差分进化算法MATLAB

以下是标准差分进化算法的MATLAB代码示例：

function [bestSol, bestCost, Convergence_curve] = DE(F, nVar, VarMin, VarMax, MaxIt, NP, F1, F2, CR)
    
    % 参数设置
    VarSize = [1 nVar];                     % 决策变量大小
    nPop = NP;                              % 种群大小
    
    % 初始化种群
    pop = repmat(VarMin, nPop, 1) + rand(nPop, nVar) .* (repmat(VarMax, nPop, 1) - repmat(VarMin, nPop, 1));
    costs = zeros(nPop, 1);
    for i = 1:nPop
        costs(i) = F(pop(i, :));
    end
    
    % 优化迭代
    bestSol = zeros(VarSize);
    bestCost = inf;
    Convergence_curve = zeros(MaxIt, 1);
    for it = 1:MaxIt
        for i = 1:nPop
            % 选择个体
            A = randperm(nPop);
            A(A == i) = [];
            r1 = A(1);
            r2 = A(2);
            r3 = A(3);
            
            % 变异
            p = pop(r1, :) + F1 .* (pop(r2, :) - pop(r3, :));
            p = max(p, VarMin);
            p = min(p, VarMax);
            
            % 交叉
            c = rand(VarSize) <= CR;
            p(c) = pop(i, c);
            
            % 选择
            if F(p) < costs(i)
                pop(i, :) = p;
                costs(i) = F(p);
            end
            
            % 更新全局最优解
            if costs(i) < bestCost
                bestCost = costs(i);
                bestSol = pop(i, :);
            end
        end
        
        % 记录收敛曲线
        Convergence_curve(it) = bestCost;
        
        % 输出迭代信息
        fprintf('Iteration %d: Best Cost = %f\n', it, bestCost);
    end
end

其中，`F`为目标函数句柄，`nVar`为决策变量个数，`VarMin`和`VarMax`为决策变量的上下界，`MaxIt`为最大迭代次数，`NP`为种群大小，`F1`和`F2`为差分进化算法的参数，`CR`为交叉概率。算法输出最优解`bestSol`，最优解对应的目标函数值`bestCost`，以及收敛曲线`Convergence_curve`。