Components and Parameters of DE, Real-coded CHC, and G-CMAES
نویسندگان
چکیده
In this document, we provide the description of the instances of Differential Evolution (DE) [6], Real-coded CHC [3], and Restart Evolution Strategy with Increasing Population Size (G-CMA-ES) [1] that were used to evaluate the performance of the proposed algorithms for the Special Issue of Soft Computing on Scalability of Evolutionary Algorithms and other Metaheuristics for Large Scale Continuous Optimization Problems. 1 Differential Evolution We have considered a classic DE model, with no parameter adaptation, at all. The crossover operator applied was rand/1/exp. We have observed that the results obtained on the test suite by using the rand/1/exp operator are clearly better than the ones obtained by employing the rand/1/bin operator, which is another well-known crossover operator for DE (the results of DE with these two operators may be found in http://sci2s.ugr.es/eamhco/decross_values. xls). The F and CR parameters were fixed to 0.5 and 0.9 values, respectively. An important decision for the application of DE to large scale problems is the choice of the population size (popsize). Usually, this parameter is set in function of the problem dimension (10 ·D or 3 ·D). When DE tackles functions with high dimensionality (500−1000), this criterion is not adequate, and a maximum limit should be fixed. For the experiments, a population of 60 individuals was used (we have analyzed DE with popsize = 100 and similar results were achieved).
منابع مشابه
Evolutionary algorithms based design of multivariable PID controller
In this paper, performance comparison of evolutionary algorithms (EAs) such as real coded genetic algorithm (RGA), modified particle swarm optimization (MPSO), covariance matrix adaptation evolution strategy (CMAES) and differential evolution (DE) on optimal design of multivariable PID controller design is considered. Decoupled multivariable PI and PID controller structure for Binary distillati...
متن کاملEnhanced opposition-based differential evolution for solving high-dimensional continuous optimization problems
This paper presents a novel algorithm based on generalized opposition-based learning (GOBL) to improve the performance of differential evolution (DE) to solve highdimensional optimization problems efficiently. The proposed approach, namely GODE, employs similar schemes of opposition-based DE (ODE) for opposition-based population initialization and generation jumping with GOBL. Experiments are c...
متن کاملModeling dynamics of a real-coded CHC algorithm in terms of dynamical probability distributions
Some theoretical models have been proposed in the literature to predict dynamics of real-coded evolutionary algorithms. These models are often applied to study very simplified algorithms, simple real-coded functions or sometimes these make difficult to obtain quantitative measures related to algorithm performance. This paper, trying to reduce these simplifications to obtain a more useful model,...
متن کاملBackground: Hepatic steatosis is commonly observed in patients with chronic hepatitis C (CHC). Many studies indicate a relationship between steatosis and fibrosis progression. The aim of this study was to analyze the prevalence of hepatic steatosis and related factors in Iranian CHC patients. Methods: One hundred and fifteen consecutive patients with CHC were enrolled which were treat...
متن کاملPrevalence of hepatic steatosis and associated factors in Iranian patients with chronic hepatitis C
Background: Hepatic steatosis is commonly observed in patients with chronic hepatitis C (CHC). Many studies indicate a relationship between steatosis and fibrosis progression. The aim of this study was to analyze the prevalence of hepatic steatosis and related factors in Iranian CHC patients. Methods: One hundred and fifteen consecutive patients with CHC were enrolled which were treat...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2010