matlab_遗传算法-计算电源规划用_低碳要素引入电源规划决策_建立含碳捕集电厂的低碳电源规划模型

clear [fztjdata,fztjstr]=xlsread('10test_fuhe.xlsx','A1:BB50');%读取数据 [fztjdata1,fztjstr1]=xlsread('10test_canshu2.xlsx','A1:BB50');%读取数据 for i = 1:24; PDS(i) = fztjdata(i,1); PW(i) = fztjdata(i,2); PD(i) = fztjdata(i,1) - fztjdata(i,2); end; for i = 1:15; Pmax(i) = fztjdata1(i,3); Pmin(i) = fztjdata1(i,2); a(i) = fztjdata1(i,4); b(i) = fztjdata1(i,5); c(i) = fztjdata1(i,6); UR(i) = fztjdata1(i,7); DR(i) = fztjdata1(i,8); C(i) = fztjdata1(i,9); a1(i) = fztjdata1(i,10); b1(i) = fztjdata1(i,11); c1(i) = fztjdata1(i,12); end; %初始化种群 Methodset.Method1 = sjfa(PD,PDS,PW,Pmax,Pmin,UR,DR); Methodset.Method2 = sjfa(PD,PDS,PW,Pmax,Pmin,UR,DR); Methodset.Method3 = sjfa(PD,PDS,PW,Pmax,Pmin,UR,DR); Methodset.Method4 = sjfa(PD,PDS,PW,Pmax,Pmin,UR,DR); Methodset.Method5 = sjfa(PD,PDS,PW,Pmax,Pmin,UR,DR); Methodset.Method6 = sjfa(PD,PDS,PW,Pmax,Pmin,UR,DR); Methodset.Method7 = sjfa(PD,PDS,PW,Pmax,Pmin,UR,DR); Methodset.Method8 = sjfa(PD,PDS,PW,Pmax,Pmin,UR,DR); Methodset.Method9 = sjfa(PD,PDS,PW,Pmax,Pmin,UR,DR); Methodset.Method0 = sjfa(PD,PDS,PW,Pmax,Pmin,UR,DR); Methodset1 = Methodset; %初始化最佳种群个体适应度值 ebest = jscb(a,b,c,C,a1,b1,c1,readMethod(Methodset,1)); %最大迭代200次 n = 1; for K = 1:200; %适应度值进行排序:从小到大 for i = 1:9; for j = i + 1:10; if( jscb(a,b,c,C,a1,b1,c1,readMethod(Methodset,i)) > jscb(a,b,c,C,a1,b1,c1,readMethod(Methodset,j)) ) T = readMethod(Methodset,j); Methodset = writeMethod(Methodset,readMethod(Methodset,i),j); Methodset = writeMethod(Methodset,T,i); end; end; end; %若当前种群最佳个体适应度值大于历史最佳种群个体适应度值，则进行替换 for i = 1:10; if( jscb(a,b,c,C,a1,b1,c1,readMethod(Methodset,i)) < ebest ) ubest = readMethod(Methodset,i); ebest = jscb(a,b,c,C,a1,b1,c1,readMethod(Methodset,i)); end; end; %进行选择及重组操作：概率50%，目的是将不够优良的个体剔除种群 for i = 1:10; %将一半的优良个体保留 if( i <= 5 ) %将另一半的优良个体替换 else Methodset = writeMethod(Methodset,sjfa(PD,PDS,PW,Pmax,Pmin,UR,DR),i); end; end; %迭代进行变异操作判断和变异操作 for i = 1:10; %计算并赋值适应度函数值 XE = jscb(a,b,c,C,a1,b1,c1,readMethod(Methodset,i)); %按照概率值（小于30%），决定是否进行变异操作 if( rand(1) < 0.3 && XE ~= ebest) %进行变异操作 T = getVariationMethod(readMethod(Methodset,i),PD,PDS,PW,Pmax,Pmin,UR,DR); Methodset = writeMethod(Methodset,T,i); end; end; %迭代进行交叉操作判断和交叉操作 for i = 1:10; %计算并赋值适应度函数值 XE = jscb(a,b,c,C,a1,b1,c1,readMethod(Methodset,i)); %按照概率值（小于30%），决定是否进行交叉操作 if( rand(1) < 0.3 && XE ~= ebest) %进行交叉操作 T = getCrossMethod(readMethod(Methodset,i),readMethod(Methodset,1),PD,PDS,PW,Pmax,Pmin,UR,DR); Methodset = writeMethod(Methodset,T,i); end; end; %若当前种群最佳个体适应度值大于历史最佳种群个体适应度值，则进行替换 for i = 1:10; if( jscb(a,b,c,C,a1,b1,c1,readMethod(Methodset,i)) < ebest ) ubest = readMethod(Methodset,i); ebest = jscb(a,b,c,C,a1,b1,c1,readMethod(Methodset,i)); end; end; N(n) = K; Q(n) = ebest; n = n+1; disp(n); end; %disp(ebest1); %str = strcat('近似最优解函数值Y=',ebest); %弹出图片 figure('position',[100 50 1000 650],'color',[1 1 1]); plot(N,Q,'r','Linewidth',2); %set(gca,'XTick',0:200:2000); title('遗传算法的迭代曲线'); ylabel('适应度函数值'); xlabel('进化代数(代)'); zoom xon grid on ; %设置应用坐标网格