2018/02/13 by Mohammad Reza Bonyadi, Bonyadi, Mohammad Reza
Computer Science · #Advanced Multi-Objective Optimization Algorithms #Evolutionary Algorithms and Applications #FOS: Computer and information sciences #Metaheuristic Optimization Algorithms Research #Neural and Evolutionary Computing (cs.NE)
paper · pdf · doi:10.48550/arxiv.1802.04855
openalex publication_date 2018/02/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this paper we theoretically investigate underlying assumptions that have\nbeen used for designing adaptive particle swarm optimization algorithms in the\npast years. We relate these assumptions to the movement patterns of particles\ncontrolled by coefficient values (inertia weight and acceleration coefficient)\nand introduce three factors, namely the autocorrelation of the particle\npositions, the average movement distance of the particle in each iteration, and\nthe focus of the search, that describe these movement patterns. We show how\nthese factors represent movement patterns of a particle within a swarm and how\nthey are affected by particle coefficients (i.e., inertia weight and\nacceleration coefficients). We derive equations that provide exact coefficient\nvalues to guarantee achieving a desired movement pattern defined by these three\nfactors within a swarm. We then relate these movements to the searching\ncapability of particles and provide guideline for designing potentially\nsuccessful adaptive methods to control coefficients in particle swarm. Finally,\nwe propose a new simple time adaptive particle swarm and compare its results\nwith previous adaptive particle swarm approaches. Our experiments show that the\ntheoretical findings indeed provide a beneficial guideline for successful\nadaptation of the coefficients in the particle swarm optimization algorithm.\n