Table 2.
Parameter specification of state-of-art machine learning and deep learning forecasting models
| Model | Description |
|---|---|
| SVR | Kernel = RBF,  , 
|
| ANN | 1 hidden layer with 20 neurons and an output layer of 1 neuron |
| DTR | Criterion = ‘mse’, max depth = unlimited, min samples split = 2 |
LSTM
|
LSTM layer with 70 units |
| Output layer with 1 neuron | |
LSTM
|
LSTM layer with 70 units |
| Dense layer with 8 neurons | |
| Output layer with 1 neuron | |
LSTM
|
LSTM layer with 70 units |
| LSTM layer with 30 units | |
| Output layer with 1 neuron | |
LSTM
|
LSTM layer with 50 units |
| LSTM layer with 20 units | |
| Dense layer with 8 neurons | |
| Output layer with 1 neuron |