Psogp: a Genetic Programming Based Adaptable Evolutionary Hybrid Particle Swarm Optimization

In this study we describe a method for extending particle swarm optimization. We have presented a novel approach for avoiding premature convergence to local minima by the introduction of diversity in the swarm. The swarm is made more diverse and is encouraged to explore by employing a mechanism which allows each particle to use a different equation to update its velocity. This equation is also continuously evolved through the use of genetic programming to ensure adaptability. We compare two variations of our algorithm, one utilizing random initialization while in the second one we utilize partial non-random initalization which forces some particles to use the standard PSO velocity update equation. Results from experimentation suggest that the modified PSO with complete random initialization shows promise and has potential for improvement. It is particularly very good at finding the exact optimum.