基于LSTM-CNN-attention的负荷预测(matlab)

[数学建模加油站]

 1、部分代码 

% 数据集
clc
clear
close all
% addpath('./')
load('Train.mat')
Train.weekend = dummyvar(Train.weekend);
Train.month = dummyvar(Train.month);
Train = movevars(Train,{'weekend','month'},'After','demandLag');
Train.ts = [];

% Train.hour = dummyvar(Train.hour);
%
Train(1,:) =[];
y = Train.demand;
x = Train{:,2:5};
[xnorm,xopt] = mapminmax(x',0,1);
[ynorm,yopt] = mapminmax(y',0,1);
%
% xnorm = [xnorm;Train.weekend';Train.month'];
%%
% x = x';
xnorm = xnorm(:,1:1000);
ynorm = ynorm(1:1000);

k = 24;           % 滞后长度

% 转换成2-D image
for i = 1:length(ynorm)-k

    Train_xNorm(:,i,:) = xnorm(:,i:i+k-1);
    Train_yNorm(i) = ynorm(i+k-1);
    Train_y(i) = y(i+k-1);
end
Train_yNorm= Train_yNorm';



ytest = Train.demand(1001:1170);
xtest = Train{1001:1170,2:5};
[xtestnorm] = mapminmax('apply', xtest',xopt);
[ytestnorm] = mapminmax('apply',ytest',yopt);
% xtestnorm = [xtestnorm; Train.weekend(1001:1170,:)'; Train.month(1001:1170,:)'];
xtest = xtest';
for i = 1:length(ytestnorm)-k
    Test_xNorm(:,i,:) = xtestnorm(:,i:i+k-1);
    Test_yNorm(i) = ytestnorm(i+k-1);
    Test_y(i) = ytest(i+k-1);
end
Test_yNorm = Test_yNorm';

clear k i x y
%
Train_xNorm = dlarray(Train_xNorm,'CBT');
Train_yNorm = dlarray(Train_yNorm,'BC');
Test_xNorm = dlarray(Test_xNorm,'CBT');
Test_yNorm = dlarray(Test_yNorm,'BC');
%% 训练集和验证集划分
TrainSampleLength = length(Train_yNorm);
validatasize = floor(TrainSampleLength * 0.1);
Validata_xNorm = Train_xNorm(:,end - validatasize:end,:);
Validata_yNorm = Train_yNorm(:,TrainSampleLength-validatasize:end);
Validata_y = Train_y(TrainSampleLength-validatasize:end);

Train_xNorm = Train_xNorm(:,1:end-validatasize,:);
Train_yNorm = Train_yNorm(:,1:end-validatasize);
Train_y = Train_y(1:end-validatasize);
%%

%参数设置
inputSize = size(Train_xNorm,1);   %数据输入x的特征维度
outputSize = 1;  %数据输出y的维度  
numhidden_units1=50;

[params,~] = paramsInit(numhidden_units1,inputSize,outputSize);     % 导入初始化参数

[~,validatastate] = paramsInit(numhidden_units1,inputSize,outputSize);     % 导入初始化参数
[~,TestState] = paramsInit(numhidden_units1,inputSize,outputSize);     % 导入初始化参数
% 训练相关参数
TrainOptions;
numIterationsPerEpoch = floor((TrainSampleLength-validatasize)/minibatchsize);
LearnRate = 0.01;
%% Loop over epochs.
figure
start = tic;
lineLossTrain = animatedline('color','r');
validationLoss = animatedline('color','g','Marker','o');
xlabel("Iteration")
ylabel("Loss")

% epoch 更新 
iteration = 0;
for epoch = 1 : numEpochs
   
    [~,state] = paramsInit(numhidden_units1,inputSize,outputSize);       % 每轮epoch，state初始化
    disp(['Epoch: ', int2str(epoch)])
    
