Research On Improved Particle Swarm Algorithm Based On Chaotic Mapping

Intelligent optimization is one of the research hot topics both in the fields of information and computer science during recent years.How to improve the search performance of these algorithms in a complex environment is one of the key problems in this field.Particle Swarm Optimization(PSO)is an emerging intelligent optimization algorithm,which has many advantages such as with fewer parameters,easy to use,and good performance,so it has been widely used.Presently,PSO has been used to many different fields such as unconstrained function optimization,constrained optimization,vehicle routing scheduling,robot path planning,transportation,supply chain optimization,power system,medical treatment as well as communication,and has achieved fruitful results.However,it is also prone to premature convergence,slow convergence in the late iterations,poor robustness and other shortcomings,especially when dealing with high-dimensional complex problems it may fall into a local optimum.In order to improve the search performance of PSO deeply,based on a thorough analysis of adaptive PSO and Simulated Annealing,an improved PSO named Adaptive Annealing Particle Swarm Algorithm which combines chaotic mapping and SA is proposed.The main idea is to use the particle population information to add a chaotic perturbation operator near a local optimal solution,so that it has the ability to jump from local optima,and then improve the global search ability of PSO.Inertia factor is also modified by a new linear acceleration factor in order to improve the performance of the algorithm.The performance of the improved PSO is verified by numerical experiments on different types of function optimization problems.The results show that the improved algorithm is superior both to the adaptive PSO and to SA,especially for problems with multiple local optima.Finally,in order to study the effect of different chaotic maps on the performance of PSO,three chaotic maps,namely Logistic map,Tent map and Cat map,are combined with the improved PSO respectively to test its performance.Ten common test functions are used for comparison.Simulation results show that chaotic disturbance operator has different effect the performance of improved PSO.