A Modified Quantum Delta-Potential-Well-Based Particle Swarm Optimization
A novel PSO algorithm named Quantum delta-potential-well-based PSO (QDPSO) is developed in recent years. The QDPSO is inspired by quantum mechanics and updates the position of the particles by a different set of equations. Comparing the SPSO, it has fewer parameters to control and can be demonstrated mathematically to be a global convergent algorithm. However, as other evolutionary algorithm such as SPSO and GA, QDPSO also encounter premature convergence problem. In this paper, two learning coefficients and transitional particles are introduced into Quantum Delta-Potential-Well-based Particle Swarm Optimization to increase its global search ability and escape from local minima. The experiment results on some well-known benchmark functions show the better performance of the improved QDPSO.
Weili Xiong Chongpeng Huang Jun Sun Baoguo Xu
School of control and communication engineering Southern Yangtze University Wuxi, 214122,Jiangsu, Ch School of Information Engineering Southern Yangtze University Wuxi, 214122,Jiangsu, China School of control and communication engineering Southern Yangtze University Wuxi, 214122,Jiangsu , C
国际会议
南宁
英文
2007-07-20（万方平台首次上网日期，不代表论文的发表时间）