Particle Swarm Optimization with Ensemble of Inertia Weight Strategies.
ADVANCES IN SWARM INTELLIGENCE, ICSI 2017, PT I(2017)
摘要
Particle swarm optimization (PSO) has gained significant attention for solving numerical optimization problems in different applications. However, the performance of PSO depends on the appropriate setting of inertia weight and the optimal setting changes with generations during the evolution. Therefore, different adaptive inertia weight strategies have been proposed. However, the best inertia weight adaptive strategy depends on the nature of the optimization problem. In this paper, different inertia weight strategies such as linear, Gompertz, logarithmic and exponential decreasing inertia weights as well as chaotic and oscillating inertia weight strategies are explored. Finally, PSO with an adaptive ensemble of linear & Gompertz decreasing inertia weights is proposed and compared with other strategies on a diverse set of benchmark optimization problems with different dimensions. Additionally, the proposed method is incorporated into heterogeneous comprehensive learning PSO (HCLPSO) to demonstrate its effectiveness.
更多查看译文
关键词
Particle swarm optimization,Ensemble of inertia weight strategies,Gompertz decreasing inertia weight,Linear decreasing inertia weight
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络