main_cell_li.m

多种群的链式智能体遗传算法

function [best_fit,best_fitvalue,out_dai,pop_best,time]=main_cell_li(pop,n,popsize,chromlength,fun_num,up_range,down_range,var_num)
%函数说明
%入口参数：pop         当前处理的种群,
%          n           绝对上限,
%          popsize     种群大小,
%          chromlength 基因位长度,
%          fun_num     函数序列号,
%          up_range    自变量的相对上限,
%          down_range  自变量的相对下限
%出口参数：best_fit    各代最有适应度值的集合
%功能说明：初始种群pop通过遗传交叉变异在给定定义域中寻优，在遗传最大代数dai之前得到最优值就自动退出遗传，
%          判定最优值的标准：前后两代间最优值之间差值连续30次小于 阈值0.00001
%          如果达到遗传最大代数也没有达到退出标准，则强制结束遗传。

% clear all;
% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% pop = [];
% 
% var_num = 2;
% % fun_num=6;
% % fun_num = 11;
% fun_num = 1;
% 
% switch fun_num
%     case 1
%         n=20000;
%         chromlength=15; %字符串长度（个体长度），染色体长度
%         fun_max=20000;
%         
%     case 2
%         n=2000;
%         chromlength=11; %字符串长度（个体长度），染色体长度
%         fun_max=121;
%     
%     case 3 %worse
%         n=20000;
%         chromlength=15; %字符串长度（个体长度），染色体长度
%         fun_max=50000;
%         
%     case 4
%         n=20000;
%         chromlength=15; %字符串长度（个体长度），染色体长度
%         fun_max=20000;
%         
%     case 5 %use short time
%         n=60000;
%         chromlength=16; %字符串长度（个体长度），染色体长度
%         fun_max=87000000;
%       
%     case 6 % only a little
%         n=20000;
%         chromlength=15; %字符串长度（个体长度），染色体长度
% 
%         
%     case 7 % rand
%         n=25600;
%         chromlength=15; %字符串长度（个体长度），染色体长度
%         fun_max=30;
%         
%     case 8 %much better
%         n=100000;
%         chromlength=17; %字符串长度（个体长度），染色体长度
%         fun_max=1500;
%         
%     case 9 % only a little
%         n=102400;
%         chromlength=17; %字符串长度（个体长度），染色体长度
%         fun_max=120;
%         
%     case 10 %only a little
%         n=64000;
%         chromlength=16; %字符串长度（个体长度），染色体长度
%         fun_max=30;
%         
%     case 11 % good
%         n=120000;
%         chromlength=17; %字符串长度（个体长度），染色体长度
%         fun_max=200;
%         
%     case 12 %use more time 
%         n=20000;
%         chromlength=15; %字符串长度（个体长度），染色体长度
%         
%     case 13
%         n=20000;
%         chromlength=15; %字符串长度（个体长度），染色体长度
%       
%     otherwise
%         break
% end
% up_range=n;
% down_range=0;
% popsize=62; %设置初始参数，群体大小
% 
% 
% pop=my_sga_initpop(popsize,n,var_num); %运行初始化函数，随机产生初始群体
% 
% 
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
tic;            %用于记录运行时间
% popsize=66; %设置初始参数，群体大小
% L = 6;      % 设置子群体规模

popsize=64; %设置初始参数，群体大小
L = 4;      % 设置子群体规模

S = 1;      % 设置子种群交叠个体个数
% M = 16;     % 设置 子种群个数
M = 21;     % 设置 子种群个数
cont=zeros(1,M); % 子群体计数器
contor = 0;  % 群体计数器
% pc=0.95; %设置交叉概率
% pm=0.05; %设置变异概率
pc=0.1; %设置交叉概率

pm=0.1; %设置变异概率

%参数设置结束
best_fit = [];

% 局部公告板
% local_board_dna = zeros(var_num,M);
% local_board_fitvalue = zeros(1,M);
% % 全局公告板
% global_board_dna = zeros(var_num,1);
% global_board_fitvalue = -999999;

dai=1000;
%给最佳染色体及其适应度值赋初值%
pop_best=zeros(var_num,1);
value_best=-999999;
dai_best=1;

