A Comparative Study of Several Hybrid Particle Swarm Algorithms for Function Optimization

Currently, the researchers have made a lot of hybrid particle swarm algorithm in order to solve the shortcomings that the Particle Swarm Algorithms is easy to converge to local extremum, these algorithms declare that there has been better than the standard particle swarm. This study selects three kinds of representative hybrid particle swarm optimizations (differential evolution particle swarm optimization, GA particle swarm optimization, quantum particle swarm optimization) and the standard particle swarm optimization to test with three objective functions. We compare evolutionary algorithm performance by a fixed number of iterations of the convergence speed and accuracy and the number of iterations under the fixed convergence precision; analyzing these types of hybrid particle swarm optimization results and practical performance. Test results show hybrid particle algorithm performance has improved significantly.