一种自适应变步长的Alopex算法  

A SELF-ADAPTIVE AND VARIABLE STEPWISE ALOPEX ALGORITHM

作　　者：吴翠娟[1] 李冬[1] 

机构地区：[1]苏州经贸职业技术学院,江苏苏州215009

出　　处：《数值计算与计算机应用》2010年第3期200-205,共6页Journal on Numerical Methods and Computer Applications

摘　　要：Alopex算法是一种启发式与随机优化相结合的算法.本文在改进的Alopex算法的基础上,提出了一种具有自适应能力的变步长的Alopex算法,使其能够更好的跳出局部最优解和逼近全局最优解;并且为了进一步提高改进的Alopex算法的逼近精度以及消除该算法在后期可能出现的振荡现象,提出了一种合理的改变δ_(in)的方法.仿真试验表明,这种改进是可行的,而且是有效的.Alopex is a heuristic and optimum algorithm. A self-adaptive and variable stepwise Alopex algorithm developed to exclude local optimal solution and to approximate global optimal solution based on modified Alopex algorithm. To improve modified Alopex approx- imation precision and eliminate the follow-on shocks appearance, the reasonable alternation of δin was implemented. The simulation results show algorithm optimized is practicable and effective.

关 键 词：ALOPEX算法 自适应 步长 

分 类 号：O224[理学—运筹学与控制论]