AUTOMATIC CALIBRATION OF DISPRIN MODEL PARAMETERS USING METAHEURISTIC METHODS TO GENERATE HISTORICAL DAILY DISCHARGE DATA SERIES

The fundamental weakness of the Tank model are the large number of parameters and their continuous values, which make it ineffective for solving practical problems. This article proposes a metaheuristic-based automatic calibration method to enhance the Tank model’s performance and applicability in transforming rainfall data series into runoff in a watershed. The metaheuristic methods involved include the Differential Evolution (DE) algorithm, Particle Swam Optimization (PSO), synthesis of chaotic search-opposition based learning-differential evolution-quantum mechanism (CODEQ) algorithm and Shuffled Complex Evolution (SCE). The models resulting from the integration of the Tank model with these metaheuristic methods are called the Tank-DE, Tank-PSO, Tank-CODEQ and Tank-SCE models. The four models were tested in the Welang Watershed (473.39 Km2), located in Pasuruan Regency, East Java, using a 15-year hydroclimatology dataset from 2006 to 2020. The 2006-2010 dataset served as the training dataset forTank model parameter calibration, while the 2011-2020 dataset was used for model validation. Calibration results show that all models achieved an accuracy level equivalent to an average RMSE of 0.05 m3/s. However, during validation, there were slight differences in high flow response results. Compared to the training dataset, the model output responded effectively to both low and high flows but tended to produce slightly higher discharge at intermediate flows, with an average difference of 1.33 m3/s. When compared to the test dataset, the model outputs tended to overestimate high flow rates (average difference of 1.63 m3/s) and underestimated low flow rates, with minor deviations.Keywords: tank model, metaheuristic, transformation, rainfall-streamflow, Welang Watershed.

The reliability and ease of applying metaheuristic methods in solving large and complex equation systems make it interesting to be applied as an alternative solution to solving problems in various fields. This article proves the effectiveness of an optimization model based on the metaheuristic method for the analysis of hydraulic parameters of drinking water distribution pipes. The metaheuristic methods explored are Differential Evolution (DE) algorithm, Particle Swam Optimization (PSO) algorithm and CODEQ algorithm. The effectiveness of the three methods is measured relative by comparing the results of the analysis of the three models with the results from Newton Raphson method and Monte Carlo simulation method. The analysis shows that the optimization model based on the DE, PSO and CODEQ algorithms is very effective for solving problems on a simple network that has 6 pipe elements and 5 service nodes. The results obtained have a level of accuracy as good as Newton Raphson method. In the case of complex networks that have 32 pipe elements and 21 service nodes, there is an indication of performance degradation which is indicated by a decrease in fitness value. In this case, Newton Raphson method still shows its consistency. The optimization model based on the metaheuristic method is still far more effective than the Monte Carlo simulation method, although it is not as effective as Newton Raphson method. The Monte Carlo simulation method is not recommended for hydraulic pipe network analysis, even for simple networks.

The aim of this study is to improve the performance of the shuffled complex evolution (SCE) algorithm used in the optimization of hydropower generation in reservoirs as a complex issue in water resources. First, the SCE algorithm is merged with the differential evolution (DE) algorithm to form the SCE-DE algorithm. Then, a complex mathematical function is used as a benchmark to evaluate the performance and validate the SCE-DE algorithm and the outcomes are compared with the original SCE algorithm to show the superiority of the proposed SCE-DE algorithm. In addition, the two-reservoir system of Dez-Gotvand is considered as a real optimization problem to evaluate the performance of the SCE-DE algorithm. It is revealed that optimization by SCE-DE is much better than SCE. In conclusion, the results show that the proposed SCE-DE algorithm is a reasonable alternative to optimizing resource systems and can be used to solve complex issues of water resources.

