Evolutionary Multi-objective Optimisation by Diversity Control

Autor:	Djitt Laowattana, Pasan Kulvanit, Nachol Chaiyaratana, Theera Piroonratana
Rok vydání:	2006
Předmět:	Mathematical optimization symbols.namesake Computer science Genetic algorithm Evolutionary algorithm Benchmark (computing) Pareto principle Sorting symbols Contrast (statistics) ComputingMilieux_LEGALASPECTSOFCOMPUTING Pareto distribution Multi-objective optimization
Zdroj:	Computer Science – Theory and Applications ISBN: 9783540341666 CSR
DOI:	10.1007/11753728_45
Popis:	This paper presents an improved multi-objective diversity control oriented genetic algorithm (MODCGA-II). The performance comparison between the MODCGA-II, a non-dominated sorting genetic algorithm II (NSGA-II) and an improved strength Pareto evolutionary algorithm (SPEA-II) is carried out where different two- and three-objective benchmark problems with specific multi-objective characteristics are used. The results indicate that the two-objective MODCGA-II solutions are better than the solutions generated by the NSGA-II and SPEA-II in terms of the closeness to the true Pareto optimal solutions and the uniformity of solution distribution along the Pareto front. In contrast, the NSGA-II in overall produces the best solutions in three-objective problems. As a result, the limitation of the proposed algorithm is identified.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::d15722ccc83a52e5a55e25f627491922 https://doi.org/10.1007/11753728_45 Zobrazit plný text záznamu