Title: Improving the responsiveness of NSGA-II using an adaptive mutation operator: a case study

Authors: Alvaro Gomes, C. Henggeler Antunes, A. Gomes Martins

Addresses: Department of Electrical Engineering and Computers, University of Coimbra, Portugal; INESC Coimbra, R. Antero de Quental, 199, Coimbra, Portugal. ' Department of Electrical Engineering and Computers, University of Coimbra, Portugal; INESC Coimbra, R. Antero de Quental, 199, Coimbra, Portugal. ' Department of Electrical Engineering and Computers, University of Coimbra, Portugal; INESC Coimbra, R. Antero de Quental, 199, Coimbra, Portugal

Abstract: This paper presents a comparative analysis of the results obtained with two different implementations of the Non-dominated Sorting Genetic Algorithm-II (NSGA-II) in the framework of load management activities in power systems. The multiobjective real-world problem deals with the identification and the selection of control strategies to be applied to groups of loads aimed at reducing maximum power demand (PD), maximising profits and minimising user discomfort. It is shown that the algorithm performance is improved when the NSGA-II mutation operator is adaptively changed to incorporate information about the results of the search process and transfer this |knowledge| to the population.

Keywords: evolutionary multiobjective optimisation; real-world applications; NSGA-II; genetic algorithms; load management; power systems; adaptive mutation operators.

DOI: 10.1504/IJAIP.2010.029437

International Journal of Advanced Intelligence Paradigms, 2010 Vol.2 No.1, pp.4 - 18

Published online: 30 Nov 2009 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article