An Effective Hybrid Algorithm Based on Simplex Search and Differential Evolution for Global Optimization

摘要

In this paper, an effective hybrid NM-DE algorithm is proposed for global optimization by merging the searching mechanisms of Nelder-Mead (NM) simplex method and differential evolution (DE). First a reasonable framework is proposed to hybridize the NM simplex-based geometric search and the DE-based evolutionary search. Second, the NM simplex search is modified to further improve the quality of solutions obtained by DE. By interactively using these two searching approaches with different mechanisms, the searching behavior can be enriched and the exploration and exploitation abilities can be well balanced. Based on a set of benchmark functions, numerical simulation and statistical comparison are carried out. The comparative results show that the proposed hybrid algorithm outperforms some existing algorithms including hybrid DE and hybrid NM algorithms in terms of solution quality, convergence rate and robustness.