关键词: 粒子群优化, 局部最优, 哈夫曼编码, 哈夫曼算法, 哈夫曼树

Abstract: Aiming at particle swarm optimization (PSO) algorithm easy to fall into local optimal problems in optimizing a population, a new particle swarm optimization on Huffman Coding (HCPSO) algorithm was put forward. Using Huffman Coding, one population will be divided into two sub populations, and each subpopulation will be optimized independently. At the same time, the two subpopulations cooperatively complete searching the global optimum solution.Through six standard test functions, the experimental results show that the algorithm can effectively avoid the population falling into local optimum, is of better optimization performance and stability, and convergence accuracy is significantly improved.

Key words: particle swarm optimization, local optimal, Huffman coding, Huffman algorithm, Huffman tree