Evolutionary algorithms for the optimal management of coastal groundwater: A comparative study toward future challenges

Differential evolution (DE) algorithms compose an efficient type of evolutionary algorithm (EA) for the global optimization domain. Although it is well known that the population structure has a major influence on the behavior of EAs, there are few works studying its effect in DE algorithms. In this paper, we propose and analyze several DE variants using different panmictic and decentralized population schemes. As it happens for other EAs, we demonstrate that the population scheme has a marked influence on the behavior of DE algorithms too. Additionally, a new operator for generating the mutant vector is proposed and compared versus a classical one on all the proposed population models. After that, a new heterogeneous decentralized DE algorithm combining the two studied operators in the best performing studied population structure has been designed and evaluated. In total, 13 new DE algorithms are presented and evaluated in this paper. Summarizing our results, all the studied algorithms are highly competitive compared to the state-of-the-art DE algorithms taken from the literature for most considered problems, and the best ones implement a decentralized population. With respect to the population structure, the proposed decentralized versions clearly provide a better performance compared to the panmictic ones. The new mutation operator demonstrates a faster convergence on most of the studied problems versus a classical operator taken from the DE literature. Finally, the new heterogeneous decentralized DE is shown to improve the previously obtained results, and outperform the compared state-of-the-art DEs.

Accurate long-term electricity load forecasting was essential for efficient energy planning and infrastructure development. This study addressed forecasting challenges in rapidly growing regions, such as East Java, where electricity demand was influenced by both linear and non-linear patterns. Conventional forecasting models, such as the Autoregressive Integrated Moving Average (ARIMA) effectively captured linear trends but failed to model non-linear dynamics, whereas networks with Long Short-Term Memory (LSTM) excelled with non-linear data but were often less effective when used alone. This research developed and evaluated an ARIMA-LSTM hybrid model optimized with the Differential Evolution (DE) algorithm to forecast electricity load until 2026. The model was trained and validated using historical daily load data from 2021 to 2023 from PT PLN UP2B East Java. This hybrid methodology first used ARIMA to model the linear components of the time series. The resulting residual errors, which contained non-linear patterns, were then modeled using an LSTM network. The DE algorithm was used to automatically optimize hyperparameters for both the ARIMA (p, d, q) and LSTM (units, learning rate, drop out etc.) components. The suggested hybrid model's performance was contrasted with that of the independent LSTM and ARIMA models. The results showed that the DE-optimized hybrid model achieved higher accuracy, yielding a Mean Absolute Percentage Error (MAPE) of 3.97 %, which was significantly better than the ARIMA model (12.39 % MAPE) and the LSTM model (4.50 % MAPE) on the validation set. According to these results, the suggested hybrid model was a dependable and extremely accurate instrument for predicting long-term loads, offering a solid basis for strategic energy planning.

The Dee Investigation Simulation Program for Regulating Network (DISPRIN) model consists of eight tanks that are mutually interconnected. It contains 25 parameters involved in the process of transforming rainfall into runoff data. This complexity factor is the appeal to be explored in order to more efficiently. Parameterization process in this research is done by using Differential Evolution (DE) algorithm while parameters sensitivity analysis is done by using Monte Carlo simulation method. Software application models of merging the two concepts are called DISPRIN25-DE model and compiled using code program M-FILE from MATLAB. Results of research on Lesti watershed at the control point Tawangrejeni automatic water level recorder (AWLR) station (319.14 km2) in East Java Indonesia indicate that the model can work effectively for transforming rainfall into runoff data series. Model performance at the calibration stage provide value of NSE = 0.871 and PME = 0.343 while in the validation stage provide value of NSE = 0.823 and PME = 0.180. Good performance in the calibration process indicates that DE algorithm is able to solve problems of global optimization of the equations system with a large number of variables. The results of the sensitivity analysis of 25 parameters showed that 3 parameters have a strong sensitivity level, 7 parameters with a medium level and 15 other parameters showed weak sensitivity level to performance of DISPRIN model.

