多目标差分进化算法的电力系统无功优化

 在传统电力系统无功优化( Reactive Power Optimization,RPO) 模型中引入电压水平 指标,建立了以网损最小,电压水平最好为目标的多目标差分进化算法( Differential Evolution Algorithm) 的模型。针对基本差分进化算法易陷入局部最优解、收敛速度慢的缺点,提出一种 具有自适应参数策略的改进差分进化算法并首次用于多目标电力系统无功优化问题。通过在 算法进化过程中调整变异因子F 和交叉因子CR,在初期增加种群的多样性、扩大全局搜索区 域; 从而可以避免算法陷入局部最优解; 同时在后期也加快了收敛速度。将该算法用于电力系 统无功优化并仿真计算了IEEE-14 节点标准测试系统,结果验证模型和算法的有效性。     

Self-adapting control parameters modified differential evolution for trajectory planning of manipulators

Control parameters of original differential evolution （DE） are kept fixed throughout the entire evolutionary process. However, it is not an easy task to properly set control parameters in DE for different optiinization problems. According to the relative position of two different individual vectors selected to generate a difference vector in the searching place, a self-adapting strategy for the scale factor F of the difference vector is proposed. In terms of the convergence status of the target vector in the current population, a self-adapting crossover probability constant CR strategy is proposed. Therefore, good target vectors have a lower CFI while worse target vectors have a large CFI. At the same time, the mutation operator is modified to improve the convergence speed. The performance of these proposed approaches are studied with the use of some benchmark problems and applied to the trajectory planning of a three-joint redundant manipulator. Finally, the experiment results show that the proposed approaches can greatly improve robustness and convergence speed.     

Self-adapting control parameters modified differential evolution for trajectory planning of manipulators

Control parameters of original differential evolution (DE) are kept fixed throughout the entire evolutionary process. However, it is not an easy task to properly set control parameters in DE for different optimization problems. According to the relative position of two different individual vectors selected to generate a difference vector in the searching place, a self-adapting strategy for the scale factor F of the difference vector is proposed. In terms of the convergence status of the target vector in the current population, a self-adapting crossover probability constant strategy is proposed. Therefore, good target vectors have a lower while worse target vectors have a large . At the same time, the mutation operator is modified to improve the convergence speed. The performance of these proposed approaches are studied with the use of some benchmark problems and applied to the trajectory planning of a three-joint redundant manipulator. Finally, the experiment results show that the proposed approaches can greatly improve robustness and convergence speed.     

Solution of Jiles-Atherton vector hysteresis parameters estimation by modified Differential Evolution approaches

Differential Evolution (DE) is a simple and efficient stochastic global optimization algorithm of evolutionary computation field, which involves the evolution of a population of solutions using operators such as mutation, crossover, and selection. The basic idea of DE is to adapt the search during the evolutionary process. At the start of the evolution, the perturbations are large since parent populations are far away from each other. As the evolutionary process matures, the population converges to a small region and the perturbations adaptively become small. DE approaches have been successfully applied to solve a wide range of optimization problems. In this paper, the parameters set of the Jiles-Atherton vector hysteresis model is obtained with an approach based on modified Differential Evolution (MDE) approaches using generation-varying control parameters based on generation of random numbers with uniform distribution. Several evaluated MDE approaches perform better than the classical DE methods and a genetic algorithm approach in terms of the quality and stability of the final solutions in optimization of vector Jiles-Atherton vector hysteresis model from a workbench containing a rotational single sheet tester.     

Self-adaptive population sizing for a tune-free differential evolution

The study and research of evolutionary algorithms (EAs) is getting great attention in recent years. Although EAs have earned extensive acceptance through numerous successful applications in many fields, the problem of finding the best combination of evolutionary parameters especially for population size that need the manual settings by the user is still unresolved. In this paper, our system is focusing on differential evolution (DE) and its control parameters. To overcome the problem, two new systems were carried out for the self-adaptive population size to test two different methodologies (absolute encoding and relative encoding) in DE and compared their performances against the original DE. Fifty runs are conducted for every 20 well-known benchmark problems to test on every proposed algorithm in this paper to achieve the function optimization without explicit parameter tuning in DE. The empirical testing results showed that DE with self-adaptive population size using relative encoding performed well in terms of the average performance as well as stability compared to absolute encoding version as well as the original DE.     

