Cooperative particle swarm optimizer with improved elimination mechanism for global optimization

This paper develops a new elimination mechanism strategy to improve the performance of cooperative particle swarm optimizer with elimination mechanism (CPSO-EM) algorithm which is proposed to extract better vector elements by analyzing features of cooperative particle swarm optimizer (CPSO). The extracting method is simple and has the potential to be improved. The proposed cooperative particle swarm optimizer with improved elimination mechanism (CPSO-IEM) makes two main changes in order to extract useful elements from elimination mechanism (EM) effectively. These changes not only increase the diversity of solution vectors which are stored in EM, but also improve the performance of cooperative particle swarm optimizer (CPSO) which is treated as a basic operator in CPSO-IEM. Experimental studies on a set of test functions show that CPSO-EM exhibits better performance than several other peer algorithms in solving nonseparable multimodal problems.