摘要
粒子群算法是一种进化计算技术,并成功的运用于广泛的数值优化问题。PSO算法在求解高维复杂函数优化问题时容易陷入局部最优。有鉴于此,本文提出了一种基于信息熵的粒子优化算法。该算法提高设计了一种兼顾种群选择性压力以及种群多样性的选择策略,从而提高了粒子在运行过程中的多样性。实验表明,该算法有效避免了陷入局部最优,提高了全局最优解的搜索精度。
Particle Swarm Optimization(PSO)algorithm which has been shown to successfully optimize a wide range of continuous functions.PSO easily plunge into the local minimum when it solve the complex high dimension function optimization problem.Thus this paper proposes a new PSO based on information entropy,which give attention to population selective pressure and population diversity,improve the diversity of swam.The algorithm can not only escape from local minimum,but also enhance the capability to search the global optimization.
出处
《微型电脑应用》
2008年第5期31-33,5,共3页
Microcomputer Applications
关键词
粒子群优化算法
信息熵
种群多样性
Particle Swarm Optimization
Information Entropy
Diversity of swarm