    % batch 更新
    for i = 1 : numIterationsPerEpoch
       
        iteration = iteration + 1;
        disp(['Iteration: ', int2str(iteration)])
        idx = (i-1)*minibatchsize+1:i*minibatchsize;
        
        dlX = gpuArray(Train_xNorm(:,idx,:));
        dlY = gpuArray(Train_yNorm(idx));
        [gradients,loss,state] = dlfeval(@TPAModel,dlX,dlY,params,state);
        
        % L2正则化
%         L2regulationFactor = 0.000011;
%         gradients = dlupdate( @(g,parameters) L2Regulation(g,parameters,L2regulationFactor),gradients,params);
%         gradients = dlupdate(@(g) thresholdL2Norm(g, gradientThreshold),gradients);
        
        [params,averageGrad,averageSqGrad] = adamupdate(params,gradients,averageGrad,averageSqGrad,iteration,LearnRate);
        
        
        
        % 验证集测试
        if iteration == 1 || mod(iteration,validationFrequency) == 0
            output_Ynorm = TPAModelPredict(gpuArray(Validata_xNorm),params,validatastate);
            lossValidation = mse(output_Ynorm, gpuArray(Validata_yNorm));
        end

        
        % 作图（训练过程损失图）--------------------------********————————————————————————————————————————————————
        D = duration(0,0,toc(start),'Format','hh:mm:ss');
        addpoints(lineLossTrain,iteration,double(gather(extractdata(loss))))
        if iteration == 1 || mod(iteration,validationFrequency) == 0
            addpoints(validationLoss,iteration,double(gather(extractdata(lossValidation))))
        end
        title("Epoch: " + epoch + ", Elapsed: " + string(D))
        legend('训练集','验证集')
        drawnow
        
    end
    
    % 每轮epoch 更新学习率
    if mod(epoch,5) == 0
        LearnRate = LearnRate * LearnRateDropFactor;
    end
end


%% 训练集
Predict_yNorm = TPAModelPredict(gpuArray(Train_xNorm),params,TestState);
Predict_yNorm = extractdata(Predict_yNorm);

Predict_y = mapminmax('reverse',Predict_yNorm,yopt);
%
figure
plot(Predict_y,'r');
hold on 
plot(Train_y,'g')
legend('训练集预测值','训练集实际值')
%% 验证集
Predict_yNorm = TPAModelPredict(gpuArray(Validata_xNorm),params,TestState);
Predict_yNorm = extractdata(Predict_yNorm);

Predict_y = mapminmax('reverse',Predict_yNorm,yopt);
%
figure
plot(Predict_y,'r');
hold on 
plot(Validata_y,'g')
legend('验证集预测值','验证集实际值')

%%  predict(传统递归测试集)
% clear Predict_yNorm
% % Test_xNorm = extractdata(Test_xNorm);
% for i = 1:size(Test_xNorm,2)
%     if i ==1
%         [a,Teststate] = TPAModelPredict(dlarray(Test_xNorm(:,i,:),'CBT'),params,TestState);
%         Predict_yNorm(i) = extractdata(a);
%     else
% %         a = extractclcdata(Test_xNorm(:,i,:));
%         Test_xNorm(end,i,end)= gather(Predict_yNorm(i-1));
%         [a,Teststate] = TPAModelPredict(dlarray(Test_xNorm(:,i,:),'CBT'),params,TestState);
%         Predict_yNorm(i) = extractdata(a);
%     end
% Predict_YNorm(i) = Predict_yNorm(i);
% end
%% predict(直接测试集)
Predict_yNorm = TPAModelPredict(dlarray(Test_xNorm,'CBT'),params,TestState);
Predict_YNorm = extractdata(Predict_yNorm);
Predict_y = mapminmax('reverse',Predict_YNorm,yopt);
%
figure
plot(Predict_y,'r');
hold on 
plot(Test_y,'g')
legend('测试集预测值','测试集实际值')

2、结果展示

    

       

      

     

      完整代码见基于LSTM-CNN-attention的负荷预测(matlab)-数据 (mianbaoduo.com)