Dynamic Regional Harmony Search with Opposition and Local Learning

A. Kai Qin 1 Florence Forbes 1, *
* Auteur correspondant
1 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Harmony search (HS), as an emerging metaheuristic algorithm mimicking the musician's improvisation behavior, has demonstrated strong efficacy in solving various numerical and real-world optimization problems. To deal with the deficiencies in the original HS such as premature convergence and stagnation, a dynamic regional harmony search (DRHS) algorithm with opposition and local learning is proposed. DRHS utilizes opposition-based initialization, and performs independent harmony searches with respect to multiple groups created by periodically and randomly regrouping the harmony memory. Besides the traditional harmony improvisation operators, an opposition-based harmony creation scheme is used in DRHS to update each group memory. Any prematurely converged group will be restarted with its size being doubled to enhance exploration. Local search is periodically applied to exploit promising regions around topranked candidate solutions. The performance of DRHS has been evaluated and compared to the original HS using 12 numerical test problems taken from the CEC2005 benchmark. DRHS consistently outperforms HR on all test problems at both 10D and 30D.
Type de document :
Communication dans un congrès
GECCO'11 - 13th annual conference companion on Genetic and evolutionary computation, Jul 2011, Dublin, Ireland. ACM, pp.53-54, 2011, 〈http://dl.acm.org/citation.cfm?id=2001890〉. 〈10.1145/2001858.2001890〉
Liste complète des métadonnées

https://hal.inria.fr/hal-00780548
Contributeur : Florence Forbes <>
Soumis le : jeudi 24 janvier 2013 - 11:40:28
Dernière modification le : mercredi 11 avril 2018 - 01:59:40

Identifiants

Collections

Citation

A. Kai Qin, Florence Forbes. Dynamic Regional Harmony Search with Opposition and Local Learning. GECCO'11 - 13th annual conference companion on Genetic and evolutionary computation, Jul 2011, Dublin, Ireland. ACM, pp.53-54, 2011, 〈http://dl.acm.org/citation.cfm?id=2001890〉. 〈10.1145/2001858.2001890〉. 〈hal-00780548〉

Partager

Métriques

Consultations de la notice

280