1 简介
This paper proposes a new hybrid optimization algorithm, called ‘‘(HSSOGSA)’’ with the combination of ‘‘gravitationalsearch algorithm (GSA)’’ and ‘‘sperm swarm optimization (SSO)’’. The underlying concepts and ideas behind the proposedalgorithm are to combine the capability of exploitation in SSO with the capability of exploration in GSA to synthesize bothalgorithms’ strength. To evaluate the effificiency of the proposed approach, different test bed problems of optimization areconsidered, called the ‘‘congress on evolutionary computation (CEC)’’ 2017 suite. The proposed HSSOGSA is comparedagainst both the standard GSA and SSO algorithms. These algorithms are compared based on two mechanisms, including,qualitative and quantitative tests. For the quantitative test, we adopt best fifitness, standard deviation, and average measures,while for the qualitative test, we compare between the convergence rates achieved by the proposed algorithm and theconvergence rates achieved by SSO and GSA. The outcomes of the study present the hybrid method possesses a bettercapability and performance to escape from local extremes with faster rate of convergence than the standard SSO and GSAfor the majority of benchmarks functions of wide and narrow search space domain.
2 部分代码
%HSSOGSA source code, Generated by Hisham A. Shehadeh, 2021.
%Adopted from: Hisham A. Shehadeh, 鉄hehadeh, H. A. (2021). A hybrid sperm swarm
% This function gives boundaries and dimension of search space for test functions.
function [down,up,dim]=benchmark_functions_details(Benchmark_Function_ID)
%If lower bounds of dimensions are the same, then 'down' is a value.
%Otherwise, 'down' is a vector that shows the lower bound of each dimension.
%This is also true for upper bounds of dimensions.
%Insert your own boundaries with a new Benchmark_Function_ID.
dim=30;
if Benchmark_Function_ID==1
down=-100;up=100;
end
if Benchmark_Function_ID==2
down=-10;up=10;
end
if Benchmark_Function_ID==3
down=-100;up=100;
end
if Benchmark_Function_ID==4
down=-100;up=100;
end
if Benchmark_Function_ID==5
down=-30;up=30;
end
if Benchmark_Function_ID==6
down=-100;up=100;
end
if Benchmark_Function_ID==7
down=-1.28;up=1.28;
end
if Benchmark_Function_ID==8
down=-500;up=500;
end
if Benchmark_Function_ID==9
down=-5.12;up=5.12;
end
if Benchmark_Function_ID==10
down=-32;up=32;
end
if Benchmark_Function_ID==11
down=-600;up=600;
end
if Benchmark_Function_ID==12
down=-50;up=50;
end
if Benchmark_Function_ID==13
down=-50;up=50;
end
if Benchmark_Function_ID==14
down=-65.536;up=65.536;dim=2;
end
if Benchmark_Function_ID==15
down=-5;up=5;dim=4;
end
if Benchmark_Function_ID==16
down=-5;up=5;dim=2;
end
if Benchmark_Function_ID==17
down=[-5;0];up=[10;15];dim=2;
end
if Benchmark_Function_ID==18
down=-2;up=2;dim=2;
end
if Benchmark_Function_ID==19
down=0;up=1;dim=3;
end
if Benchmark_Function_ID==20
down=0;up=1;dim=6;
end
if Benchmark_Function_ID==21
down=0;up=10;dim=4;
end
if Benchmark_Function_ID==22
down=0;up=10;dim=4;
end
if Benchmark_Function_ID==23
down=0;up=10;dim=4;
end
3 仿真结果
4 参考文献
Mirjalili S, Lewis A (2016) The whale optimization algorithm.Adv Eng Softw 95:51–67. https://doi.org/10.1016/j.advengsoft.2016.01.0082. Fausto F, Reyna-Orta A, Cuevas E, Andrade A´ G, Perez-CisnerosM (2020) From ants to whales: metaheuristics for all tastes. ArtifIntell Rev 53(1):753–810. https://doi.org/10.1016/j.advengsoft.2016.01.008
博主简介：擅长智能优化算法、神经网络预测、信号处理、元胞自动机、图像处理、路径规划、无人机等多种领域的Matlab仿真，有科研问题可私信交流。
部分理论引用网络文献，若有侵权联系博主删除。
