Table 8 Parameter setting of various models.
From: The development of CC-TF-BiGRU model for enhancing accuracy in photovoltaic power forecasting
Model | Label | Parameter setting |
|---|---|---|
CC-Transformer | #1 | Sequence_length = 10, batch_size = 64, feature_size = 250, num_layers = 1, nhead = 10, num_epochs = 100 |
CC-CNN-Transformer | #2 | CNN channels=[Input: 13, Conv1: 32, Conv2: 64], Pooling kernel size = 2, sequence_length = 10, batch_size = 64, feature_size = 250, num_layers = 1, nhead = 10, |
CC-BiGRU | #3 | For hidden layer 2, number of nodes = 20; For hidden layer 1, number of nodes = 10 |
CC-CNN-BiGRU | #4 | CNN channels=[Input: 13, Conv1: 64, Conv2: 128], Pooling kernel size = 2, For hidden layer 2, number of nodes = 20; For hidden layer 1, number of nodes = 10 |
CC-TF-BiGRU | #5 | n_estimators = 10; learning_rate = 0.001; For hidden layer 2, number of nodes = 20; For hidden layer 1, number of nodes = 10 |