遗传算法函数寻优性能影响因素分析——基于正交试验的方法

遗传算法在函数寻优领域得到了广泛应用,选取合适的参数对提高遗传算法寻优性能至关重要。以四个经典函数为例,基于正交试验原理分析了遗传算法五个参数对其寻优时间和迭代次数的影响。结果表明：对寻优搜索时间影响最大的参数为变异概率,其次为种群大小,交叉算子的选择、交叉概率和编码长度影响相对较小;对寻优迭代次数影响较大的三个参数为变异概率、种群大小和编码长度,而交叉概率和交叉算子的选择影响相对较小。分析了使遗传算法性能最优时参数组合的原则。     

Differential evolution based on covariance matrix learning and bimodal distribution parameter setting

Differential evolution (DE) is an efficient and robust evolutionary algorithm, which has been widely applied to solve global optimization problems. As we know, crossover operator plays a very important role on the performance of DE. However, the commonly used crossover operators of DE are dependent mainly on the coordinate system and are not rotation-invariant processes. In this paper, covariance matrix learning is presented to establish an appropriate coordinate system for the crossover operator. By doing this, the dependence of DE on the coordinate system has been relieved to a certain extent, and the capability of DE to solve problems with high variable correlation has been enhanced. Moreover, bimodal distribution parameter setting is proposed for the control parameters of the mutation and crossover operators in this paper, with the aim of balancing the exploration and exploitation abilities of DE. By incorporating the covariance matrix learning and the bimodal distribution parameter setting into DE, this paper presents a novel DE variant, called CoBiDE. CoBiDE has been tested on 25 benchmark test functions, as well as a variety of real-world optimization problems taken from diverse fields including radar system, power systems, hydrothermal scheduling, spacecraft trajectory optimization, etc. The experimental results demonstrate the effectiveness of CoBiDE for global numerical and engineering optimization. Compared with other DE variants and other state-of-the-art evolutionary algorithms, CoBiDE shows overall better performance.     

An evolving surrogate model-based differential evolution algorithm

Differential evolution (DE) is a simple and effective approach for solving numerical optimization problems. However, the performance of DE is sensitive to the choice of mutation and crossover strategies and their associated control parameters. Therefore, to achieve optimal performance, a time-consuming parameter tuning process is required. In DE, the use of different mutation and crossover strategies with different parameter settings can be appropriate during different stages of the evolution. Therefore, to achieve optimal performance using DE, various adaptation, self-adaptation, and ensemble techniques have been proposed. Recently, a classification-assisted DE algorithm was proposed to overcome trial and error parameter tuning and efficiently solve computationally expensive problems. In this paper, we present an evolving surrogate model-based differential evolution (ESMDE) method, wherein a surrogate model constructed based on the population members of the current generation is used to assist the DE algorithm in order to generate competitive offspring using the appropriate parameter setting during different stages of the evolution. As the population evolves over generations, the surrogate model also evolves over the iterations and better represents the basin of search by the DE algorithm. The proposed method employs a simple Kriging model to construct the surrogate. The performance of ESMDE is evaluated on a set of 17 bound-constrained problems. The performance of the proposed algorithm is compared to state-of-the-art self-adaptive DE algorithms: the classification-assisted DE algorithm, regression-assisted DE algorithm, and ranking-assisted DE algorithm.     

基于简化群优化算法和协方差矩阵学习的差分进化算法

把SSO算法的交叉策略、协方差矩阵学习策略与传统的DE算法结合,提出一个新的DE算法的变种,我们把它称作SCDE算法。正如我们所知,DE算法的变异策略在DE算法中占据了非常重要的位置,然而,传统的DE算法的变异策略都是用相对位置来产生候选解,本文尝试利用个体历史最优解来诱导变异产生候选解,这将大大提高种群跳出局部最优的能力。此外,将算法的变异和交叉操作放在由种群的协方差矩阵的所有特征向量组成的坐标系中执行,这将使算法的交叉和变异操作具有旋转不变性。实验结果表明,本文提出的新的交叉和变异策略可以大大提高DE算法在CEC 2013中28个测试函数的全局寻优能力。     

An adaptive surrogate assisted differential evolutionary algorithm for high dimensional constrained problems

Differential evolution (DE) is a competitive algorithm for constrained optimization problems (COPs). In this study, in order to improve the efficiency and accuracy of the DE for high dimensional problems, an adaptive surrogate assisted DE algorithm, called ASA-DE is suggested. In the ASA, several kinds of surrogate modeling techniques are integrated. Furthermore, to avoid violate the constraints and obtain better solution simultaneously, adaptive strategies for population size and mutation are also suggested in this study. The suggested adaptive population strategy which controls the exploring and exploiting states according to whether algorithm find enough feasible solution is similar to a state switch. The mutation strategy is used to enhance the effect of state switch based on adaptive population size. Finally, the suggested ASA-DE is evaluated on the benchmark problems from congress on evolutionary computation (CEC) 2017 constrained real parameter optimization. The experimental results show the proposed algorithm is a competitive one compared to other state-of-the-art algorithms.