Self-adaptive Differential Evolution Research Articles

High-temperature oxidation of methyl isopropyl ketone: A shock tube experiment and a kinetic model

Pentanone has three types of isomers: 3-methyl-2-butanone (methyl isopropyl ketone, MIPK), 3-pentanone (diethyl ketone, DEK) and 2-pentanone (methyl propyl ketone, MPK). Since MIPK is the smallest branched ketone and a promising biofuel, it is important to fully understand its combustion kinetics. In this work, the ignition delay times were measured in the temperature range from 1150 to 1600 K at pressures from 1 to 5 bar and for the equivalence ratios of 0.5, 1.0 and 1.5 (Mixes 1–9). A high-temperature detailed combustion kinetic model for MIPK was developed via a hierarchical method. Previous theoretical computations of the H-atom abstraction by HO˙2 and O˙H from the tertiary carbon of MIPK were adopted, and the reaction rate coefficients of H-abstraction by H˙ from the MIPK tertiary carbon were calculated via quantum chemical techniques. The rate coefficients of the reactions that are related to the acetyl group and the isopropyl group of MIPK were estimated by analogy with MPK and DIPK, respectively. Eleven elementary reactions in the submodel that are related to MIPK were selected for the optimization due to the poor prediction performance of the raw model. The self-adaptive differential evolution algorithm was applied to optimize the raw kinetic model based on the ignition delay times of Mixes 1–6. The optimized MIPK model was validated against the ignition delay times of Mixes 7–9. A brute-force sensitivity analysis, in combination with a flux analysis, demonstrates that the amount of unsaturated fuel-related stable intermediate products is the key factor that determines the reactivity of MIPK and DEK.

Application of an Enhanced Self-adapting Differential Evolution Algorithm to Workload Prediction in Cloud Computing

Application of an Enhanced Self-adapting Differential Evolution Algorithm to Workload Prediction in Cloud Computing

A Modified Multiobjective Self-Adaptive Differential Evolution Algorithm and Its Application on Optimization Design of the Nuclear Power System

A modified multiobjective self-adaptive differential evolution algorithm (MMOSADE) is presented in this paper to improve the accuracy of multiobjective optimization design in the nuclear power system. The performance of the MMOSADE is tested by the ZDT test function set and compared with classical evolutionary algorithms. The results indicate that MMOSADE has a better performance in convergence and diversity. Based on the MMOSADE, a multiobjective optimization design platform for the nuclear power system is proposed, and the application of which is carried out. The evaluation program of the PRHR-HX in AP1000 is developed, and its reliability is verified. The optimal design schemes of PHHR-HX are obtained by utilizing the multiobjective optimization design platform. The results show that the optimal design schemes can envelop the prototype design scheme. This conclusion proves that the optimization design platform proposed in this paper is effective and feasible.

A Comparative Study on Meta-Heuristic Algorithms For Solving the RNP Problem

The continuous increases in the size of current telecommunication infrastructures have led to the many challenges that existing algorithms face in underlying optimization. The unrealistic assumptions and low efficiency of the traditional algorithms make them unable to solve large real-life problems at reasonable times.The use of approximate optimization techniques, such as adaptive metaheuristic algorithms, has become more prevalent in a diverse research area. In this paper, we proposed the use of a self-adaptive differential evolution (jDE) algorithm to solve the radio network planning (RNP) problem in the context of the upcoming generation 5G. The experimental results prove the jDE with best vector mutation surpassed the other metaheuristic variants, such as DE/rand/1 and classical GA, in term of deployment cost, coverage rate and quality of service (QoS).

