Research And Application Of Hybrid Particle Swarm Algorithm

Particle swarm optimization algorithm is an evolutionary computation technique based on swarm intelligence method, it is a population-based optimization tool, but also an optimization tool based on iteration. The basic idea of particle swarm optimization algorithm is to find the optimal solution through cooperation and information sharing between individuals in groups, the system is initialized with a set of random solutions, through iterative search the optimal solution, particle (potential solutions) to search in the solution space to follow the optimal particle. Particle swarm optimization algorithm is simple, the search speed and range, just a few codes and parameters, easy to realize and easy to adjust parameters, so it is widely used in various fields.Found that particle swarm algorithm is easy to premature convergence in the long-term practice, taking into account the artificial immune algorithm can use the diversity in the immune system to maintain the diversity of population, this article will introduce the idea of artificial immune particle swarm optimization algorithm to design a hybrid artificial immune particle swarm algorithm. The basic idea of the hybrid algorithm is the particles in particle swarm algorithm simultaneously considered immune antibodies, the fitness evaluation of particles is consistent with the evaluation of antibody affinity.Numerical analysis and experiments show that the hybrid algorithm not only has the advantage of improved particle swarm optimization algorithm, but also effectively maintain the diversity of the population, avoiding premature convergence disadvantage. The PSO and immune particle swarm algorithm are applied to both logistics distribution center location problem, the performance of the algorithm were compared, the numerical results show that the immune system can effectively avoid the conventional particle swarm easily premature convergence defects.