A Particle Swarm Optimization Algorithm Based on Uniform Design

Abstract

The Particle Swarm Optimization (PSO) Algorithm is one of swarm intelligence optimization algorithms. Usually the population's values of PSO algorithm are random which leads to random distribution of search quality and search velocity. This paper presents PSO based on uniform design (UD). UD is widely used in various applications and introduced to generate an initial population, in which the population members are scattered uniformly over the search space. In evolution, UD is also introduced to replace some worse individuals. Based on abovementioned these technologies a Particle Swarm Optimization Algorithm based on Uniform Design (PSO-UD) algorithm is proposed. At last, the performance of PSO-UD algorithm is tested and compared. Tests show that the PSO-UD algorithm faster than standard PSO algorithm with random populations.

A Fuzzy-PID Controller Combined with PSO Algorithm for the Resistance Furnace

“…There are two fitness value are required in the update process of particles, that are pbest (personal best) and gbest (global best). The pbest value is trace in every iteration of particles and gbest value is computed among the best solution in pbest value [19]. In the PSO algorithm, the velocity value and position values of particles are continuously updated by following formulas.…”