On the Efficacy of Ensemble of Constraint Handling Techniques in Self-Adaptive Differential Evolution

Self-adaptive variants of evolutionary algorithms (EAs) tune their parameters on the go by learning from the search history. Adaptive differential evolution with optional external archive (JADE) and self-adaptive differential evolution (SaDE) are two well-known self-adaptive versions of differential evolution (DE). They are both unconstrained search and optimization algorithms. However, if some constraint handling techniques (CHTs) are incorporated in their frameworks, then they can be used to solve constrained optimization problems (COPs). In an early work, an ensemble of constraint handling techniques (ECHT) is probabilistically hybridized with the basic version of DE. The ECHT consists of four different CHTs: superiority of feasible solutions, self-adaptive penalty, ε -constraint handling technique and stochastic ranking. This paper employs ECHT in the selection schemes, where offspring competes with their parents for survival to the next generation, of JADE and SaDE. As a result, JADE-ECHT and SaDE-ECHT are developed, which are the constrained variants of JADE and SaDE. Both algorithms are tested on 24 COPs and the experimental results are collected and compared according to algorithms’ evaluation criteria of CEC’06. Their comparison, in terms of feasibility rate (FR) and success rate (SR), shows that SaDE-ECHT surpasses JADE-ECHT in terms of FR, while JADE-ECHT outperforms SaDE-ECHT in terms of SR.

Multi-objective flow shop scheduling with limited buffers using hybrid self-adaptive differential evolution

In this paper, a self-adaptive differential evolution (DE) algorithm is designed to solve multi-objective flow shop scheduling problems with limited buffers (FSSPwLB). The makespan and the largest job delay are treated as two separate objectives which are optimized simultaneously. To improve the performance of the proposed algorithm and eliminate the difficulty of setting parameters, an adaptive mechanism is designed and incorporated into DE. Moreover, various local search and hybrid meta-heuristic methods are presented and compared to improve the convergence. Through the analysis of the experimental results, the proposed algorithm is able to tackle the FSSPwLB problems effectively by generating superior and stable scheduling strategies.

OPTIMUS: Self-Adaptive Differential Evolution with Ensemble of Mutation Strategies for Grasshopper Algorithmic Modeling

Most of the architectural design problems are basically real-parameter optimization problems. So, any type of evolutionary and swarm algorithms can be used in this field. However, there is a little attention on using optimization methods within the computer aided design (CAD) programs. In this paper, we present Optimus, which is a new optimization tool for grasshopper algorithmic modeling in Rhinoceros CAD software. Optimus implements self-adaptive differential evolution algorithm with ensemble of mutation strategies (jEDE). We made an experiment using standard test problems in the literature and some of the test problems proposed in IEEE CEC 2005. We reported minimum, maximum, average, standard deviations and number of function evaluations of five replications for each function. Experimental results on the benchmark suite showed that Optimus (jEDE) outperforms other optimization tools, namely Galapagos (genetic algorithm), SilverEye (particle swarm optimization), and Opossum (RbfOpt) by finding better results for 19 out of 20 problems. For only one function, Galapagos presented slightly better result than Optimus. Ultimately, we presented an architectural design problem and compared the tools for testing Optimus in the design domain. We reported minimum, maximum, average and number of function evaluations of one replication for each tool. Galapagos and Silvereye presented infeasible results, whereas Optimus and Opossum found feasible solutions. However, Optimus discovered a much better fitness result than Opossum. As a conclusion, we discuss advantages and limitations of Optimus in comparison to other tools. The target audience of this paper is frequent users of parametric design modelling e.g., architects, engineers, designers. The main contribution of this paper is summarized as follows. Optimus showed that near-optimal solutions of architectural design problems can be improved by testing different types of algorithms with respect to no-free lunch theorem. Moreover, Optimus facilitates implementing different type of algorithms due to its modular system.

Application of vision measurement model with an improved moth-flame optimization algorithm

An improved moth-flame optimization (IMFO) algorithm is proposed to increase the location accuracy of a vision measurement system. This algorithm can optimize the initial pose parameters by improving a series of random solutions to the required precision. A measurement experiment system of space manipulator is designed to precision test. The IMFO algorithm is evaluated on 23 benchmark functions and measurement experiments for pose, and the results are verified by a comparative study with self-adaptive differential evolution (SaDE), moth-flame optimization (MFO), and proactive particle swarm optimization (PPSO). The statistical results of the benchmark functions show that the IMFO algorithm can provide very promising and competitive results. Additionally, the experimental results of pose measurement show that the accuracy of the IMFO algorithm is approximately twice higher than that of other three algorithms. All in all, the experiments indicate that the IMFO algorithm has a good optimization ability to complete the visual identification accurately.

