具有自适应搜索策略的灰狼优化算法  

Grey Wolf Optimization Algorithm with Self-adaptive Searching Strategy

作　　者：魏政磊 赵辉[1] 韩邦杰[1,2] 孙楚[1] 李牧东[1] WEI Zheng-lei ZHAO Hui HAN Bang-jie SUN Chu LI Mu-dong(College of Aeronautics and Astronautics, Air Force Engineering University, Xi＇an 710038, China Military Delegate Office of Air Force, Handan 056004, China)

机构地区：[1]空军工程大学航空航天工程学院,西安710038 [2]空军驻石家庄地区军事代表室,邯郸056004

出　　处：《计算机科学》2017年第3期259-263,共5页Computer Science

基　　金：国家科学基金(71501184)资助

摘　　要：灰狼优化算法(Grey Wolf Optimization,GWO)是一种新型的群智能优化算法。与其他智能优化算法类似,该算法仍存在收敛速度慢、容易陷入局部极小点的缺点。针对这一问题,提出了具有自适应搜索策略的改进算法。为了提高算法的收敛速度和优化精度,通过适应度值控制智能个体位置,并引入了最优引导搜索方程;另一方面,为提高GWO的种群多样性,改进算法利用位置矢量差随机跳出局部最优。最后对10个标准测试函数进行了仿真实验,并与其他4种算法进行了比较,统计结果和Wilcoxon符号秩检验结果均表明,所提出的改进算法在收敛速度以及搜索精度方面具有明显优势。The grey wolf optimization algorithm （GWO） is a new type intelligence optimization algorithm. However, the GWO has the problem of low convergence speed and easily falling into local optimum as the same as other optimization algorithms. Aiming at this problem, an improved GWO with the self-adaptive searching strategy was proposed. Firstly, the search direction is controlled by fitness value and the best learning equation is introduced to improve the conver- gence speed and the optimization precision. Secondly, in order to maintain the population diversity, the position vector difference is utilized to escape from local optimum. Finally, 10 benchmarks and other four popular algorithms were com- pared to illustrate the superiority of GWO with the self-adaptive searching strategy. The experimental results and the Wilcoxon signed ranks test results show that the improved GWO outperforms the other four algorithms in terms of con- vergence speed and precision.

关 键 词：灰狼优化算法 自适应 最优学习搜索方程 Wilcoxon符号秩检验 函数优化 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]