摘要
针对实数编码的遗传算法容易掉入局部极值、收敛速度慢等缺点,提出一种改进的实数编码的遗传算法,并对其进行了基于GPU的并行化实现.通过4个典型的遗传算法性能测试函数进行测试,结果表明,改进后的算法可以有效地跳出局部极值点,并能加快算法的收敛速度;在求解复杂的高维函数时,并行化后的改进算法可以显著减少算法的运行时间.
Aiming at the shortcoming of the real-coded genetic algorithm, which is easy to fall into local extremum and slow convergence speed, an improved real-coded genetic algorithm is proposed and implemented by GPU-based parallelization. Through four typical genetic algorithm performance test functions, the results show that the improved algorithm can not only effectively jump out of the local extremum , but also accelerate the convergence speed of the algorithm;When solving complex high-dimensional functions, the improved parallel algorithm can significantly reduce the running time of the algorithm .
作者
刘振鹏
王雪峰
薛雷
张彬
张寿华
LIU Zhenpeng;WANG Xuefeng;XUE Lei;ZHANG Bin;ZHANG Shouhua(School of Cyberspace Security and Computer,Hebei University,Baoding 071002,China;Information Technology Center,Hebei University,Baoding 071002,China)
出处
《河北大学学报（自然科学版）》
CAS
北大核心
2019年第1期86-92,共7页
Journal of Hebei University(Natural Science Edition)
基金
河北省创新能力提升计划项目(179676278D
17455309D)
教育部"云数融合"科教创新基金资助项目(2017A20004)
关键词
遗传算法
实数编码
算法改进
GPU并行
genetic algorithm
real-coded
algorithm improvement
GPU parallel