Parameters identification of PMSM based on self-adaptive DE algorithm with hybrid mutation operator

The parameter identification of permanent magnet synchronous motor (PMSM) is an important and challenging task of power electronic systems, which has an important impact on the control performance of the drive system. Due to hardware limitations, this problem requires both a higher solution quality and a faster convergence speed. Aiming at the parameter identification problem, an adaptive differential evolution algorithm based on hybrid mutation operator (SHDE) is proposed. In this method, a randomly selected optimal solution is mixed with the current population, and a new mutation operator is developed, called “current to best archive”. Therefore, the algorithm can use the best search memory to date to generate promising solutions, resulting in a faster evolutionary process. In addition, the SHDO corresponding control parameters are adaptive without the need of trial and error and error processing, and the appropriate control values are obtained. In addition, the parameter estimation program is introduced into the permanent magnet synchronous motor simulation and solved by the Newton-Raphson method without prior assumption and simplification. The framework can be used in any interference-prone working conditions and, unlike other publications, has a wider range of applications. The parameter identification method of permanent magnet synchronous motor drive system under two different operating modes was evaluated. Comprehensive results and statistical analysis show that SHDE can find higher quality solutions with higher convergence speed and probability than other most advanced algorithms.

Optimal Tuning of PI Controllers for DFIG-Based Wind Energy System using Self-adaptive Differential Evolution Algorithm

Optimal Tuning of PI Controllers for DFIG-Based Wind Energy System using Self-adaptive Differential Evolution Algorithm

Estimation of Static Young’s Modulus for Sandstone Formation Using Artificial Neural Networks

In this study, we used artificial neural networks (ANN) to estimate static Young’s modulus (Estatic) for sandstone formation from conventional well logs. ANN design parameters were optimized using the self-adaptive differential evolution optimization algorithm. The ANN model was trained to predict Estatic from conventional well logs of the bulk density, compressional time, and shear time. The ANN model was trained on 409 data points from one well. The extracted weights and biases of the optimized ANN model was used to develop an empirical relationship for Estatic estimation based on well logs. This empirical correlation was tested on 183 unseen data points from the same training well and validated using data from three different wells. The optimized ANN model estimated Estatic for the training dataset with a very low average absolute percentage error (AAPE) of 0.98%, a very high correlation coefficient (R) of 0.999 and a coefficient of determination (R2) of 0.9978. The developed ANN-based correlation estimated Estatic for the testing dataset with a very high accuracy as indicated by the low AAPE of 1.46% and a very high R and R2 of 0.998 and 0.9951, respectively. In addition, the visual comparison of the core-tested and predicted Estatic of the validation dataset confirmed the high accuracy of the developed ANN-based empirical correlation. The ANN-based correlation overperformed four of the previously developed Estatic correlations in estimating Estatic for the validation data, Estatic for the validation data was predicted with an AAPE of 3.8% by using the ANN-based correlation compared to AAPE’s of more than 36.0% for the previously developed correlations.

Artificial Neural Network Optimal Modeling and Optimization of UAV Measurements for Mobile Communications Using the L-SHADE Algorithm

Channel modeling of wireless communications from unmanned aerial vehicles (UAVs) is an emerging research challenge. In this paper, we propose a solution to this issue by applying a new framework for the prediction of received signal strength (RSS) in mobile communications based on artificial neural networks (ANNs). The experimental data measurements are taken with a UAV at different altitudes. We apply several evolutionary algorithms (EAs) in conjunction with the Levenberg–Marquardt (LM) backpropagation algorithm in order to train different ANNs and in particular the L-SHADE algorithm, which self-adapts control parameters and dynamically adjusts population size. Five new hybrid training methods are designed by combining LM with self-adaptive differential evolution (DE) strategies. These new training methods obtain better performance to ANN weight optimization than the original LM method. The received results are compared with the real values using representative ANN performance indices and exhibit satisfactory accuracy.