Recently, physically-based hydrological models have been gaining much popularity in various activities of water resources planning and management, such as assessment of basin water availability, floods, droughts, and reservoir operation. Every hydrological model contains some parameters that must be tuned to the catchment being studied to obtain reliable estimates from the model. This study evaluated the performance of different evolutionary algorithms, namely genetic algorithm (GA), shuffled complex evolution (SCE), differential evolution (DE), and self-adaptive differential evolution (SaDE) algorithm for the parameter calibration of a computationally intensive distributed hydrological model, variable infiltration capacity (VIC) model. The methodology applied and tested for a case study of the upper Tungabhadra River basin in India and the performance of the algorithms is evaluated in terms of reliability, variability, efficacy measures in a limited number of function evaluations, their ability for achieving global convergence, and also by their capability to produce a skilful simulation of streamflows. The results of the study indicated that SaDE facilitates an effective calibration of the VIC model with higher reliability and faster convergence to optimal solutions as compared to the other methods. Moreover, due to the simplicity of the SaDE, it provides easy implementation and flexibility for the automatic calibration of complex hydrological models.

Evolutionary algorithms (EAs) have recently been successfully applied in optimization problems and engineering disciplines. They can solve complex optimization problems without specialized information such as gradient or smoothness of objective functions. Although pure EAs such as genetic algorithm (GA), evolutionary strategies (ES) and evolutionary programming (EP) are easy to implement and offer fair performance in many applications, experimental results have shown that a variant of evolutionary method namely Differential Evolution (DE) has good convergence properties and outperforms other well known EAs (Ilonen et al., 2003). This variation was first introduced by Storn and Price (Storn & Price, 1997) and has an increasing interest as an optimization technique in recent years due to its achievement for a global minimum. It has several important differences from the traditional genetic optimization especially in the nature of the mutation, in which instead of taking a random perturbation, DE randomly selects a pair of individuals and computes the difference between their parameter vectors. This vector of difference is then added to the individual being mutated after multiplying by a constant. Another important difference is that the DE does not require the selection of parents based on fitness. Instead, fitness determines which children are kept for the next generation. Advantages of these approaches are shown in (Storn & Price, 1997). Using DE for training neural networks was first introduced in (Masters & Land, 1997). It was reported that the DE algorithm is particularly suitable for training general regression neural networks (GRNN), and it outperforms other training methods such as gradient and Hessian on applications which have the presence of multiple local minima in the error space. Recently, the combination of the DE and other training algorithms has also been investigated. Subudhi and Jena (Subudhi & Jena, 2008) proposed a combination of DE and Levenberg Marquardt (LM) to train neural network for nonlinear system identification. It was shown that this combination can offer better identification results than neural networks trained by ordinary LM algorithm. More comprehensive studies for using DE in the training neural networks are presented in (Ilonen et al., 2003). Although there are many network architectures proposed for different problems and applications, it was shown that single hidden-layer feedforward neural networks (SLFNs) can form boundaries with arbitrary shape and approximate any function with arbitrarily small error if the activation functions are chosen properly (Huang et al., 2000). An efficient training algorithm namely extreme learning machine (ELM) was proposed for SLFNs. It O pe n A cc es s D at ab as e w w w .in te ch w eb .o rg

The Differential Evolution (DE) algorithm, under the family of Evolutionary Algorithms (EAs), is one of the powerful algorithms used for solving continuous parameter optimization challenges. The simplistic nature and robustness of the classical DE algorithm have drawn researchers' attention towards its progressive enhancement. This work reports on an investigation of the behavioral changes of the classical DE algorithm, evoked when its mutation and crossover components are fine tuned for enhancement of DE's performance. The scope of this study covers the implementation of a mutation level enhancement and a crossover level enhancement, followed by their integration. The mutation and the crossover components are augmented by incorporation of Centroid DE and Superior-Superior & Superior-Inferior DE logics, respectively. The algorithms appraised in this inquiry were classical DE, Centroid based DE(cDE), Superior-Superior based DE (ssDE), Superior-Inferior DE (siDE), Centroid Superior-Superior DE (cssDE) and Centroid Superior-Inferior DE (csiDE). These algorithms were evaluated by comparison of the values of their mean objective function (MOV), and their speed, at solving the global optimization problems in a simple benchmarking function suite with 4 functions of different categories. The study concludes that the DE algorithm shows enhancement performance with modified mutation and crossover components. However, with a trend for inconsistency for varying values of its control parameters and benchmarking problems.

