多维时序 | MATLAB实现WOA-CNN鲸鱼算法优化卷积神经网络的数据多变量时间序列预测
@TOC
效果一览
基本介绍
多维时序 | MATLAB实现WOA-CNN鲸鱼算法优化卷积神经网络的数据多变量时间序列预测
MATLAB实现WOA-CNN鲸鱼算法优化卷积神经网络的数据多变量时间序列预测
输入7个特征，输出1个，即多输入单输出；优化参数为学习率，批大小，正则化系数。
运行环境Matlab2018及以上,运行主程序main即可，其余为函数文件无需运行,所有程序放在一个文件夹,data为数据集；
命令窗口输出RMSE、MAE、R2、MAPE。
程序设计
- 完整程序和数据下载方式：私信我。
%% 记录最佳参数
Best_pos(1, 2) = round(Best_pos(1, 2));
best_lr = Best_pos(1, 1);
best_hd = Best_pos(1, 2);
best_l2 = Best_pos(1, 3);
%% 建立模型
% ---------------------- 修改模型结构时需对应修改fical.m中的模型结构 --------------------------
layers = [
sequenceInputLayer(f_) % 输入层
fullyConnectedLayer(outdim) % 输出回归层
regressionLayer];
%% 参数设置
% ---------------------- 修改模型参数时需对应修改fical.m中的模型参数 --------------------------
options = trainingOptions('adam', ... % Adam 梯度下降算法
'MaxEpochs', 500, ... % 最大训练次数 500
'InitialLearnRate', best_lr, ... % 初始学习率 best_lr
'LearnRateSchedule', 'piecewise', ... % 学习率下降
'LearnRateDropFactor', 0.5, ... % 学习率下降因子 0.1
'LearnRateDropPeriod', 400, ... % 经过 400 次训练后 学习率为 best_lr * 0.5
'Shuffle', 'every-epoch', ... % 每次训练打乱数据集
'ValidationPatience', Inf, ... % 关闭验证
'L2Regularization', best_l2, ... % 正则化参数
'Plots', 'training-progress', ... % 画出曲线
'Verbose', false);
%% 训练模型
net = trainNetwork(p_train, t_train, layers, options);
%% 仿真验证
t_sim1 = predict(net, p_train);
t_sim2 = predict(net, p_test );
%% 数据反归一化
T_sim1 = mapminmax('reverse', t_sim1, ps_output);
T_sim2 = mapminmax('reverse', t_sim2, ps_output);
T_sim1=double(T_sim1);
T_sim2=double(T_sim2);
%% 均方根误差
error1 = sqrt(sum((T_sim1 - T_train).^2) ./ M);
error2 = sqrt(sum((T_sim2 - T_test ).^2) ./ N);
%_________________________________________________________________________%
% The Whale Optimization Algorithm
function [Best_Cost,Best_pos,curve]=WOA(pop,Max_iter,lb,ub,dim,fobj)
% initialize position vector and score for the leader
Best_pos=zeros(1,dim);
Best_Cost=inf; %change this to -inf for maximization problems
%Initialize the positions of search agents
Positions=initialization(pop,dim,ub,lb);
curve=zeros(1,Max_iter);
t=0;% Loop counter
% Main loop
while t<Max_iter
for i=1:size(Positions,1)
% Return back the search agents that go beyond the boundaries of the search space
Flag4ub=Positions(i,:)>ub;
Flag4lb=Positions(i,:)<lb;
Positions(i,:)=(Positions(i,:).*(~(Flag4ub+Flag4lb)))+ub.*Flag4ub+lb.*Flag4lb;
% Calculate objective function for each search agent
fitness=fobj(Positions(i,:));
% Update the leader
if fitness<Best_Cost % Change this to > for maximization problem
Best_Cost=fitness; % Update alpha
Best_pos=Positions(i,:);
end
end
a=2-t*((2)/Max_iter); % a decreases linearly fron 2 to 0 in Eq. (2.3)
% a2 linearly dicreases from -1 to -2 to calculate t in Eq. (3.12)
a2=-1+t*((-1)/Max_iter);
% Update the Position of search agents
for i=1:size(Positions,1)
r1=rand(); % r1 is a random number in [0,1]
r2=rand(); % r2 is a random number in [0,1]
A=2*a*r1-a; % Eq. (2.3) in the paper
C=2*r2; % Eq. (2.4) in the paper
b=1; % parameters in Eq. (2.5)
l=(a2-1)*rand+1; % parameters in Eq. (2.5)
p = rand(); % p in Eq. (2.6)
for j=1:size(Positions,2)
if p<0.5
if abs(A)>=1
rand_leader_index = floor(pop*rand()+1);
X_rand = Positions(rand_leader_index, :);
D_X_rand=abs(C*X_rand(j)-Positions(i,j)); % Eq. (2.7)
Positions(i,j)=X_rand(j)-A*D_X_rand; % Eq. (2.8)
elseif abs(A)<1
D_Leader=abs(C*Best_pos(j)-Positions(i,j)); % Eq. (2.1)
Positions(i,j)=Best_pos(j)-A*D_Leader; % Eq. (2.2)
end
elseif p>=0.5
distance2Leader=abs(Best_pos(j)-Positions(i,j));
% Eq. (2.5)
Positions(i,j)=distance2Leader*exp(b.*l).*cos(l.*2*pi)+Best_pos(j);
end
end
end
t=t+1;
curve(t)=Best_Cost;
[t Best_Cost]
end
参考资料
[1] https://blog.csdn.net/kjm13182345320/article/details/129215161
[2] https://blog.csdn.net/kjm13182345320/article/details/128105718