Self-adaptive mutation differential evolution algorithm based on particle swarm optimization

Differential evolution (DE) is an effective evolutionary algorithm for global optimization, and widely applied to solve different optimization problems. However, the convergence speed of DE will be slower in the later stage of the evolution and it is more likely to get stuck at a local optimum. Moreover, the performance of DE is sensitive to its mutation strategies and control parameters. Therefore, a self-adaptive mutation differential evolution algorithm based on particle swarm optimization (DEPSO) is proposed to improve the optimization performance of DE. DEPSO can effectively utilize an improved DE/rand/1 mutation strategy with stronger global exploration ability and PSO mutation strategy with higher convergence ability. As a result, the population diversity can be maintained well in the early stage of the evolution, and the faster convergence speed can be obtained in the later stage of the evolution. The performance of the proposed DEPSO is evaluated on 30-dimensional and 100-dimensional functions. The experimental results indicate that DEPSO can significantly improve the global convergence performance of the conventional DE and thus avoid premature convergence, and its average performance is better than those of the conventional DE, PSO and the compared algorithms. Moreover, DEPSO is applied to solve arrival flights scheduling and the optimization results show that it can optimize the sequence and decrease the delay time.

Applying a fuzzy multi-objective model for a production–distribution network design problem by using a novel self-adoptive evolutionary algorithm

In this paper, a new fuzzy bi-objective mathematical model for production–distribution problem under uncertainty for a four-echelon supply chain network design involving of several suppliers, producers, distributors, customers, and a set of transportation modals with different reliability rates are presented. In addition to minimise the total cost of the supply chain, the second objective is maximising reliability rate of the whole proposed system. In order to solve the proposed model, a hybrid two-phase solution procedure is proposed based on possibilistic programming, fuzzy multi-objective programming and an efficient algorithm called self-adaptive differential evolution algorithm. Finally, an extensive comparison by a set of numerical examples with different complexity along with some sensitivity analyses has been reported to explore the efficiency of proposed model as well as the performance of proposed evolutionary algorithm.

Hybrid Grasshopper Optimization Algorithm and Differential Evolution for Multilevel Satellite Image Segmentation

An efficient satellite image segmentation method based on a hybrid grasshopper optimization algorithm (GOA) and minimum cross entropy (MCE) is proposed in this paper. The proposal is known as GOA–jDE, and it merges GOA with self-adaptive differential evolution (jDE) to improve the search efficiency, preserving the population diversity especially in the later iterations. A series of experiments is conducted on various satellite images for evaluating the performance of the algorithm. Both low and high levels of the segmentation are taken into account, increasing the dimensionality of the problem. The proposed approach is compared with the standard color image thresholding methods, as well as the advanced satellite image thresholding techniques based on different criteria. Friedman test and Wilcoxon’s rank sum test are performed to assess the significant difference between the algorithms. The superiority of the proposed method is illustrated from different aspects, such as average fitness function value, peak signal to noise ratio (PSNR), structural similarity index (SSIM), feature similarity index (FSIM), standard deviation (STD), convergence performance, and computation time. Furthermore, natural images from the Berkeley segmentation dataset are also used to validate the strong robustness of the proposed method.

An approach for initializing the random adaptive grouping algorithm for solving large-scale global optimization problems

Many real-world optimization problems deal with high dimensionality and are known as large-scale global optimization (LSGO) problems. LSGO problems, which have many optima and are not separable, can be very challenging for many heuristic search algorithms. In this study, we have proposed a novel two-stage hybrid heuristic algorithm, which incorporates the coordinate descent algorithm with the golden-section search (CDGSS) and the random adaptive grouping for cooperative coevolution of the Self-adaptive Differential Evolution with Neighborhood Search (DECC-RAG) algorithm. At the first stage, the proposed algorithm roughly scans the search space for a better initial population for the DECC-RAG algorithm. At the second stage, the algorithm uses the DECC-RAG framework for solving the given LSGO problem. We have evaluated the proposed approach (DECC-RAG1.1) with 15 most difficult LSGO problems from the IEEE CEC’2013 benchmark set. The experimental results show that DECC-RAG1.1 outperforms the standard DECC-RAG and some the state-of-the-art LSGO algorithms.

