ABSTRACT
Optimization techniques based on behaviors of some animal species in natural environment are strongly developed. Algorithms simulating behaviors of bees colony, ants colony, and birds flock have appeared. The last algorithm is named in the literature as a particle swarm optimization (PSO) algorithm, and is a new technique dedicated to optimization problems having continuous domain. However, its modifications to optimize discreet problems have been developed lately. The PSO algorithm has many common features with evolutionary computation techniques. This algorithm is operating on randomly created population of potential solutions, and is searching optimal solution through the creation of successive populations of solutions. Genetic operators like cross-over and mutation, which exist in evolutionary algorithms, are not used in the PSO algorithm. In this algorithm, potential solutions are moving to the actual optimum in the solution space. There exist two versions of PSO algorithm: local, LPSO, and global, GPSO, algorithm.
