flow. We concluded that the proposed method allowed us to optimize the reservoir model in CO2 geological storage with limited calculation resources.

Rayleigh’s quotient–based damage detection algorithm: Theoretical concepts, computational techniques, and field implementation strategies

This article proposes a Rayleigh’s quotient–based damage detection algorithm. It aims at efficiently revealing nascent structural changes on a given structure with the capability to differentiate between an actual damage and a change in operational conditions. The first three damage detection levels are targeted: existence, location, and severity. The proposed algorithm is analytically developed from the dynamics theory and the virtual energy principle. Some computational techniques are proposed for carrying out computations, including discretization, integration, derivation, and suitable optimization methods. Field implementation strategies are also considered for the purpose of online damage monitoring. In order to prove the efficiency of this strategy, one experimental and three numerical case studies were conducted. The proposed algorithm successfully detected the damage in all simulated cases and estimated the damage severity with acceptable accuracy. The conclusion is that the proposed algorithm was able to efficiently detect damage appearance in a range of structures for various damage levels and locations, and under different operational conditions.

Hybrid Optimization Method for Strategic Control of Water Withdrawal from Water Reservoir with Using Support Vector Machines

The aim of strategic control is the effort to achieve optimal water resource management (water reservoir). Classic strategic control of water withdrawal from water reservoir are based mainly on the rules and rules curves, which are created by generalization of historical data of water inflows to the reservoirs and water demand. Discharge series are changing in the time due to expected climate change. It is necessary to looking for intelligent water withdrawal control, which will allow to react on these hydrological changes and contribute to the efficient use of accumulated water for ensure water demand. The paper will describe the algorithm based on adaptive control. The normal adaptive control required knowledge of the water flow medium-term prediction into the reservoir. The created algorithm of intelligent water withdrawal control does not require knowledge of hydrological predictions. This control method is based on a suitable combination optimization method with the Support vector machines method. The control algorithm is one of the possible measures to mitigate the negative impacts of droughts and water scarcity. The algorithm of adaptive control is applied to the control of water withdrawal from selected single-reservoir. The results are compared with usual rules for water withdrawal control.