PyTorch搭建LSTM实现多变量多步长时间序列预测（三）：多模型单步预测

I. 前言

系列文章：

1. 深入理解PyTorch中LSTM的输入和输出（从input输入到Linear输出）
2. PyTorch搭建LSTM实现时间序列预测（负荷预测）
3. PyTorch搭建LSTM实现多变量时间序列预测（负荷预测）
4. PyTorch搭建双向LSTM实现时间序列预测（负荷预测）
5. PyTorch搭建LSTM实现多变量多步长时间序列预测（一）：直接多输出
6. PyTorch搭建LSTM实现多变量多步长时间序列预测（二）：单步滚动预测
7. PyTorch搭建LSTM实现多变量多步长时间序列预测（三）：多模型单步预测
8. PyTorch搭建LSTM实现多变量多步长时间序列预测（四）：多模型滚动预测
9. PyTorch搭建LSTM实现多变量多步长时间序列预测（五）：seq2seq
10. PyTorch中实现LSTM多步长时间序列预测的几种方法总结（负荷预测）

II. 多模型单步预测

所谓多模型单步预测：比如前10个预测后3个，那么我们可以训练三个模型分别根据[1…10]预测[11]、[12]以及[13]。也就是说如果需要进行n步预测，那么我们一共需要训练n个LSTM模型，缺点很突出。

III. 代码实现

3.1 数据处理

我们根据前24个时刻的负荷以及该时刻的环境变量来预测接下来12个时刻的负荷（步长pred_step_size可调）。

数据处理代码：

# multiple model single step.
def nn_seq_mmss(B, pred_step_size):
    data = load_data()
    # 划分为训练集和测试
    train = data[:int(len(data) * 0.7)]
    test = data[int(len(data) * 0.7):len(data)]

    def process(dataset, batch_size):
        load = dataset[dataset.columns[1]]
        load = load.tolist()
        m, n = np.max(load), np.min(load)
        load = (load - n) / (m - n)
        dataset = dataset.values.tolist()
        # 需要针对每一个步骤返回多个seq
        seqs = [[] for i in range(pred_step_size)]
        for i in range(0, len(dataset) - 24 - pred_step_size, pred_step_size):
            train_seq = []

            for j in range(i, i + 24):
                x = [load[j]]
                for c in range(2, 8):
                    x.append(dataset[j][c])
                train_seq.append(x)
            for j, ind in zip(range(i + 24, i + 24 + pred_step_size), range(pred_step_size)):
                # 形成多个label和seq
                train_label = [load[j]]
                seq = torch.FloatTensor(train_seq)
                train_label = torch.FloatTensor(train_label).view(-1)
                seqs[ind].append((seq, train_label))
        # 形成多个Dte
        res = []
        for seq in seqs:
            seq = MyDataset(seq)
            seq = DataLoader(dataset=seq, batch_size=batch_size, shuffle=False, num_workers=0, drop_last=True)
            res.append(seq)

        return res, [m, n]

    Dtrs, lis1 = process(train, B)
    Dtes, lis2 = process(test, B)

    return Dtrs, Dtes, lis1, lis2

简单来说，如果需要利用前24个值预测接下来12个值，那么我们需要生成12个数据集。

3.2 模型搭建

模型和之前的文章一致：

class LSTM(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, output_size, batch_size):
        super().__init__()
        self.input_size = input_size
        self.hidden_size = hidden_size
        self.num_layers = num_layers
        self.output_size = output_size
        self.num_directions = 1
        self.batch_size = batch_size
        self.lstm = nn.LSTM(self.input_size, self.hidden_size, self.num_layers, batch_first=True)
        self.linear = nn.Linear(self.hidden_size, self.output_size)

    def forward(self, input_seq):
        batch_size, seq_len = input_seq[0], input_seq[1]
        h_0 = torch.randn(self.num_directions * self.num_layers, self.batch_size, self.hidden_size).to(device)
        c_0 = torch.randn(self.num_directions * self.num_layers, self.batch_size, self.hidden_size).to(device)
        # output(batch_size, seq_len, num_directions * hidden_size)
        output, _ = self.lstm(input_seq, (h_0, c_0))
        pred = self.linear(output)
        pred = pred[:, -1, :]
        return pred

3.3 模型训练/测试

与前文不同的是，这种方法需要训练多个模型：

Dtrs, Dtes, lis1, lis2 = load_data(args, flag, batch_size=args.batch_size)
for Dtr, path in zip(Dtrs, LSTM_PATHS):
    train(args, Dtr, path)

模型测试：

def m_test(args, Dtes, lis, PATHS):
    # Dtr, Dte, lis1, lis2 = load_data(args, flag, args.batch_size)
    pred = []
    y = []
    print('loading model...')
    input_size, hidden_size, num_layers = args.input_size, args.hidden_size, args.num_layers
    output_size = args.output_size
    # model = LSTM(input_size, hidden_size, num_layers, output_size, batch_size=args.batch_size).to(device)
    Dtes = [[x for x in iter(Dte)] for Dte in Dtes]
    models = []
    for path in PATHS:
        if args.bidirectional:
            model = BiLSTM(input_size, hidden_size, num_layers, output_size, batch_size=args.batch_size).to(device)
        else:
            model = LSTM(input_size, hidden_size, num_layers, output_size, batch_size=args.batch_size).to(device)
        model.load_state_dict(torch.load(path)['model'])
        model.eval()
        models.append(model)
    print('predicting...')
    for i in range(len(Dtes[0])):
        for j in range(len(Dtes)):
            model = models[j]
            seq, label = Dtes[j][i][0], Dtes[j][i][1]
            label = list(chain.from_iterable(label.data.tolist()))
            y.extend(label)
            seq = seq.to(device)
            with torch.no_grad():
                y_pred = model(seq)
                y_pred = list(chain.from_iterable(y_pred.data.tolist()))
                pred.extend(y_pred)

    y, pred = np.array(y), np.array(pred)
    m, n = lis[0], lis[1]
    y = (m - n) * y + n
    pred = (m - n) * pred + n
    print('mape:', get_mape(y, pred))
    # plot
    x = [i for i in range(1, 151)]
    x_smooth = np.linspace(np.min(x), np.max(x), 900)
    y_smooth = make_interp_spline(x, y[150:300])(x_smooth)
    plt.plot(x_smooth, y_smooth, c='green', marker='*', ms=1, alpha=0.75, label='true')

    y_smooth = make_interp_spline(x, pred[150:300])(x_smooth)
    plt.plot(x_smooth, y_smooth, c='red', marker='o', ms=1, alpha=0.75, label='pred')
    plt.grid(axis='y')
    plt.legend()
    plt.show()

多步预测的每一步，都需要用不同的模型来进行预测。值得注意的是，在正式预测时，数据的batch_size需要设置为1。

3.4 实验结果

前24个预测未来12个，每个模型训练50轮，MAPE为9.94%，还需要进一步完善。

IV. 源码及数据

源码及数据我放在了GitHub上，下载时请随手给个follow和star，感谢！
LSTM-MultiStep-Forecasting