A Short-Term Photovoltaic Power Generation Forecast Method Based on LSTM

Table 6

LSTM-FC parameters setting.

Parameters	Content	Setting
n_LSTM	The number of LSTMs	2
n_FC	Th number of FCs	4
batch_size	The number of batch training samples	64
P	Periodic time interval	13
Adam	Optimization algorithm	—
Relu	Activation function	—
Lr	Learning rate	0.001
Lc	The number of contiguity samples	4
Lp	The number of periodic samples	9
epoch	Iterations	200