Konferensartikel

Self-adaptive of Differential Evolution using Neural Network with Island Model of Genetic Algorithm

Linh Tao
D. Functional Control System, Shibaura Institute of Technology, Japan

Hieu Pham
National Institute of Patent and Technology Exploitation, Vietnam

Hiroshi Hasegawa
D. Functional Control System, Shibaura Institute of Technology, Japan

Ladda ner artikelhttp://dx.doi.org/10.3384/ecp17142533

Ingår i: Proceedings of The 9th EUROSIM Congress on Modelling and Simulation, EUROSIM 2016, The 57th SIMS Conference on Simulation and Modelling SIMS 2016

Linköping Electronic Conference Proceedings 142:77, s. 533-539

Visa mer +

Publicerad: 2018-12-19

ISBN: 978-91-7685-399-3

ISSN: 1650-3686 (tryckt), 1650-3740 (online)

Abstract

A new evolutionary algorithm called NN-DEGA that using Arti?cial Neural Network (ANN) for Self-adaptive Differential Evolution (DE) with Island model of Genetic Algorithm (GA) is proposed to solve large scale optimization problems, to reduce calculation cost, and to improve stability of convergence towards the optimal solution. This is an approach that combines the global search ability of DE and the local search ability of Adaptive System with Island model of GA. The proposed algorithm incorporates concept from DE, GA, and Neural Networks (NN) for self-adaptive of control parameters. The NN-DEGA is applied to several benchmark tests with multi-dimensions to evaluate its performance. It is shown to be statistically signi?cantly superior to other Evolutionary Algorithms (EAs), and Memetic Algorithms (MAs).

Nyckelord

differential evolution, memetic algorithm, migration, neural network, parallel genetic algorithm

Referenser

Inga referenser tillgängliga

Citeringar i Crossref