时间序列预测 — BiLSTM实现多变量多步光伏预测(Tensorflow)

import time
import datetime
import pandas as pd 
import numpy as np 
import matplotlib.pyplot as plt  
from sampen import sampen2  # sampen库用于计算样本熵
from vmdpy import VMD  # VMD分解库

import tensorflow as tf 
from sklearn.cluster import KMeans
from sklearn.metrics import r2_score, mean_squared_error, mean_absolute_error, mean_absolute_percentage_error 
from sklearn.preprocessing import MinMaxScaler
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Activation, Dropout, LSTM, GRU
from tensorflow.keras.callbacks import ReduceLROnPlateau, EarlyStopping

# 忽略警告信息
import warnings
warnings.filterwarnings('ignore')  

# 导入数据
data_raw = pd.read_excel("E:\\课题\\08数据集\\新疆风电光伏数据\\光伏2019.xlsx")
data_raw

from itertools import cycle
# 可视化数据
def visualize_data(data, row, col):
    cycol = cycle('bgrcmk')
    cols = list(data.columns)
    fig, axes = plt.subplots(row, col, figsize=(16, 4))
    fig.tight_layout()
    if row == 1 and col == 1:  # 处理只有1行1列的情况
        axes = [axes]  # 转换为列表，方便统一处理
    for i, ax in enumerate(axes.flat):
        if i < len(cols):
            ax.plot(data.iloc[:,i], c=next(cycol))
            ax.set_title(cols[i])
        else:
            ax.axis('off')  # 如果数据列数小于子图数量，关闭多余的子图
    plt.subplots_adjust(hspace=0.6)
    plt.show()

visualize_data(data_raw.iloc[:,1:], 2, 4)

?

data_raw.info()

?

data_raw.isnull().sum()

?

timesteps = 96*5 #构造x，为96*5个数据,表示每次用前96*5个数据作为一段
predict_steps = 96 #构造y，为96个数据，表示用后96个数据作为一段
length = 96 #预测多步，预测96个数据
feature_num = 7 #特征的数量

# 构造数据集，用于真正预测未来数据
# 整体的思路也就是，前面通过前timesteps个数据训练后面的predict_steps个未来数据
# 预测时取出前timesteps个数据预测未来的predict_steps个未来数据。
def create_dataset(datasetx,datasety,timesteps=36,predict_size=6):
    datax=[]#构造x
    datay=[]#构造y
    for each in range(len(datasetx)-timesteps - predict_steps):
        x = datasetx[each:each+timesteps]
        y = datasety[each+timesteps:each+timesteps+predict_steps]
        datax.append(x)
        datay.append(y)
    return datax, datay

?

# 数据归一化操作
def data_scaler(datax,datay):
    # 数据归一化操作
    scaler1 = MinMaxScaler(feature_range=(0,1))
    scaler2 = MinMaxScaler(feature_range=(0,1))
    datax = scaler1.fit_transform(datax)
    datay = scaler2.fit_transform(datay)
    # 用前面的数据进行训练，留最后的数据进行预测
    trainx, trainy = create_dataset(datax[:-timesteps-predict_steps,:],datay[:-timesteps-predict_steps,0],timesteps, predict_steps)
    trainx = np.array(trainx)
    trainy = np.array(trainy)
    
    return trainx, trainy, scaler1, scaler2

datax = df_vmd[:,:-1]
datay = df_vmd[:,-1].reshape(df_vmd.shape[0],1)
trainx, trainy, scaler1, scaler2 = data_scaler(datax, datay)

?

# # 创建BiLSTM模型
def BiLSTM_model_train(trainx, trainy):
    # 调用GPU加速
    gpus = tf.config.experimental.list_physical_devices(device_type='GPU')
    for gpu in gpus:
        tf.config.experimental.set_memory_growth(gpu, True)
              
    # BiLSTM网络构建 
    start_time = datetime.datetime.now()
    model = Sequential()
    model.add(Bidirectional(LSTM(units=50, return_sequences=True), input_shape=(timesteps, feature_num)))
    model.add(Bidirectional(LSTM(units=100, return_sequences=True), input_shape=(timesteps, feature_num)))
    model.add(Bidirectional(LSTM(units=150)))
    model.add(Dropout(0.1))
    model.add(Dense(predict_steps))
    model.compile(loss='mse', optimizer='adam')
    # 模型训练
    model.fit(trainx, trainy, epochs=50, batch_size=64)
    end_time = datetime.datetime.now()
    running_time = end_time - start_time
    # 保存模型
    model.save('BiLSTM_model.h5')
    
    # 返回构建好的模型
    return model