一种自适应差分演化算法  

AN ADAPTIVE DIFFERENTIAL EVOLUTION ALGORITHM

作　　者：毛润宇[1] 王小平[1] 薛小平[2] 

机构地区：[1]同济大学计算机科学与技术系,上海200092 [2]同济大学信息与通信工程系,上海200092

出　　处：《计算机应用与软件》2008年第12期7-8,26,共3页Computer Applications and Software

基　　金：国家自然科学基金项目(60475019)

摘　　要：差分演化算法是一类基于种群的启发式全局搜索技术,对于实值参数的优化具有很强的鲁棒性。为了提高差分演化算法的寻优速度、克服启发式算法常见的早熟收敛问题,提出了一种自适应的方法来调整控制参数。实验表明,算法的收敛速度和寻优能力得到很大的提高。Differential evolution （DE） is a new heuristic global searching technique based on population, which has been found to be very robust for real parameter＇ s optimization. In order to accelerate the convergence speed of DE algorithm in optimal searching and to overcome the premature convergence which is frequently existed in heuristic algorithms, in this paper it proposed an adaptive differential evolution algorithm to adjust the scale factor and the crossover probability adaptively. The experiment indicated that this algorithm improves remarkably the convergence speed and optimal searching ability.

关 键 词：差分演化 自适应 优化 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构] TP273.2[自动化与计算机技术—计算机科学与技术]