Darwinian Particle Swarm Optimization

Particle Swarm Optimization (PSO), an evolutionary algorithm for optimization is extended to determine if natural selection, or survival-of-thefittest, can enhance the ability of the PSO algorithm to escape from local optima. To simulate selection, many simultaneous, parallel PSO algorithms, each one a swarm, operate on a test problem. Simple rules are developed to implement selection. The ability of this so-called Darwinian PSO to escape local optima is evaluated by comparing a single swarm and a similar set of swarms, differing primarily in the absence of the selection mechanism, operating on the same test problem. The selection process is shown to be capable of evolving the best type of particle velocity control, which is a problem specific design choice of the PSO algorithm. 1. Particle Swarm Optimization (PSO) The PSO [1] approach utilizes a cooperative swarm of particles, where each particle represents a candidate solution, to explore the space of possible solutions to an optimization problem. Each particle is randomly or heuristically initialized and then allowed to ‘fly’. At each step of the optimization, each particle is allowed to evaluate its own fitness and the fitness of its neighboring particles. Each particle can keep track of its own solution, which resulted in the best fitness, as well as see the candidate solution for the best performing particle in its neighborhood. At each optimization step, indexed by t , each particle, indexed by i , adjusts its candidate solution (flies) according to, (1) 1 2 , , ( 1) ( ) ( ) ( ( 1) ( ) ( 1) i i i p i i n i i i v t v t x x x x x t x t v t φ φ + = + − + −