ABSTRACT
This chapter focuses on the advantages of introducing Particle swarm optimization (PSO) into the mutation process of genetic algorithm (GA), for improving the GA learning efficiency. It describes the PSO concept in terms of its precursors, briefly reviewing the stages of its development from social simulation to optimizer for science and engineering area. The chapter discusses application of this algorithm to the training of algorithms. Using the conventional GA or PSO approach optimal solutions are obtained mostly with some initially the differentiated data and there is a high possibility for obtaining local optimal solutions. PSO developed by the concept, and paradigms can be implemented in a few lines of computer code. PSO is an extremely simple algorithm that seems to be effective for optimizing a wide range of functions. The GA-PSO system proposed in for proportional-integral-derivative controller tuning could be easily extended to model other complex problems involving local optimal and global optimal solutions.
