Mutation is the main operator of differential evolution (DE), as it is responsible for combining the information of distinct solutions to generate a donor vector. Aiming at improving the search effectivity of DE, previous research incorporated the calculation of centroids into the DE mutations. In some of the existing methods, the centroids are simply calculated as the center of some selected solutions (or, the entire population); in other cases, one-step clustering is used to perform a local search, or the centroids themselves are used as actual solutions in the population. As opposed to these methods, in this paper we extend some traditional DE mutation strategies to incorporate centroids calculated by deterministic hierarchical clustering. Experimental results on two sets of well-known benchmark problems show that the proposed cluster-centroid-based mutation strategies outperform, in general, the traditional rand/1 strategy, as well as several metaheuristics from the literature. Therefore, the use of clustering is an effective way to improve the search performance that could be exploited also in other population-based metaheuristics.
Cluster-centroid-based mutation strategies for Differential Evolution / Iacca, Giovanni; de Melo, Vinícius Veloso. - In: SOFT COMPUTING. - ISSN 1432-7643. - 2022, 26:(2022), pp. 1889-1921. [10.1007/s00500-021-06448-z]
Cluster-centroid-based mutation strategies for Differential Evolution
Iacca, Giovanni;
2022-01-01
Abstract
Mutation is the main operator of differential evolution (DE), as it is responsible for combining the information of distinct solutions to generate a donor vector. Aiming at improving the search effectivity of DE, previous research incorporated the calculation of centroids into the DE mutations. In some of the existing methods, the centroids are simply calculated as the center of some selected solutions (or, the entire population); in other cases, one-step clustering is used to perform a local search, or the centroids themselves are used as actual solutions in the population. As opposed to these methods, in this paper we extend some traditional DE mutation strategies to incorporate centroids calculated by deterministic hierarchical clustering. Experimental results on two sets of well-known benchmark problems show that the proposed cluster-centroid-based mutation strategies outperform, in general, the traditional rand/1 strategy, as well as several metaheuristics from the literature. Therefore, the use of clustering is an effective way to improve the search performance that could be exploited also in other population-based metaheuristics.File | Dimensione | Formato | |
---|---|---|---|
main_springer.pdf
Open Access dal 07/11/2022
Tipologia:
Post-print referato (Refereed author’s manuscript)
Licenza:
Altra licenza (Other type of license)
Dimensione
2.26 MB
Formato
Adobe PDF
|
2.26 MB | Adobe PDF | Visualizza/Apri |
Iacca-Melo2021_Article_Cluster-centroid-basedMutation.pdf
Solo gestori archivio
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
1.64 MB
Formato
Adobe PDF
|
1.64 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione