采用动态权重和概率扰动策略改进的灰狼优化算法

发布时间：2018-01-08 11:34

本文关键词：采用动态权重和概率扰动策略改进的灰狼优化算法　出处：《计算机应用》2017年12期 　论文类型：期刊论文

【摘要】：针对基本灰狼优化(GWO)算法存在易陷入局部最优,进而导致搜索精度偏低的问题,提出了一种改进的GWO(IGWO)算法。一方面,通过引入由GWO算法系数向量构成的权值因子,动态调整算法的位置向量更新方程;另一方面,通过采用概率扰动策略,增强算法迭代后期的种群多样性,从而提升算法跳出局部最优的能力。对多个基准测试函数进行仿真实验,实验结果表明,相对于GWO算法、混合GWO(HGWO)算法、引力搜索算法(GSA)和差分进化(DE)算法,所提IGWO算法有效摆脱了局部收敛,在搜索精度、算法稳定性以及收敛速度上具有明显优势。
[Abstract]:In order to solve the problem that the basic gray wolf optimization (GWOO) algorithm is easy to fall into local optimum, which leads to low searching precision, an improved GWOO algorithm is proposed. On the one hand, an improved GWOO algorithm is proposed. The position vector updating equation of the algorithm is dynamically adjusted by introducing the weight factor which is composed of the coefficient vector of the GWO algorithm. On the other hand, by using probabilistic perturbation strategy to enhance the diversity of population in the late iteration stage of the algorithm, thus enhancing the ability of the algorithm to jump out of the local optimum. The simulation results of several benchmark functions show that. Compared with the GWO algorithm, the hybrid IGWO algorithm, the gravity search algorithm and the differential evolution algorithm, the proposed IGWO algorithm can effectively get rid of the local convergence and the search accuracy. The algorithm has obvious advantages in terms of stability and convergence speed.
【作者单位】：南京工业大学电气工程与控制科学学院;桂林理工大学测绘地理信息学院;
【分类号】：TP18
【正文快照】： 0引言近20年来,元启发式算法得到了迅速发展。它源自于自然现象的启发,在解决复杂计算问题时提供了一种新的手段,典型的有遗传算法(Genetic Algorithm,GA)[1]、粒子群(Particle Swarm Optimization,PSO)算法[2]、差分进化(Differential Evolution,DE)算法[3]、引力搜索算法(Gr

【相似文献】