ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

Evolutionary Algorithms Performance Comparison For Optimizing Unimodal And Multimodal Test Functions

Journal: International Journal of Scientific & Technology Research (Vol.5, No. 7)

Publication Date:

Authors : ; ;

Page : 38-45

Keywords : Benchmark test functions; Evolutionary population based algorithms; Meta-heuristic techniques; Optimization.;

Source : Downloadexternal Find it from : Google Scholarexternal

Abstract

Many evolutionary algorithms have been presented in the last few decades some of these algorithms were sufficiently tested and used in many researches and papers such as Particle Swarm Optimization PSO Genetic Algorithm GA and Differential Evolution Algorithm DEA. Other recently proposed algorithms were unknown and rarely used such as Stochastic Fractal Search SFS Symbiotic Organisms Search SOS and Grey Wolf Optimizer GWO. This paper trying to made a fair comprehensive comparison for the performance of these well-known algorithms and other less prevalent and recently proposed algorithms by using a variety of famous test functions that have multiple different characteristics through applying two experiments for each algorithm according to the used test function the first experiments carried out with the standard search space limits of the proposed test functions while the second experiment multiple ten times the maximum and minimum limits of the test functions search space recording the Average Mean Absolute Error AMAE Overall Algorithm Efficiency OAE Algorithms Stability AS Overall Algorithm Stability OAS each algorithm required Average Processing Time APT and Overall successful optimized test function Processing Time OPT for both of the experiments and with ten epochs each with 100 iterations for each algorithm.

Last modified: 2017-06-11 22:50:52