自适应柯西蜂群及其收敛性分析  

Artificial Bee Colony Algorithm Based on Adaptive Cauchy Mutation and Its Convergence Analysis

作　　者：张鑫[1] 陈国初[1] 公维祥[1] 

机构地区：[1]上海电机学院电气学院,上海200240

出　　处：《计算机系统应用》2015年第12期118-124,共7页Computer Systems & Applications

基　　金：上海市教委科研创新项目(13YZ140);上海市自然科学基金(11ZR1413900);上海市教委重点学科(J51901)

摘　　要：针对人工蜂群算法容易陷入局部最优的缺陷,提出一种自适应柯西变异人工蜂群算法.该算法引入自适应因子来扩大蜂群的搜索范围,并利用柯西分布的特点对全局进行搜索,提高了蜂群搜索的普遍性.然后利用随机过程理论,对自适应柯西变异人工蜂群算法进行了理论分析,论证了该算法的收敛性.最后将改进的人工蜂群算法应用到风电功率短期预测模型参数的优化中,与单一支持向量机模型比较,表明该方法拟合精度更高.As to the problem of failing into the local optimum in standard artificial bee colony, it is proposed to introduce an adaptive factor which can expand the search of the swarm and use the Cauchy distribution to improve the universality of colony search. This improved algorithm named adaptive Cauchy mutation artificial bee colony （ACMABC）. Then the ACMABC is analyzed in theory by using the theory of random process to prove the convergence of the algorithm. Finally, this modified method is applied to the optimization of the parameters of wind power short-term prediction model, compared with standard statistic strategy, an illustration with higher precision is given.

关 键 词：自适应 柯西变异 收敛性分析 风功率预测 应用 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]