基于混沌透镜成像学习的哈里斯鹰算法及其应用

Harris Hawks Optimization Based on Chaotic Lens Imaging Learning and Its Application

针对哈里斯鹰算法(HHO)很难在探索和开发之间取得平衡,且易陷于局部最优和种群低多样性等问题,本文提出一种基于混沌透镜成像学习的哈里斯鹰算法(FLHHO)。首先,利用Fuch无限折叠混沌策略初始化种群,丰富种群多样性;其次,在探索阶段引入黄金正弦策略,提高算法的求解精度;最后,利用混合透镜成像学习和柯西变异策略,对哈里斯鹰最佳位置进行扰动,提高算法跳出局部最优的能力。将改进后的哈里斯鹰算法(FLHHO)在10个经典测试函数和29个CEC2017测试函数上进行求解精度,仿真结果表明,FLHHO算法优于HHO算法、其他改进HHO算法和其他最新算法。同时,将FLHHO应用到工业物联网中来优化频谱分配,将能量效率作为评价指标,实验结果表明基于FLHHO算法的能量效率优于其他算法,验证了FLHHO应用到实际中的可行性。

Harris’s Hawk algorithm(HHO)is difficult to strike a balance between exploration and development.It is easy to get into the problems of local optimum and low diversity of population.To solve these problems,a new Harris’s Hawk algorithm based on chaotic Lens Imaging Learning(FLHHO)is proposed.First,it uses Fuch chaotic strategy to initialize the population and enrich the diversity of the population.Second,it uses golden sine strategy to improve the precision of the algorithm in the exploration phase.Finally,it uses hybrid lens imaging learning and Cauchy mutation strategy,the best position of the Harris’s Hawk is disturbed to improve the ability of the algorithm to jump out of local optimum.The improved Harris’s Hawk algorithm(FLHHO)is applied to 10 classical test functions and 29 CEC2017 test functions.The simulation results show that the FLHHO algorithm is superior to HHO algorithm,other improved HHO algorithm and other new algorithms.Meanwhile,FLHHO is applied to the industrial Internet of things to optimize spectrum allocation,and the energy efficiency is taken as the evaluation index.The experimental results show that the energy efficiency based on FLHHO algorithm is better than other algorithms,which verifies the feasibility of FLHHO application in practice.