Particle Swarm Optimization Algorithm Based on Homogenized Chaos Mapping
Lei Zhao, Liyong Bao, Zheng Guan, Hongwei Ding · Proceedings of the 3rd International Conference on Computer Science and Application Engineering · 2019
Particle Swarm Optimization has some defects such as the rule of initial population selection and maybe get into the local extremum. In order to solve those shortcomings, this paper introduces an homogenized homogenized Logistic chaos mapping into the Particle Swarm Optimization algorithm. The modified time series has the characteristics of rapid divergence, strong ergodic, and high randomness. In this paper, the Particle Swarm Optimization is optimized by the above modified sequence, and a homogeneous chaos Particle Swarm Optimization algorithm is obtained. The particle position information and the initial velocity information are initialized by the linear transformation of the homogenized logistic sequence, so that the distribution of the particles is random and can traverse the value space of variables. At the same time, the chaos transformation of the optimal value in the particle population of each iteration makes the particle "mutate", thus ensuring the diversity of the particles in the iterative process.The experimental results show that the algorithm does not fall into the local extremum and has faster convergence.