%结束
% i=1;
% max_fitvalue=0;
 %计算群体中每个个体的适应度
fitvalue=my_sga_calfitvalue(pop,fun_num,var_num);
[bestindividual,bestfit]=my_sga_best(popsize,pop,fitvalue);
best_fit(1)=bestfit;
pop_best  = bestindividual;
value_best = bestfit;
old_max_fitvalue=max(fitvalue);
old_max_dna = bestindividual;

for i=1:dai %1000为迭代次数   
    
%     fitvalue=my_sga_calfitvalue(pop,fun_num,var_num);
%     [bestindividual,bestfit]=my_sga_best(popsize,pop,fitvalue);
%     old_max_fitvalue=max(fitvalue);
%     old_max_dna = bestindividual;
    
    start_number = 1;
    end_number = L;
    for j = 1:M
        
%         if subpop_flg(j) ~= 1
            % 子种群初始化
            subpop = pop(:,start_number:end_number);
            % 计算子种群的适应值
            subpop_fitvalue = my_sga_calfitvalue(subpop,fun_num,var_num);
            %左右邻域竞争 
            [sub_newpop]=improve_compete3(L,subpop,subpop_fitvalue,fun_num,up_range,down_range,var_num);
            % 计算适应值
            subpop_fitvalue = my_sga_calfitvalue(sub_newpop,fun_num,var_num);
            %交叉
            [sub_newpop]=complete3_o_crossover(L,sub_newpop,pc,subpop_fitvalue,fun_num,up_range,down_range,var_num);
            %变异
            [sub_newpop]=complete_mutation_cell_new(L,sub_newpop,pm,i,fun_num,var_num);
            % 更新大种群
            pop(:,start_number:end_number)=sub_newpop;
%             %计算群体中每个个体的适应度
%             subpop_fitvalue=my_sga_calfitvalue(subpop,fun_num,var_num);
%             % 求出进化后子种群的最大适应值
%             [new_subpop_fitvalue_max,max_indax] = max(subpop_fitvalue);
%             new_subpop_dna_max = subpop(:,max_indax);
%             % 更新全局最优值
%             if new_subpop_fitvalue_max > value_best
%                 pop_best  = new_subpop_dna_max;
%                 value_best = new_subpop_fitvalue_max;
%                 dai_best=i;
%             end
%         end
        
        % 更新起始终止位
        start_number = end_number - S+1;
        end_number = start_number + L -1;
%         sub_best_fit
    end
    
    fitvalue_tem=my_sga_calfitvalue(pop,fun_num,var_num);
    [bestindividual,bestfit]=my_sga_best(popsize,pop,fitvalue_tem);
    new_max_dna = bestindividual;
    new_max_fitvalue = bestfit;
    
    if new_max_fitvalue > old_max_fitvalue
        pop_best  = new_max_dna;
        value_best = new_max_fitvalue;
        best_fitvalue = value_best;
        best_fit(i+1) = new_max_fitvalue;
        dai_best=i;
        
        old_max_fitvalue=new_max_fitvalue;
        old_max_dna = new_max_dna;
    else
        new_max_fitvalue = old_max_fitvalue;
        pop_best  = old_max_dna;
        value_best = old_max_fitvalue;
        best_fitvalue = value_best;
        best_fit(i+1) = old_max_fitvalue;
        % 精英保留
        [max_value,indax] = max(fitvalue_tem);
        pop(:,indax) = old_max_dna;
        
        old_max_fitvalue=old_max_fitvalue;
        old_max_dna = old_max_dna;
    end
%     fitvalue_aaaa=my_sga_calfitvalue(pop,fun_num,var_num);
%     aaaa = max(fitvalue_aaaa)
%         best_fit
    if  best_fit(i+1) == best_fit(i)
%     if new_max_fitvalue == old_max_fitvalue
        contor = contor + 1;
    else
        
        contor = 0;
    end
    if contor == 10
        out_dai = i;
        break;
    end
     
    if i == dai
        out_dai = i;
        best_fitvalue = best_fit(i);
    end

%     if min(subpop_flg) ~= 0
%         out_dai = i;
%         break;
%         
%     end
%     new_max_value = max(max(sub_best_fit));
%     [temp,subpop_num] = max(sub_best_fit);
%     [new_max_value,best_dai] = max(temp);
%     best_fitvalue = new_max_value;
%     temp_dna = sub_best_dna(:,subpop_num);
%     bestindividual = temp_dna(:,best_dai);
%     best_fit = temp;
%     new_max_value = max(local_board_fitvalue);
%     if new_max_value > old_max_value
%         best_fit(i+1)=new_max_value;
%     else
%         best_fit(i+1)=old_max_value;
%     end
%     best_fitvalue = max(best_fit);
%     if new_max_value == old_max_value
%         contor = contor + 1;
%     else
%         old_max_value = new_max_value;
%         contor = 0;
%     end
%     if contor == 10
%         out_dai = i;
%         break;
%     end
      

end

time = toc;
% 
% 
% plot(-sub_best_fit,'r--')
% 
% sub_best_fit