Experimental comparison of methods to handle boundary constraints in differential evolution

Authors:
Jarosław Arabas;Adam Szczepankiewicz;Tomasz Wroniak
Affiliations:
Institute of Electronic Systems, Warsaw University of Technology, Poland;Faculty of Electronics and Information Technology, Warsaw University of Technology, Poland;Faculty of Electronics and Information Technology, Warsaw University of Technology, Poland
Venue:
PPSN'10 Proceedings of the 11th international conference on Parallel problem solving from nature: Part II
Year:
2010

Citing 6
Cited 1

A Fuzzy Adaptive Differential Evolution Algorithm

Soft Computing - A Fusion of Foundations, Methodologies and Applications
Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series)

Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series)
Differential evolution algorithm with strategy adaptation for global numerical optimization

IEEE Transactions on Evolutionary Computation
Recent advances in differential evolution: a survey and experimental analysis

Artificial Intelligence Review
JADE: adaptive differential evolution with optional external archive

IEEE Transactions on Evolutionary Computation
Self-Adapting Control Parameters in Differential Evolution: A Comparative Study on Numerical Benchmark Problems

IEEE Transactions on Evolutionary Computation

Repair methods for box constraints revisited

EvoApplications'13 Proceedings of the 16th European conference on Applications of Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we show that the technique of handling boundary constraints has a significant influence on the efficiency of the Differential Evolution method. We study the effects of applying several such techniques taken from the literature. The comparison is based on experiments performed for a standard DE/rand/1/bin strategy using the CEC2005 benchmark. The paper reports the results of experiments and provides their simple statistical analysis. Among several constraint handling methods, a winning approach is to repeat the differential mutation by resampling the population until a feasible mutant is obtained. Coupling the aforementioned method with a simple DE/rand/1/bin strategy allows to achieve results that outperform in many cases results of almost all other methods tested during the CEC2005 competition, including the original DE/rand/1/bin strategy.