In recent years, Differential Evolution (DE) algorithm that is one of the most important delegate of the evolutionary algorithms have been successfully used for solving different optimization problems with its both serial and parallel variants. In this study, the performance of DE algorithm powered with cooperative emigrant creation strategy was investigated over the different types of numerical problems and obtained results were compared with the results of the serial DE and parallel DE algorithm supported with conventional emigrant creation strategy. Experimental studies showed that the convergence speed of the parallel DE algorithm is significantly improved with the cooperative emigrant creation strategy and the proposed parallel DE algorithm produces better results compared to the serial DE algorithm and parallel DE algorithm with the conventional emigrant creation strategy.

Optimum scheduling of hydro plants generation is of great importance to electric utilities. Hydro generation scheduling is a nonlinear programming problem. The nonlinearity is due to the generating characteristic of hydro plant, whose outputs are generally a non linear function of water discharge and net hydraulic head. Evolutionary algorithms are popular due to their low convergence time and high accuracy. In this paper the comparison of Particle swam optimization (PSO), Differential Evolution (DE) algorithm and Genetic Algorithm (GA) are use to show the optimal generation scheduling of hydro generation. The comparisons of these methods are shown for four generating plants of hydro here.

Differential evolution is arguably one of the hottest topics in today's computational intelligence research. This book seeks to present a comprehensive study of the state of the art in this technology and also directions for future research. The fourteen chapters of this book have been written by leading experts in the area. The first seven chapters focus on algorithm design, while the last seven describe real-world applications. Chapter 1 introduces the basic differential evolution (DE) algorithm and presents a broad overview of the field. Chapter 2 presents a new, rotationally invariant DE algorithm. The role of self-adaptive control parameters in DE is investigated in Chapter 3. Chapters 4 and 5 address constrained optimization; the former develops suitable stopping conditions for the DE run, and the latter presents an improved DE algorithm for problems with very small feasible regions. A novel DE algorithm, based on the concept of opposite points, is the topic of Chapter 6. Chapter 7 provides a survey of multi-objective differential evolution algorithms. A review of the major application areas of differential evolution is presented in Chapter 8. Chapter 9 discusses the application of differential evolution in two important areas of applied electromagnetics. Chapters 10 and 11 focus on applications of hybrid DE algorithms to problems in power system optimization. Chapter 12 applies the DE algorithm to computer chess. The use of DE to solve a problem in bioprocess engineering is discussed in Chapter 13. Chapter 14 describes the application of hybrid differential evolution to a problem in control engineering.

Mobile manipulator robots have become important pieces of equipment due to the high mobility of mobile subsystems and the high flexibility of manipulator subsystems. Considering the increasing degrees of freedom and the need to avoid singular locations, one of the most challenging problems is solving the inverse kinematics problem of mobile manipulator robots (IKMM). Of all the popular optimization algorithms, the differential evolution (DE) algorithm is the most effective method for quickly solving the IKMM problem with sufficient solutions. Currently, many strategies have been proposed for DE algorithms to improve the performance of solving mathematical problems; some symmetry strategies or symmetry functions have been introduced to DE algorithms. However, the effects of various DE algorithms on solving the actual IKMM lack a comprehensive explanation. Therefore, we divide various DE algorithms into three categories considering the control parameter selection and compare the specific optimization of various DE algorithms. Then, we compare the performance of various DE algorithms when solving the inverse kinematics problems of mobile manipulators with different degrees of freedom. Considering the effectiveness and the speed of the DE algorithm on the IKMM problem, we determine the best DE algorithm by comparing the error and time required to reach 100 random mission points and tracking the typical trajectories. Finally, the best-performing DE method is further improved by studying the selection of fundamental parameters in the best DE algorithm. Valuable conclusions are obtained from these experimental simulations, which can help with choosing an algorithm that is suitable for solving the inverse kinematics problem of mobile manipulator robots in practice.

Static and frequency optimization of folded laminated composite plates using an adjusted Differential Evolution algorithm and a smoothed triangular plate element