Improved Flower Pollination Algorithm for Linear Antenna Design Problems

Abstract

Flower pollination algorithm (FPA) is an evolutionary nature-inspired optimization technique, which mimics the pollinating behavior of flowers. FPA has a simple structure and has been applied to numerous problems in different fields of research. However, it has been found that it has poor exploration and exploitation capabilities. In this paper, to mitigate the problems of original FPA, a modified algorithm namely adaptive FPA (AFPA) has been proposed. In the modified algorithm, a four-fold population division has been followed for both global and local search phases. Moreover, to balance the local and global search, switching probability has been decreased exponentially with respect to iterations. For experimental testing, this algorithm has been further applied to antenna design problems. The aim is to optimize linear antenna array (LAA) in order to achieve minimum SLL in the radiation pattern to avoid antenna radiation in the undesired directions. The results of the proposed algorithm for same problems are compared with the results of popular algorithms such as particle swarm optimization (PSO), tabu search (TS), self-adaptive differential evolution (SADE), Taghchi’s method (TM), cuckoo search (CS), and biogeography-based optimization (BBO). The simulation results clearly indicate the superior performance of AFPA in optimizing LAA.