双种群差分进化规划算法  

Novel bi-group differential evolutionary programming

作　　者：何兵[1,2] 车林仙[1,2] 刘初升[1] 

机构地区：[1]中国矿业大学机电工程学院,江苏徐州221008 [2]泸州职业技术学院机电工程研究所,四川泸州646005

出　　处：《计算机工程与应用》2012年第26期25-31,共7页Computer Engineering and Applications

基　　金：四川省应用基础研究计划项目(No.2008JY0163);泸州市重点科技计划项目(No.2010-S-21(2/7))

摘　　要：标准差分进化算法(SDE)具有算法简单,控制参数少,易于实现等优点。但在难优化问题中,算法存在收敛速度较慢和容易早熟等缺陷。为克服此缺点,提出一种改进算法——双种群差分进化规划算法(BGDEP)。该算法将种群划分为两个子群独立进化,分别采用DE/rand/1/bin和DE/best/2/bin版本生成变异个体。每隔δt(取5～10)代,将两个子群合并为一个种群,再应用混沌重组算子将之划分为两个子群,以实现子群间的信息交流。在双种群协同差分进化的同时,应用非均匀变异算子对其最优个体执行进化规划操作,使得算法具有较快的收敛速度和较强的全局寻优能力。为测试BGDEP的性能,给出了4个30维benchmark函数优化问题的对比数值实验。结果表明,BGDEP的求解精度、收敛速度、鲁棒性等性能优于SDE、双种群差分进化(BGDE)和非均匀变异进化规划(NUMEP)等4种算法。The Standard Differential Evolution （SDE） algorithm has the advantages of simplicity, few control pa- rameters required, and easily be used, but has the disadvantage of premature convergence and relatively slow rate for hard optimization problems. The improved DE algorithm, namely Bi-Group Differential Evolutionary Program- ming（BGDEP）, is presented to overcome some drawbacks of the SDE algorithm. The proposed BGDEP algorithm divides the entire population into double subgroups which utilize DE/rand/I/bin and DE/best/2/bin schemes to gener- ate new mutate individuals to evolve next generation in parallel, respectively. In order to interact information be- tween double subgroups, the modified algorithm merges them into one whole population at intervals of ~t-periodic generations and divides subsequently this population into new double subgroups by using chaotic recombination op- erators. In every generation of co-evolution process of hi-group, the best individual in double subgroups is evolved by evolutionary programming with non-uniform mutation operators. Due to the above co-evolution, the proposed al- gorithm performs significantly fast and robust convergence, and performs a global exploratory search. 4 benchmark 30-dimensional functions in hard optimization fields are utilized to test comparatively performances of the new BGDEP algorithm and the experimental results show that this approach outperforms other 4 algorithms, such as SDEs （i.e., DE/rand/I/bin and DE/best/2/bin strategies）, Bi-Group Differential Evolution （BGDE） and Evolutionary Program- ming with Non-Uniform Mutation （NUMEP）, etc., in terms of solution accuracy, robustness, convergence speed and global exploring ability.

关 键 词：差分进化算法 进化规划算法 双种群 混沌重组策略 非均匀变异 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]