效果一览

基本介绍

1.Matlab基于Transformer-LSTM多变量时间序列多步预测；
2.多变量时间序列数据集（负荷数据集），采用前96*2个时刻预测的特征和负荷数据预测未来96个时刻的负荷数据；
3.excel数据方便替换，运行环境matlab2023及以上，展示最后96个时间步的预测对比图，评价指标MAE、MAPE、RMSE、MSE、R2；
注：程序和数据放在一个文件夹。
4.程序语言为matlab，程序可出预测效果图，指标图;
5.代码特点：参数化编程、参数可方便更改、代码编程思路清晰、注释明细。

程序设计

• 完整程序和数据获取方式私信博主回复Matlab基于Transformer-LSTM多变量时间序列多步预测。

%  数据归一化
[p_train, ps_input] = mapminmax(P_train, 0, 1);
p_test = mapminmax('apply', P_test, ps_input);
​
[t_train, ps_output] = mapminmax(T_train, 0, 1);
t_test = mapminmax('apply', T_test, ps_output);
​
%%  数据平铺
​
for i = 1:size(p_train,2)
    trainD{i,:} = (reshape(p_train(:,i),or_dim,[]));
end
​
​
​
for i = 1:size(p_test,2)
    testD{i,:} = (reshape(p_test(:,i),or_dim,[]));
end
​
​
targetD =  t_train';
targetD_test  =  t_test';
​
%% 模型
numChannels = or_dim;
maxPosition = 256*2;
numHeads = 4;
numKeyChannels = numHeads*32;
layers = [ 
    sequenceInputLayer(numChannels,Name="input")
    positionEmbeddingLayer(numChannels,maxPosition,Name="pos-emb");
    additionLayer(2, Name="add")
options = trainingOptions(solver, ...
    'Plots','none', ...
    'MaxEpochs', maxEpochs, ...
    'MiniBatchSize', miniBatchSize, ...
    'Shuffle', shuffle, ...
    'InitialLearnRate', learningRate, ...
    'GradientThreshold', gradientThreshold, ...
    'ExecutionEnvironment', executionEnvironment);
​

参考资料

[1] http://t.csdn.cn/pCWSp
[2] https://download.csdn.net/download/kjm13182345320/87568090?spm=1001.2014.3001.5501
[3] https://blog.csdn.net/kjm13182345320/article/details/129433463?spm=1001.2014.3001.5501