This repository contains a basic implementation of the Particle Swarm Optimization (PSO) algorithm. The code has been evaluated using several benchmark functions, both with and without constraints. A quadratic penalty method was employed for handling constraints.
Particle Swarm Optimization (PSO) is a population-based stochastic optimization technique inspired by the social behavior of birds flocking or fish schooling. This repository provides a fundamental PSO algorithm implementation designed to solve optimization problems with and without constraints using a quadratic penalty method.
The PSO algorithm has been tested on various benchmark functions.
The quadratic penalty method is used to handle constraints in the optimization process. This method adds a penalty term to the objective function for any violation of constraints, thereby guiding the swarm towards feasible solutions.
This implementation and methodology are based on the following seminal works in PSO:
CLERC, Maurice; KENNEDY, James. "The particle swarm-explosion, stability, and convergence in a multidimensional complex space." IEEE transactions on Evolutionary Computation, v. 6, n. 1, p. 58-73, 2002.
KENNEDY, James; EBERHART, Russell. "Particle swarm optimization." In: Proceedings of ICNN'95-international conference on neural networks. IEEE, 1995. p. 1942-1948.
PARSOPOULOS, Konstantinos E. et al. "Particle swarm optimization method for constrained optimization problems." Intelligent technologies–theory and application: New trends in intelligent technologies, v. 76, n. 1, p. 214-220, 2002.