Evolutionary algorithm-based design optimization for right choice of transformer conductor material and stepped core

In this paper two crucial variables, namely type of winding material and number of core steps, have been proposed to minimize the purchase cost, total mass, loss, and life time cost of the transformer. In order to make cost-effective and energy-efficient transformer design, the proposed variables are used in conjunction with six primary variables for deciding the most appropriate conductor and core step size. Further, the efficacy of the proposed methodology, in terms of cost savings, material savings, and loss reduction, is tested on 1500-kVA transformer using covariance matrix adaptation evolution strategy (CMA-ES) and self-adaptive differential evolution (SaDE). It is revealed that the proposed crucial variables with CMA-ES provide better design option than the SaDE and knowledge-based systems. Also, faster convergence and consistency have been established with CMA-ES than SaDE through the statistical analysis. Core losses are calculated using proposed methodology, and employing analytical equations is validated using 3D finite element method.

Fully Automatic Spectral–Spatial Fuzzy Clustering Using an Adaptive Multiobjective Memetic Algorithm for Multispectral Imagery

Clustering of remote sensing imagery is a tough task due to the particular and complex structure of remote sensing images and the shortage of known information. In this paper, we propose a fully automatic spectral–spatial fuzzy clustering method using an adaptive multiobjective memetic algorithm (AMOMA) for multispectral remote sensing imagery. This approach is made up of two automatic layers: an automatic determination layer and an automatic clustering layer. The first layer seeks the optimal number of clusters through a self-adaptive differential evolution algorithm. The second layer then takes advantage of the AMOMA for spectral–spatial clustering using the optimal number of clusters. The knee point from the Pareto front is then selected through the angle-based method in every generation, and we then compare the knee points between generations to output the final optimal solution. The effectiveness of the proposed method is verified by the experimental results obtained with three remote sensing data sets.

Research on the Adaptive Control in Sugar Evaporative Crystallization Using LSSVM and SaDE-ELM

Abstract The process of sugar evaporative crystallization is a nonlinear process with large time lag and strong coupling. It is difficult to establish a reasonable mechanism model. In this paper, we use the data driving modeling method to establish an Adaptive Control model for batch boiling sugar crystallization process. First, by analyzing the main influencing factors of the evaporative crystallization process of intermittent boiling sugar, the most important two parameters, brix and liquid level, are selected as the control object. The self-adaptive differential evolution Extreme Learning Machine (SaDE-ELM) is used to construct the control model. A least squares support vector machine (LSSVM) is established and connected in the control loop to control the opening of the feed valve so that to control the feed flowrate according to the objective values of syrup Brix and liquid level. Experiments are conducted and the obtained data are used to train and verify the learning machines. Experiments indicate that the learning machines are able to realize adaptive control to key parameters of the crystallization process. Comparison of different neural networks indicates that the LSSVM performs better than BP, RBF and ELM and SaDE-ELM with prediction error of below 0.01, and training time of below 0.05 s.

Application of Differential Evolution Algorithm and Its Variants for Solving Energy Storage Technologies Integrated Generation Expansion Planning

Generation expansion planning (GEP) should consider the integration of renewable energy sources (RES) and energy storage technologies (EST), along with conventional generating units so as to overcome the challenges such as uncertainties in future load growth forecasting, restrictions on investment for power generation, the type and availability of source for the generating units, environmental policy based on emission constraints and the reliability level to guarantee a continuous power. The proposed coordinated GEP-EST planning aims at minimizing the overall generation cost and environmental pollution, and at the same time, it considers large-scale ESTs. In this paper, the promising intelligent techniques such as differential evolution and self-adaptive differential evolution algorithms are applied to solve GEP-EST problem, where the power generating system of Tamil Nadu, an Indian state is taken as study system. Simulation results show that the integration of ESTs significantly reduces the overall cost and the pollutant emission.