摘 要：针对狼群算法在迭代过程中逐渐失去多样性及分布性的问题，提出一种基于组合变异的平衡灰狼优化算法BGWO。通过融入 metropolis 准则的等温过程，有效加快算法的收敛速度。通过引入转换概率组合两种变异策略对 alpha 狼进行变异，来控制种群聚散的特征，使算法具备跳出局部极值的能力。最后，将所提算法 BGWO 与 EOGWO、EGWO、CGWO 在IEEE CEC2013 基准函数集上相比，所提算法的求解效率显著提升。实验结果表明，所提算法具有良好的收敛性，算法收敛精度更高，寻优能力更强。
关键词：群智能；灰狼优化；模拟退火；组合变异；metropolis 准则；等温过程
DOI:10.19850/j.cnki.2096-4706.2021.18.027
基金项目：新疆师范大学数据安全重点实验 室招标课题（XJNUSYS102018B01）；新疆师范 大学优秀青年教师科研启动基金（XJNU201814）
中图分类号：TP301.6 文献标识码：A 文章编号：2096-4706（2021）18-0106-05
A Balanced Gray Wolf Optimization Algorithm Based on Combinatorial Variation
GE Yang, HU Chuangye
(College of Computer Science and Technology, Xinjiang Normal University, Urumqi 830094, China)
Abstract: Aiming at the problem that the wolf swarm algorithm gradually loses its diversity and distribution in the iterative process, a balanced gray wolf optimization algorithm based on combinatorial variation (BGWO) is proposed. By incorporating the isothermal process of metropolis criterion, the convergence speed of the algorithm is effectively accelerated. Through introducing transformation probability to combine two mutation strategies for alpha volf mutation, so as to control the characteristics of population aggregation and dispersion, making the algorithm has the ability to jump out of local extremum. Finally, the proposed algorithm BGWO is compared with EOGWO, EGWO and CGWO in IEEE CEC2013 benchmark function set. The efficiency of the proposed algorithm is significantly improved. Experimental results show that the proposed algorithm has good convergence, higher convergence accuracy and stronger optimization ability.
Keywords: swarm intelligence; gray wolf optimization; simulated annealing; combinatorial variation; metropolis criterion; isothermal process
参考文献：
[1] STORN R，PRICE K. Differential Evolution—A Simple and Efficient Heuristic for global Optimization over Continuous Spaces [J]. Journal of Global Optimization，1997，11：341-359.
[2] 黄戈文 , 蔡延光 , 戚远航 , 等 . 自适应遗传灰狼优化算法求解带容量约束的车辆路径问题 [J]. 电子学报，2019，47（12）： 2602-2610.
[3] 晏福 , 徐建中 , 李奉书 . 混沌灰狼优化算法训练多层感知器 [J]. 电子与信息学报，2019，41（4）：872-879.
[4] 胡小平 , 曹敬 . 改进灰狼优化算法在 WSN 节点部署中的应用 [J]. 传感技术学报，2018，31（5）：753-758.
[5] DRAA A，BOUZOUBIA S，BOUKHALFA I. A sinusoidal differential evolution algorithm for numerical optimization [J].Applied Soft Computing，2015，27：99-126.
[6] LI X T，YIN M H. Modified differential evolution with selfadaptive parameters method [J].Journal of Combinatorial Optimization， 2016，31：546–576.
[7] ZENG Y R，PENG L，ZHANG J，et al. An Effective Hybrid Differential Evolution Algorithm Incorporating Simulated Annealing for Joint Replenishment and GWOlivery Problem with TraGWO Credit [J]. International Journal of Computational Intelligence Systems，2016，9 （6）：1001-1015.
[8] ZHENG Y J，XU X L，LING H F，et al. A hybrid fireworks optimization method with differential evolution operators [J]. Neurocomputing，2015，148：75-82.
[9] CHEN B，ZENG W，LIN Y，et al. An Enhanced Differential Evolution Based Algorithm with Simulated Annealing for Solving Multiobjective Optimization Problems [J/OL].Journal of Applied Mathematics，2014，2014[2021-06-31].https://www.hindawi.com/ journals/jam/2014/931630/.
[10] JADON S S，TIWARI R，SHARMA H，et al. Hybrid Artificial Bee Colony algorithm with Differential Evolution [J].Applied Soft Computing，2017，58：11-24.
[11] ZORARPACI E，ÖZEL S A. A hybrid approach of differential evolution and artificial bee colony for feature selection [J]. Expert Systems with Applications，2016，62：91-103.
[12] 刘爱军，杨育，李斐等 . 混沌模拟退火粒子群优化算法研究及应用 [J]. 浙江大学学报（工学版），2013，47（10）：1722-1730.
[13] TAN Y，ZHU Y. Fireworks Algorithm for Optimization [C]// Proceedings of the First international conference on Advances in Swarm Intelligence. Berlin：Springer，2010：355-364.
[14] ELSAYED S M，SARKER R A，RAY T. Differential evolution with automatic parameter configuration for solving the CEC2013 competition on Real-Parameter Optimization [C]//2013 IEEE Congress on Evolutionary Computation.Cancun，Mexico：IEEE，2013：1932-1937.
[15] 黄晨晨，魏霞，黄德启，等 . 求解高维复杂函数的混合蛙跳 - 灰狼优化算法 [J]. 控制理论与应用，2020，37（7）： 1655-1666.
作者简介：戈阳（1992.05—），男，汉族，江苏泗阳人，助教，硕士研究生，研究方向：群智能优化算法的研究与应用。