1 簡介

基于自編LSTM神經(jīng)網(wǎng)絡實現(xiàn)空調能耗數(shù)據(jù)預測。

2 部分代碼

%% 程序說明% ?1、數(shù)據(jù)為7天，四個時間點的空調功耗，用前三個推測第四個訓練，依次類推。第七天作為檢驗% ?2、LSTM網(wǎng)絡輸入結點為12，輸出結點為4個，隱藏結點18個clear all;clc;%% 數(shù)據(jù)加載，并歸一化處理[train_data,test_data]=LSTM_data_process();data_length=size(train_data,1);data_num=size(train_data,2);%% 網(wǎng)絡參數(shù)初始化% 結點數(shù)設置input_num=12;cell_num=18;output_num=4;% 網(wǎng)絡中門的偏置bias_input_gate=rand(1,cell_num);bias_forget_gate=rand(1,cell_num);bias_output_gate=rand(1,cell_num);% ab=1.2;% bias_input_gate=ones(1,cell_num)/ab; ? ?end ? ?if(Error_Cost(1,iter)<cost_gate) ? ? ? ?break; ? ?endend%% 繪制Error-Cost曲線圖% for n=1:1:iter% ? ? text(n,Error_Cost(1,n),'*');% ? ? axis([0,iter,0,1]);% ? ? title('Error-Cost曲線圖'); ? % endfor n=1:1:iter ? ?semilogy(n,Error_Cost(1,n),'*'); ? ?hold on; ? ?title('Error-Cost曲線圖'); ? end%% 使用第七天數(shù)據(jù)檢驗%數(shù)據(jù)加載test_final=[0.4557 0.4790 0.7019 0.8211 0.4601 0.4811 0.7101 0.8298 0.4612 0.4845 0.7188 0.8312]';test_final=test_final/sqrt(sum(test_final.^2));test_output=test_data(:,4);%前饋m=4;gate=tanh(test_final'*weight_input_x+h_state(:,m-1)'*weight_input_h);input_gate_input=test_final'*weight_inputgate_x+cell_state(:,m-1)'*weight_inputgate_c+bias_input_gate;forget_gate_input=test_final'*weight_forgetgate_x+cell_state(:,m-1)'*weight_forgetgate_c+bias_forget_gate;output_gate_input=test_final'*weight_outputgate_x+cell_state(:,m-1)'*weight_outputgate_c+bias_output_gate;for n=1:cell_num ? ?input_gate(1,n)=1/(1+exp(-input_gate_input(1,n))); ? ?forget_gate(1,n)=1/(1+exp(-forget_gate_input(1,n))); ? ?output_gate(1,n)=1/(1+exp(-output_gate_input(1,n)));endcell_state_test=(input_gate.*gate+cell_state(:,m-1)'.*forget_gate)';pre_h_state=tanh(cell_state_test').*output_gate;h_state_test=(pre_h_state*weight_preh_h)'test_output

3 仿真結果

4 參考文獻

[1]徐凌峰, 高洪. 基于LSTM神經(jīng)網(wǎng)絡的乘用車能耗預測[J]. 井岡山大學學報:自然科學版, 2021, 42(5):7.

博主簡介：擅長智能優(yōu)化算法、神經(jīng)網(wǎng)絡預測、信號處理、元胞自動機、圖像處理、路徑規(guī)劃、無人機等多種領域的Matlab仿真，相關matlab代碼問題可私信交流。

部分理論引用網(wǎng)絡文獻，若有侵權聯(lián)系博主刪除。