摘要
针对复杂函数的最优化的遗传退火算法,此文提出了一种基于邻域函数的尺度参数自寻优和多操作的基于概率接受思想的变异操作及竞争生存的种群数量控制策略的改进遗传退火算法。基于典型算例的仿真结果验证了本文算法对高维复杂函数最优化的有效性和高效性,其性能明显优于传统遗传退火算法、改进的进化规划方法以及遗传-ALOPEX算法。
Aimed to global optimization for complex functions, this paper proposes an improved simulated annealing with neighbor function based on self-optimization of scale parameter. Furthermore, with multi-operator mutations based on probabilistic acceptance, combining the improved annealing into genetic algorithm, an improved genetic-annealing algorithm is proposed. Simulation results based on some benchmarks demonstrate the effectiveness and efficiency of the proposed algorithms applied to high-dimensional complex functions, whose performances are quite better than those of classic genetic-annealing, improved evolutionary programming and genetic-ALOPEX methods.
出处
《系统仿真学报》
CAS
CSCD
2001年第z1期111-113,共3页
Journal of System Simulation
关键词
函数优化
遗传算法
模拟退火
遗传退火
function optimization
genetic algorithm
simulated annealing
genetic-annealing