An Improved Flower Pollination Algorithm for Global Numerical Optimization

Abstract

A new bionic algorithm named as Flower Pollination algorithm (FPA) was proposed by Yang. FPA has some shortcomings, such as premature convergence, low precision, et al. So an improved flower pollination algorithm (IFPA) is proposed in this paper. IFPA combines three aspects: global pollination with quantum search mechanics, local pollination with DE/rand/1 mutation, and switch on dimensions. The experimental results show that IFPA can speed up convergence and improve accuracy.