Table 2 The architecture of the encoder and decoder in the used cVAE
From: Boost short-term load forecasts with synthetic data from transferred latent space information
Layers of the encoder | |
|---|---|
Input | [Load data, Calendar information] |
1 | Dense 32, activation: tanh |
2 | Dense 16, activation: tanh |
3 | \(\mu\): Dense latent dimension, activation: linear |
\(\sigma\): Dense latent dimension, activation: linear |
Layers of the decoder | |
|---|---|
Input | [Seed noise, Calendar information] |
1 | Dense 16, activation: tanh |
2 | Dense 32, activation: tanh |
3 | Dense horizon, activation: linear |