摘要
为了提高QPSO算法的收敛性能,在对随机因子进行分析的基础上提出了三元相关性QPSO(TC-QPSO,ternary correlation QPSO)算法。该算法使用正态Copula函数建立了粒子对自身经验信息、群体共享信息以及粒子当前位置与群体平均最好位置的距离信息之间的内在认知和联系,并利用Cholesky平方根公式给出了三元相关因子的生成方法。对测试函数的仿真结果证明,当三元相关因子u与r1或r2之间存在负线性相关关系时,TC-QPSO算法可以获得比标准QPSO算法更好的优化性能。
In order to more effectively utilize existing information and improve QPSO＇s （quantum-behaved particle swarm optimization） convergence performance, the ternary correlation QPSO （TC-QPSO） algorithm was proposed based on the analysis of the random factors in location formula. The novel algorithm changed the information independent ran- dom processing method of standard QPSO and established internal relations during particles＇ own experience information, group sharing information and the distance from the particles＇ current location to the population mean best position using normal copula functions.Then, the method of generating ternary correlation factors was given by using the Cholesky square root formula. The simulation results of the test functions showed that TC-QPSO algorithm outperforms the stan- dard QPSO algorithm in terms of optimization results, given that the negative linear correlation exists betweenu and rl or u and r2.
出处
《通信学报》
EI
CSCD
北大核心
2015年第3期207-214,共8页
Journal on Communications
基金
国家自然科学基金资助项目(61104175)
四川省软科学研究计划基金资助项目(2012ZR0022)
四川省科技支撑计划基金资助项目(2012GZX0090)~~
关键词
粒子群优化
量子粒子群优化
量子势阱
正态Copula函数
收敛
particle swarm optimization （PSO）
quantum-behaved particle swarm optimization （QPSO）
quantum poten-tial well
normal copula function
convergence
