Research On Elite Particle Swarm Optimization Algorithm Based On Adaptive Normal Distribution

Particle swarm optimization(PSO)is a heuristic global optimization algorithm,which is one of the most commonly used optimization techniques.The algorithm is based on the original model of the birds and fish,which is composed of a plurality of independent individuals.Particle swarm optimization(PSO)is a miniature artificial biological system.Particle swarm optimization(PSO)can be used to find the global optimum in some complex search space through the competition and cooperation among particles.Its characteristics are as follows:easy to understand,easy to implementation and strong global search capability,etc..Now,it has been widely concerned by scholars in the field of computer science and has become one of the most popular swarm intelligence algorithms.Therefore,the research of PSO algorithm analysis and improvement strategy has a very important practical significance for the reality of social production and so on.This paper first describes the research background and significance of swarm intelligence,and illustrates the research status at home and abroad.Secondly,the characteristics of swarm intelligence and several common swarm intelligence algorithms are introduced.Then,the work we have done in the principle,the standard PSO algorithm parameters were as follows:(1)the setting of inertia weight and learning factors of PSO algorithm is improved by the cosine function to adjust the inertia weight and linear decreasing function to adjust the learning factor;(2)the best position of each individual and the optimal position in swarm are updated by using the normal perturbation strategy to enhance the diversity of the population.This proposed method effectively avoids falling into the local optimum;(3)based on the improvement of above work,the elite particle swarm optimization algorithm can effectively use the information of elite particles to update the individuals in the swarm,which successfully improve the speed of convergence.At the end of this paper,the research work of this thesis is summarized and the future work is prospected.