Pseudo derivative evolutionary algorithm and convergence analysis

Research output: Contribution to journalArticle

Published

DOI

View graph of relations

Original languageEnglish
Number of pages7
JournalInternational Journal of Modeling, Simulation, and Scientific Computing
DOIs
StatePublished - 6 Jul 2018

Abstract

In this paper a novel evolutionary algorithm (EA), called pseudo derivative evolutionary algorithm (PDEA), is proposed. The basic idea of PDEA is to use pseudo derivative, which is obtained based on the information produced during the evolution, to help search the solution of optimization problem. The pseudo derivative drives the search process in a more informed direction. That makes PDEA different from the random optimization methods. The convergence of PDEA is first analyzed based on systems theory. The convergence condition of PDEA is then derived, though this condition is too strong to be satisfied. Next, this condition is relaxed based on entropy theory. Finally, performances of PDEA are evaluated on the benchmark functions and an adaptive liquid level control system of a surge tank. The numeric simulation results show that PDEA is capable of finding the solutions to the optimization problems with good accuracy, reliability, and speed.

Keywords

  • pseudo derivative evolutionary algorithm , evolutionary algorithm , convergence analysis, entropy theory