Runtime Analysis of Pigeon-Inspired Optimizer Based on Average Gain Model

Abstract

The pigeon-inspired optimization (PIO) algorithm is a novel swarm intelligence optimizer inspired by the homing behaviors of pigeons. Although PIO has demonstrated effectiveness and superiority in numerous fields, there are few results about the theoretical foundation of PIO. This paper employs the average gain model to estimate the upper bound for the expected first hitting time of PIO in continuous optimization. The case study and experiment result indicate that our theoretical analysis is applicable to the general case where the population size and problem size are both larger than 1, which is close to the practical situation.